Determination method, determination program, and information processing device

By dynamically switching between open and closed ReID based on the number of registrants, the method improves person determination accuracy in continuous authentication systems, addressing the challenge of decreased accuracy due to new entrants or exits.

WO2024236765A1PCT designated stage expired Publication Date: 2024-11-21FUJITSU LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
PCT/JP2023/018426
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-17
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

Continuous authentication technologies, such as open ReID and closed ReID, face challenges in maintaining accurate person determination, especially when new individuals enter or exit the authentication space, leading to decreased accuracy in both scenarios.

Method used

A method and device that dynamically switch between open ReID and closed ReID based on the number of registrants within a predetermined time, using a storage unit to store information and determine whether detected individuals are new registrants, adjusting identification standards accordingly to improve accuracy.

Benefits of technology

This approach enhances person determination accuracy by adapting authentication methods to changes in the number of registrants, maintaining high accuracy even when new individuals enter or exit the authentication space, and reduces erroneous authentication.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure JP2023018426_21112024_PF_FP_ABST
    Figure JP2023018426_21112024_PF_FP_ABST
Patent Text Reader

Abstract

This determination method is executed by a computer and comprises: referring to a storage unit that stores information on a registrant; determining whether or not the number of registrants stored in the storage unit has changed within a predetermined time; if a person is detected from an image obtained by photographing a predetermined space, determining whether or not the detected person is the registrant on the basis of a predetermined criterion; if the detected person is determined not to be the registrant and the number of registrants is determined to have changed within the predetermined time, storing the detected person into the storage unit as a new registrant; and if the detected person is determined not to be the registrant and the number of registrants is determined not to have changed within the predetermined time, determining whether or not the detected person is the registrant on the basis of a criterion less strict than the predetermined criterion. 
Need to check novelty before this filing date? Find Prior Art

Description

Determination method, determination program, and information processing device

[0001] The present invention relates to a determination method, a determination program, and an information processing device.

[0002] Techniques for extracting feature information using a camera and performing authentication have been disclosed (see, for example, Patent Document 1 or Non-Patent Document 1).

[0003] JP 2019-128880 A

[0004] GU et al., Clothes-Changing Person Re-identification with RGB Modality Only, IEEE / CVF Conference on Computer Vision and Pattern Recognition, 2022, p. 1050-1059

[0005] In recent years, continuous authentication techniques have been developed that eliminate the need for repeated authentication actions and allow users to continue using services after a single authentication. Continuous authentication, for example, uses open ReID and closed ReID.

[0006] OpenReID is a continuous authentication method that accepts a person detected from an image captured by a camera as a new person if the person is not identified as a pre-registered user. With OpenReID, every time a person is detected from an image, it is determined whether the detected person is a registered user, which can lead to incorrect authentication.

[0007] Closed ReID is a continuous authentication method that does not identify a detected person as a new person even if the detected person is not identified as a registered user. Each time a person is detected from an image, the detected person is associated with one of the registered users without determining whether the detected person is a registered user. Therefore, compared to open ReID, improved association accuracy can be expected. However, if a new person enters or leaves the continuous authentication space, the accuracy of person identification decreases.

[0008] In one aspect, the present invention aims to provide a determination method, a determination program, and an information processing device that can improve the accuracy of person determination.

[0009] In one aspect, the determination method involves a computer executing a process in which the computer references a memory unit that stores information about registered persons, determines whether the number of registered persons stored in the memory unit has changed within a predetermined time period, and if a person is detected from an image obtained by photographing a predetermined space, determines whether the detected person is the registered person based on predetermined criteria, and if it is determined that the detected person is not the registered person and it is determined that the number of registered persons has changed within the predetermined time period, stores the detected person in the memory unit as a new registered person, and if it is determined that the detected person is not the registered person and it is determined that the number of registered persons has not changed within the predetermined time period, determines whether the detected person is the registered person based on criteria that are looser than the predetermined criteria.

[0010] This can improve the accuracy of person determination.

[0011] 1A and 1B are diagrams illustrating people entering and exiting an authentication space. FIG. 1A is a block diagram illustrating an overall configuration of a biometric authentication system according to a first embodiment, and FIG. 1B is a functional block diagram illustrating each function of an information processing device. FIG. 1B is a flowchart illustrating a registration process. FIG. 1C is a diagram illustrating a person table stored in a person registration unit. FIG. 1D is a flowchart illustrating an example of a number of people change observation process executed by an information processing device. FIG. 1E is a flowchart illustrating an example of an open ReID process in step S11. FIG. 1F is a diagram illustrating a specific area user table corresponding to a certain specific area. FIG. 1G is a diagram illustrating the difference between the time when a specific person disappeared from a camera and the time when the specific person appeared in another camera. FIG. 1H is a diagram illustrating a number of people table recorded in a number change recording unit. FIG. 1H is a flowchart illustrating an example of a switching process executed by an information processing device. FIG. 1I is a flowchart illustrating an example of a closed ReID process. FIG. 1I is a diagram illustrating an overview of an embodiment. FIG. 1I is a functional block diagram illustrating each function of an information processing device according to a second embodiment. FIG. 1I is a flowchart illustrating a user update process executed by an information processing device. FIG. 1I is a block diagram illustrating a hardware configuration of an information processing device.

[0012] Biometric authentication is a technology that verifies identity using biometric features such as fingerprints, faces, and veins. In biometric authentication, when identity verification is required, biometric feature data for verification acquired by a biometric sensor is compared (matched) with pre-registered biometric feature data, and identity verification is performed by determining whether the similarity is equal to or exceeds an identity verification threshold. Biometric authentication is used in various fields such as bank ATMs and access control, and has recently begun to be used in cashless payments at supermarkets, convenience stores, and other locations.

[0013] These biometric authentication methods are "point" authentication performed at specific authentication spots, such as in front of an authentication machine. However, with "point" authentication, the authentication state is interrupted when the user leaves the authentication spot, and if the user wishes to receive a service again or at a location where authentication is required multiple times, authentication must be performed each time. Therefore, there is a demand for continuous authentication technology that eliminates the need for repeated authentication and allows the user to continue receiving services with a single authentication.

[0014] Here, we will provide an overview of continuous authentication technology. Continuous authentication mainly involves the following three types of authentication:

[0015] The first is authentication at check-in. At the gate to the continuous authentication space, the user performs highly accurate authentication using palm vein authentication or other methods, and when authentication is successful, a camera captures a photo of the user's appearance, and the characteristic information acquired by the camera is linked to the user's ID as registration information.

[0016] Next, there is linear authentication. In a continuous authentication space, registration information and feature information obtained continuously over time using one or more cameras are used to maintain an authentication state in which a person photographed by a camera is authenticated as a registered user.

[0017] Next, there is re-authentication. For example, if the user enters a blind spot of the camera due to a stranger or a pillar, etc., and the authentication state is interrupted, re-authentication is performed. By performing such authentication, continuous authentication can be performed.

[0018] Continuous authentication may include, for example, open ReID and closed ReID. Open ReID is continuous authentication in which a detected person detected from an image acquired by a camera is accepted as a new person if the person is not identified as a pre-registered user. Open ReID requires a determination as to whether the detected person is a registered user each time a person is detected from an image, which may result in erroneous authentication. Closed ReID is continuous authentication in which a detected person is not accepted as a new person even if the detected person is not identified as a registered user. Closed ReID is continuous authentication in which a detected person is associated with one of the registered users without determining whether the detected person is a registered user each time a person is detected from an image. Therefore, compared to open ReID, improved association accuracy can be expected.

[0019] For example, as shown in FIG. 1( a), when the entry and exit of people into the continuous authentication space is not managed, it is preferable to use open ReID. However, as described above, if an erroneous authentication occurs, the accuracy of person determination decreases. As shown in FIG. 1( b), when no people enter or exit the continuous authentication space, it is preferable to use closed ReID. However, if a new person enters or exits the continuous authentication space, the accuracy of person determination decreases.

[0020] Therefore, in the following embodiments, a determination method, a determination program, and an information processing device that can improve the accuracy of person determination will be described.

[0021] Fig. 2(a) is a block diagram illustrating an example of the overall configuration of a biometric authentication system 200 according to Example 1. As illustrated in Fig. 2(a), the biometric authentication system 200 includes an information processing device 100, a linking camera 110, a tracking camera 120, a biometric sensor 130, etc. These devices are connected via a telecommunications line.

[0022] The linking camera 110 is a camera installed at a gate or the like of the continuous authentication space, and is installed in a position where it is easy to acquire characteristic information of a person. There may be one or more linking cameras 110. The biometric sensor 130 is installed at the gate or the like, and is installed near the linking camera 110.

[0023] The tracking camera 120 is a camera for tracking a person in the continuous authentication space, and is installed on the ceiling or the like to make it easier to track the person. There may be one or more tracking cameras 120. When multiple tracking cameras 120 are installed, the fields of view of two or more tracking cameras 120 may at least partially overlap. Alternatively, the fields of view of each tracking camera 120 may not overlap.

[0024] 2(b) is a functional block diagram showing each function of the information processing device 100. As illustrated in Fig. 2(b), the information processing device 100 functions as an acquisition unit 11, a person detection unit 12, a feature extraction unit 13, a ReID processing unit 14, a person registration unit 15, a user registration unit 16, an authentication processing unit 17, a number of people observation unit 18, a number of people change recording unit 19, a switching unit 20, an output unit 21, and the like.

[0025] Next, each process executed by the information processing device 100 will be described.

[0026] 3 is a flowchart showing the registration process. When each user enters the continuous authentication space, the acquisition unit 11 acquires biometric data for verification from the biometric sensor 130 (step S1). The biometric data in this case is not particularly limited, but may be, for example, fingerprints, veins, irises, etc., and is biometric data with high authentication accuracy.

[0027] Next, the authentication processing unit 17 determines whether the similarity between the biometric data for verification acquired in step S1 and the registered biometric data is equal to or greater than a threshold (step S2). If the determination in step S2 is "No," execution of the flowchart ends. In this case, for example, the user may start over from step S1.

[0028] If the determination in step S2 is "Yes," the ID of the user is identified. In this case, an image of the user is acquired from the linking camera 110 (step S3). In order to register their own characteristic information, the user assumes a posture that makes it easy to acquire the characteristic information. For example, the user faces the linking camera 110 directly.

[0029] Next, the person detection unit 12 detects a person region from the image acquired in step S3 (step S4). Methods for detecting a person region include a method of detecting a person region by background subtraction, and a method of learning person features in advance and detecting person features from an input image.

[0030] Next, the feature extraction unit 13 extracts feature information, which is identification information for identifying the person, from the person area acquired in step S4, and registers the extracted feature information in the person table stored in the person registration unit 15 in association with the specified ID (step S5). Here, the registration information includes the color of clothing, physique, facial features, behavioral features, etc. Then, execution of the flowchart ends. This registration information is feature information for continuous authentication.

[0031] Fig. 4 is a diagram illustrating a person table stored in the person registration unit 15. As illustrated in Fig. 4, in the person table, each ID is linked to a name, registration information, and the like.

[0032] (Number of people change observation process) Fig. 5 is a flowchart showing an example of the number of people change observation process executed by the information processing device 100. The number of people change observation process is executed at a predetermined cycle. An example of the number of people change observation process will be described with reference to Fig. 5 .

[0033] First, the ReID processing unit 14 executes open ReID processing for a specific area (step S11). Here, the specific area may be a part or all of the continuous authentication space. For example, the continuous authentication space may be divided into multiple specific areas. Since the position and shooting range of the tracking camera 120 are predetermined, the correspondence between each specific area and each tracking camera 120 may be determined in advance. The following explanation focuses on one specific area.

[0034] 6 is a flowchart showing an example of the open ReID process in step S11. First, the acquisition unit 11 acquires images from each tracking camera 120 (step S21).

[0035] Next, the person detection unit 12 detects a person region from each image acquired in step S21 (step S22). Methods for detecting a person region include a method of detecting a moving object region by background subtraction, and a method of learning person features in advance and detecting person features from input images.

[0036] Next, the feature extraction unit 13 extracts feature information from the image for each person region detected in step S22 and stores the feature information corresponding to the person region (step S23). Here, the feature information from the image includes the color of clothing, physique, facial features, behavioral features, etc.

[0037] Next, the ReID processing unit 14 compares the feature information of people detected simultaneously by different tracking cameras 120, or compares the feature information of people detected at a predetermined time interval by the same tracking camera 120, and if the similarity between the feature information is equal to or greater than a threshold, determines that the people are the same person (step S24). By executing step S24, it is possible to narrow down the people to be subject to ReID processing.

[0038] Next, the ReID processing unit 14 identifies, for each of the targets of the ReID processing narrowed down in step S24, which ID of the user is registered in the person table of the person registration unit 15 (step S25). For example, the ReID processing unit 14 identifies, for the target of the ReID processing, the user of the ID of the registration information that has the highest similarity between the characteristic information extracted in step S22 and the registration information registered in the person table.

[0039] Next, the ReID processing unit 14 registers the users identified from the results of step S25 in the specific area user table and stores the registered users in the user registration unit 16 (step S26). FIG. 7 is a diagram illustrating a specific area user table corresponding to a specific area. In the example of FIG. 7, Mr. A, Mr. B, Mr. C, and Mr. D are identified in the specific area. Note that the specific area user table may associate registration information corresponding to each person. This registration information can be obtained from the person table. Execution of the flowchart then ends. This process makes it possible to count the number of people in the specific area. Furthermore, a person detected from the image who is not registered in the specific area user table can be registered as a new person in the specific area user table.

[0040] 5 again. After step S11 is executed, the number of people observing unit 18 counts the number of people in the specific area (step S12). The number of people observing unit 18 counts the number of people in the specific area by referring to the specific area user table stored in the user registration unit 16.

[0041] Next, the number of people observing unit 18 observes the passage of time (step S13). For example, the number of people observing unit 18 may count the time from the time when step S13 is first executed.

[0042] Next, the number of people observation unit 18 determines whether a certain period T1 has elapsed (step S14). If the determination in step S14 is "No," the process is repeated from step S11. For example, the period during which the same person is detected by different tracking cameras 120 within a specific area is observed, and the longest period is set as the certain period T1. Alternatively, the time it takes for the person to travel the greatest distance between the installed tracking cameras 120 is set as the certain period T1. For example, the certain period T1 (e.g., 10 seconds) is set as the difference between the time when a specific person is no longer detected by one camera and the time when the specific person begins to be detected by another camera. For example, as illustrated in FIG. 8, the certain period T1 is set as the difference between the time when the specific person disappears from camera 002 (exit time) and the time when the specific person appears from camera 003 (appearance time).

[0043] If the answer to step S14 is "Yes," the number-of-users observing unit 18 stores the number of users (step S15).

[0044] Next, the number of people observing unit 18 records the change in users (step S16). For example, the number of people observing unit 18 refers to the specific area user table in the user registration unit 16, and records whether or not the IDs registered in the specific area user table have changed in the number of people table in the number of people change recording unit 19. Figure 9 is a diagram illustrating an example of the number of people table recorded in the number of people change recording unit 19.

[0045] (Switching Process) Fig. 10 is a flowchart showing an example of switching process executed by the information processing device 100. The switching process is executed at a predetermined cycle. The switching process is also executed in parallel with the number of people change observation process. An example of the switching process will be described with reference to Fig. 10.

[0046] First, the switching unit 20 refers to the number-of-users change recording unit 19 and checks whether a user has been replaced (step S31).

[0047] Next, the switching unit 20 determines whether the user has been changed (step S32). If the determination in step S32 is "Yes", the process is executed again from step S31.

[0048] If the determination in step S32 is "No", the switching unit 20 compares the number of people (step S33).

[0049] Next, the switching unit 20 determines whether the number of people has changed within the specified period T2 (step S34). For example, it determines whether the number of people has increased or decreased.

[0050] If step S34 returns "Yes," the switching unit 20 designates the open ReID process (step S35). This causes the ReID processing unit 14 to execute the open ReID process described with reference to FIG. 6. If step S34 returns "No," the switching unit 20 designates the closed ReID process (step S36). This causes the ReID processing unit 14 to execute the closed ReID process. For example, the output unit 21 outputs, to an external device or the like, information indicating whether the open ReID process was designated or the closed ReID process was executed. This allows, for example, an administrator to know which ReID process is being executed.

[0051] 11 is a flowchart showing an example of a closed ReID process. The flowchart in FIG. 11 is repeated at a predetermined interval. First, the acquisition unit 11 acquires images from each tracking camera 120 (step S41).

[0052] Next, the person detection unit 12 detects a person region from each image acquired in step S41 (step S42). Methods for detecting a person region include a method of detecting a moving object region by background subtraction, and a method of learning person features in advance and detecting person features from input images.

[0053] Next, the feature extraction unit 13 extracts feature information from the image for each person region detected in step S42 and stores the feature information corresponding to the person region (step S43). Here, the feature information from the image includes the color of clothing, physique, facial features, behavioral features, etc.

[0054] Next, the ReID processing unit 14 compares the characteristic information of the person detected between different tracking cameras 120 or the same tracking camera 120 at a predetermined time difference, and if the similarity between the characteristic information is equal to or greater than a threshold, determines that the person is the same person (step S44). Note that for each person, the ID and name of each person identified in the open ReID process of FIG. 6 can be inherited, thereby making it possible to identify each person's ID and name. This allows each person to be tracked.

[0055] Next, the ReID processing unit 14 determines whether there is any person who has not been determined to be the same person (step S45). If the determination in step S45 is "No", the execution of the flowchart ends.

[0056] If the answer to step S45 is "Yes," the ReID processing unit 14 associates the persons who are not determined to be the same person among the persons stored in the specific area user table stored in the user registration unit 16 (step S46). Then, execution of the flowchart ends.

[0057] According to this embodiment, as illustrated in FIG. 12 , if there is a change in the number of people in a specific area, open ReID processing is executed. This makes it possible to identify people entering and leaving the specific area. On the other hand, if there is no change in the number of people in the specific area, the area is considered to be a pseudo-closed room with no entry or exit, or an area where entry and exit are controlled, and closed ReID processing is executed. This improves the accuracy of association. As described above, according to this embodiment, it is possible to improve the accuracy of person determination. Note that closed ReID performs association on limited people who have been counted within the specific area and authenticated once, so high accuracy and reduced processing time can be expected.

[0058] For example, in a large space such as an airport, authentication areas are sometimes set up by dividing the area into predetermined sections. Furthermore, if people are free to enter and exit the authentication area, even if a person is staying within the authentication area, it is possible that the person cannot be correctly authenticated due to overlap or angle, and the person may be mistakenly authenticated as a new person. By applying this embodiment to such a case, it is possible to suppress a decrease in the authentication accuracy for people staying within the authentication area.

[0059] In this embodiment, the open ReID process identifies a person based on strict criteria by comparing the registration information registered in the specific area user table with the characteristic information of the person detected from the image. The closed ReID process associates the registration information registered in the specific area user table with the characteristic information of the person detected from the image without comparing it, so the criteria for identifying the person are looser than those in the open ReID process. However, the process is not limited to this.

[0060] For example, in the closed ReID process, the similarity threshold for matching with registered information may be lowered, which can prevent the person from being identified as a new person and improve the accuracy of matching.

[0061] In the second embodiment, updating of users who use a specific area will be described. Differences from the first embodiment will be described.

[0062] 13 is a functional block diagram illustrating each function of an information processing apparatus 100a according to Example 2. As illustrated in FIG.

[0063] (User Update Processing) Fig. 14 is a flowchart illustrating the user update processing executed by the information processing device 100a. The user update processing is executed in parallel with the number of people change observation processing and the switching processing described above. An example of the user update processing will be described with reference to Fig. 14.

[0064] The user update unit 22 compares the number of users counted in step S12 of FIG. 5 with the number of users registered in the specific area user table (step S51).

[0065] Next, the user update unit 22 determines whether the number of registered users is greater than the number of people counted in step S51 (step S52). If the determination in step S52 is "No," the process is executed again from step S51.

[0066] If the answer to step S52 is "Yes," the exit time in the specific area user table is checked (step S53).

[0067] Next, the user update unit 22 determines whether the specified period T2 has elapsed since the exit time (step S54). If the determination in step S54 is "No", the process is executed again from step S51.

[0068] If the answer to step S54 is "Yes," the user update unit 22 updates the specific area user table (step S55). For example, for people registered in the specific area user table who were not identified in the specific area, the user is deleted or the current time is registered as the exit time. Then, the process is executed again from step S51.

[0069] FIG. 15 is a block diagram illustrating an example of the hardware configuration of the information processing device 100, 100a. As illustrated in FIG. 15, the information processing device 100, 100a includes a CPU 101, a RAM 102, a storage device 103, and the like. The CPU (Central Processing Unit) 101 is a central processing unit. The RAM (Random Access Memory) 102 is a volatile memory that temporarily stores programs executed by the CPU 101, data processed by the CPU 101, and the like. The storage device 103 is a non-volatile storage device. For example, the storage device 103 may be a read-only memory (ROM), a solid-state drive (SSD) such as a flash memory, or a hard disk driven by a hard disk drive. The CPU 101 executes a determination program stored in the storage device 103 to realize the functions of each unit of the information processing device 100, 100a. The functions of each part of the information processing apparatus 100, 100a may be configured by a dedicated circuit or the like.

[0070] In each of the above examples, the user registration unit 16 is an example of a storage unit that stores information about registrants. The number-of-people observation unit 18 is an example of a determination unit that refers to the storage unit and determines whether the number of registrants stored in the storage unit has changed within a predetermined time. When a person is detected from an image obtained by photographing a predetermined space, the switching unit 20 and the ReID processing unit 14 determine whether the detected person is the registrant based on predetermined criteria. When the detected person is determined to be not the registrant and the number of registrants has changed within a predetermined time, the switching unit 20 and the ReID processing unit 14 store the detected person in the storage unit as a new registrant. When the detected person is determined to be not the registrant and the number of registrants has not changed within a predetermined time, the switching unit 20 and the ReID processing unit 14 are an example of a processing unit that determines whether the detected person is the registrant based on criteria that are looser than the predetermined criteria.

[0071] Although the embodiments of the present invention have been described in detail above, the present invention is not limited to such specific embodiments, and various modifications and changes are possible within the scope of the gist of the present invention as described in the claims.

[0072] REFERENCE SIGNS LIST 11 Acquisition unit 12 Person detection unit 13 Feature extraction unit 14 ReID processing unit 15 Person registration unit 16 User registration unit 17 Authentication processing unit 18 Number of people observation unit 19 Number of people change recording unit 20 Switching unit 21 Output unit 22 User update unit 100 Information processing device 110 Linking camera 120 Tracking camera 130 Biometric sensor 200 Biometric authentication system

Claims

1. A determination method characterized by being executed by a computer to perform the following processes: referencing a memory unit that stores information about registered persons, and determining whether the number of registered persons stored in the memory unit has changed within a specified time; if a person is detected from an image obtained by photographing a specified space, determining whether the detected person is a registered person based on specified criteria; if it is determined that the detected person is not a registered person and it is determined that the number of registered persons has changed within the specified time, storing the detected person in the memory unit as a new registered person; and if it is determined that the detected person is not a registered person and it is determined that the number of registered persons has not changed within the specified time, determining whether the detected person is a registered person based on criteria that are looser than the specified criteria.

2. The method of determining whether or not the detected person is a registered person, characterized in that if it is determined that the detected person is not a registered person and if it is determined that the number of registered people has not changed within a specified time, the computer executes a process of matching the detected person to one of the registered people stored in the memory unit.

3. The method of determining whether or not a person is present, characterized in that the computer executes a process of updating the information stored in the memory unit depending on the number of people counted from an image obtained by photographing the specified space.

4. The method according to claim 1, wherein the case where the number of registered persons changes within a predetermined period of time is a case where the number of registered persons increases within a predetermined period of time.

5. The method according to claim 1, wherein the case where the number of registered persons changes within a predetermined period of time is a case where the number of registered persons decreases within a predetermined period of time.

6. A determination program that causes a computer to execute the following processes: refer to a memory unit that stores information about registered persons, and determine whether the number of registered persons stored in the memory unit has changed within a specified time; if a person is detected from an image obtained by photographing a specified space, determine whether the detected person is a registered person based on specified criteria; if it is determined that the detected person is not a registered person and it is determined that the number of registered persons has changed within the specified time, store the detected person in the memory unit as a new registered person; and if it is determined that the detected person is not a registered person and it is determined that the number of registered persons has not changed within the specified time, determine whether the detected person is a registered person based on criteria that are looser than the specified criteria.

7. The determination program of claim 6, further comprising: causing the computer to execute a process of associating the detected person with one of the registered persons stored in the memory unit when it is determined that the detected person is not a registered person and when it is determined that the number of registered persons has not changed within a predetermined period of time.

8. The judgment program according to claim 6, characterized in that the computer is caused to execute a process of updating the information stored in the memory unit depending on the number of people counted from an image obtained by photographing the specified space.

9. The judgment program according to claim 6, wherein the case where the number of registered persons changes within a predetermined period of time is a case where the number of registered persons increases within a predetermined period of time.

10. The judgment program according to claim 6, wherein the case where the number of registered persons changes within a predetermined period of time is a case where the number of registered persons decreases within a predetermined period of time.

11. An information processing device comprising: a judgment unit that refers to a memory unit that stores information about registered persons, and judges whether the number of registered persons stored in the memory unit has changed within a specified time; and a processing unit that, when a person is detected from an image obtained by photographing a specified space, judges whether the detected person is a registered person based on specified criteria, and if it is determined that the detected person is not a registered person and it is determined that the number of registered persons has changed within the specified time, stores the detected person in the memory unit as a new registered person, and if it is determined that the detected person is not a registered person and it is determined that the number of registered persons has not changed within the specified time, judges whether the detected person is a registered person based on criteria that are looser than the specified criteria.

12. The information processing device of claim 11, characterized in that when the processing unit determines that the detected person is not a registered person and that the number of registered people has not changed within a predetermined time, the processing unit associates the detected person with one of the registered people stored in the memory unit.

13. An information processing device according to claim 11, further comprising an update unit that updates the information stored in the memory unit according to the number of people counted from an image obtained by photographing the specified space.

14. The information processing device according to claim 11, wherein the case where the number of registered users changes within a predetermined period of time is a case where the number of registered users increases within a predetermined period of time.

15. The information processing device according to claim 11, wherein the case where the number of registered users changes within a predetermined period of time is a case where the number of registered users decreases within a predetermined period of time.

Citation Information

Patent Citations

  • Biometric authentication device, biometric authentication method, computer program for biometric authentication and computer system

    JP2010146073A

  • Image processing apparatus, image processing method, and image processing program

    JP2010199701A