JP6697170B2 - Information processing device, information processing method, and program - Google Patents

Description

  The present invention relates to a telework management system.

  In recent years, with the development of broadband and information security technology, as well as the focus on business continuity and power saving measures in the event of a disaster, interest in telework is increasing in each company. When introducing telework, it is difficult for the administrator to see what is happening, so there is the risk that confidential information will be leaked when a third party, such as a family member, accesses the information processing terminal, and that labor management will be difficult.

  As a means for preventing leakage of confidential information, a prior art has been studied in which face recognition technology is used to perform personal authentication, and if the person is not the person himself / herself, the information processing terminal is locked. Face recognition technology is a technology for detecting the face of a person or the like and reading the attribute information thereof. In personal authentication using face recognition technology (face authentication), a discriminator that has learned the feature amount calculated from the face image calculates the similarity with the feature amount calculated from other face images and identifies the person with that face. It is a technology to do. At the time of learning, the same person is associated with the same identifier for learning.

JP, 2009-212381, A

  In the telework management system using face recognition as in the above-mentioned Patent Document 1, the preventive function is emphasized, and from what time until what time the person was present in front of the information processing terminal or was absent. , There is no mechanism for the manager to know the labor situation. Further, it is premised that the accuracy of face recognition is high, and no mention is made of the condition that the accuracy of the face recognition technology that can be used is low. Under such a condition, the information processing terminal may not be frequently used or may be used by a person other than the person himself or herself.

  Face recognition technology may not be able to detect a face or may not be able to successfully authenticate an individual depending on lighting conditions, makeup, face orientation, presence of glasses, and the like. In telework, fluctuations in these conditions may occur frequently.

  The simplest method to improve the authentication accuracy is to remove the difference between the face image to be learned (the feature amount of it) and the face image to be authenticated (the feature amount) as much as possible. Learning face images is useful. However, since the labor manager of the teleworker needs to guarantee that the face image belongs to the teleworker himself, the burden on the manager increases.

  Therefore, an object of the present invention is to provide a mechanism capable of recording the labor status of a teleworker and the trail of a security incident while suppressing the burden on the administrator.

  An information processing apparatus of the present invention includes an acquisition unit that acquires a face image of a user captured by an image capturing apparatus, a feature amount calculated from the face image of the user acquired by the acquisition unit, and a face image registered in advance. Similarity calculation means for calculating the similarity with the feature amount, event detection means for detecting an event based on the image taken by the image pickup device, and notification means for notifying an administrator of the event detected by the detection means And the event detecting means, if the similarity calculated by the similarity calculating means satisfies a first threshold and if the similarity does not satisfy the first threshold and the second threshold, An event is detected based on the registered feature amount of the face image and the image captured by the imaging device, and the similarity calculated by the similarity calculating unit does not satisfy the first threshold value, and the second When the threshold value is satisfied, the event is detected based on the feature amount of the face image acquired by the acquisition unit and the image captured by the imaging device.

  Further, in the information processing method of the present invention, the acquisition unit of the information processing apparatus acquires the face image of the user photographed by the imaging apparatus, and the similarity calculation unit of the information processing apparatus includes the acquisition step. The similarity calculating step of calculating the similarity between the feature amount calculated from the acquired face image of the user and the feature amount of the face image registered in advance, and the event detecting means of the information processing device, The event detecting step includes an event detecting step of detecting an event based on a captured image, and a notification step of notifying the event of the event detected by the detecting step to the administrator. If the similarity calculated by the similarity calculating step satisfies a first threshold value and if the first threshold value and the second threshold value are not satisfied, the feature amount of the face image registered in advance, When an event is detected based on the image captured by the image capturing device and the similarity calculated by the similarity calculation step does not satisfy the first threshold but the second threshold, the event is acquired by the acquisition step. An event is detected based on the feature amount of the face image and the image captured by the imaging device.

  Further, the program of the present invention is a program that can be executed by an information processing device, and the information processing device includes an acquisition unit that acquires a face image of a user captured by an imaging device, and a user that is acquired by the acquisition unit. Similarity calculating means for calculating the similarity between the feature amount calculated from the face image and the feature amount of the face image registered in advance, and event detecting means for detecting an event based on the image captured by the imaging device. And when the similarity detected by the similarity calculation means satisfies the first threshold value, the event detection means is caused to function as a notification means for notifying an administrator of the event detected by the detection means. , And if the first threshold value and the second threshold value are not satisfied, an event is detected based on the feature amount of the face image registered in advance and the image captured by the imaging device, and the similarity calculation is performed. When the similarity calculated by the means does not satisfy the first threshold value and does not satisfy the second threshold value, an event is generated based on the feature amount of the face image acquired by the acquisition means and the image captured by the imaging device. It is characterized by functioning as a means for detecting.

  According to the present invention, it is possible to provide a mechanism capable of recording the labor status of a teleworker and the trail of a security incident while suppressing the burden on the administrator.

It is a system block diagram which shows an example of a structure of the telework management system of this invention. FIG. 3 is a block diagram showing a hardware configuration of an information processing apparatus applicable to the trail transmission terminal 100, the trail audit terminal 110, and the trail management server 120 shown in FIG. 1. FIG. 2 is a block diagram showing a functional configuration required for a trail transmission terminal 100, a trail inspection terminal 110, and a trail management server 120 shown in FIG. 1. It is a flowchart which shows an example of the whole process of the trail transmission apparatus in the telework management system in this invention. It is a flowchart which shows an example of the personal authentication process of the trail transmission apparatus in the telework management system in this invention. It is a flow chart which shows an example of processing of registration and approval of temporary feature amount data in a telework management system in the present invention. It is a flow chart which shows an example of processing of detection of an event and transmission of the trail in the telework management system in the present invention. It is a data structure diagram showing an example of the data table in which the manager information in the telework management system in this invention was registered. It is a data structure diagram showing an example of the data table in which the teleworker information in the telework management system in this invention was registered. It is a data structure diagram showing an example of the data table in which the identifier information in the telework management system in this invention was registered. It is a data structure figure showing an example of the data table with which the feature-value data in the telework management system in this invention was registered. It is a data structure figure showing an example of a data table with which frame information was registered in a telework management system in the present invention. It is a data structure diagram showing an example of the data table in which the face detection result in the telework management system in this invention was registered. It is a data structure diagram showing an example of the data table in which the face identification result in the telework management system in this invention was registered. It is a data structure figure showing an example of the data table with which the trail information in the telework management system in the present invention was registered. It is a screen image which shows an example of the screen which the user operates in the telework management system in this invention. It is a screen image which shows an example of the screen which the user operates in the telework management system in this invention. It is a figure which shows an example of the data table with which the 1st threshold value and 2nd threshold value for calculating | requiring the authentication level in the telework management system in this invention were registered.

  First, the outline of the present invention will be described.

  The telework management system of the present invention uses face recognition technology to detect teleworker events (labor events such as "seating" and "leaving" and security incidents of "spoofing" and "peeping" by a third party). It is a system that records and allows the administrator to browse.

  When the teleworker starts to work, he / she takes a picture of the face of the teleworker and performs personal authentication using the face picture and the feature amount of the face image that is guaranteed to be the teleworker himself first, and then the teleworker himself. A degree of possibility (authentication level) is calculated (hereinafter, the face image and its feature amount are collectively referred to as feature amount data, and feature amount data used for personal authentication is referred to as authentication feature amount data).

  For example, if the possibility of being a teleworker is extremely high, "high" is likely, but if the teleworker is likely to be a third party, "medium", it is very likely to be a third party. In case of "low". As for the authentication level, the authentication level is calculated by calculating the similarity between the feature amount calculated from the face photograph and the authentication feature amount data, and using a predetermined threshold value and the similarity.

  When the authentication level is “high”, there is little difference between the authentication feature amount data and the feature amount data of the person shown in the image, and therefore the event is detected using the authentication feature amount data.

  When the authentication level is "medium", there is a slight difference between the authentication feature amount data and the feature amount data of the person shown in the image. Therefore, the feature amount data (hereinafter, temporary feature amount data) is newly added from the face shown in the current image. And) and use it to detect events. As a result, even if a slight difference is found from the characteristic amount data (authentication characteristic amount data) guaranteed by the administrator, the event can be normally detected.

  However, since the temporary feature amount data may be of a third party, the feature amount data is recorded and the administrator is asked to confirm it. If the administrator determines that the temporary feature amount data belongs to a third party, immediately cancels the event detection in the temporary feature amount data and uses the authentication feature amount data to detect the event. . Further, when it is determined that the temporary feature amount data is suitable for future teleworker authentication, the administrator registers the temporary feature amount data as the authentication feature amount data.

  When the authentication level is “low”, it is highly possible that the third party is the third party, and therefore the event is detected using the authentication feature amount data. In this case, it is considered that "spoofing" occurs frequently. However, for example, a person who normally wears makeup may not wear makeup, or a person who does not wear glasses may wear glasses, so temporary feature data may be newly added from the current image. Obtain, record, and have the administrator confirm. When the administrator determines that the temporary feature amount data is for a teleworker, the temporary feature amount data is used to detect the event.

  The above is the outline of the telework management system in the present invention.

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

  FIG. 1 is a system configuration diagram showing an example of the configuration of a telework management system of the present invention.

  In FIG. 1, one or a plurality of trail transmission terminals 100, one or a plurality of trail audit terminals 110, and one or a plurality of trail management servers 120 are connected via a local area network (LAN) 130, a router 140, and the Internet 150. It is configured to be.

  The trail transmitting terminal 100 detects a labor event and a security incident of a teleworker to be used, and transmits the trail to the trail management server 120. Also, the feature amount data of the teleworker used for event detection (face image and feature amount acquired from it) is transmitted to the trail management server 120.

  The trail audit terminal 110 performs an operation of approving the feature amount data recorded in the trail management server 120 and an operation of auditing the trail recorded in the trail management server 120.

  The trail management server 120 records the trail received from the trail sending terminal 100, and processes the audit operation of the trail auditing terminal 110 for the trail. Further, the feature amount data received from the trail transmission terminal 100 is recorded, and the approval operation of the trail inspection terminal 110 for the feature amount data is processed.

  The hardware configuration of the information processing apparatus applicable to the trail transmission terminal 100, the trail audit terminal 110, and the trail management server 120 shown in FIG. 1 will be described below with reference to FIG.

  FIG. 2 is a block diagram showing a hardware configuration of an information processing apparatus applicable to the trail transmitting terminal 100, the trail auditing terminal 110, and the trail management server 120 shown in FIG.

  In FIG. 2, reference numeral 201 denotes a CPU, which centrally controls each device and controller connected to the system bus 204. Further, the ROM 203 or the external memory 212 is necessary to realize a control program of the CPU 201, such as a BIOS (Basic Input / Output System), an operating system program (hereinafter, OS), and a function executed by each server or each PC. Various programs described later are stored.

  A RAM 203 functions as a main memory and a work area of the CPU 201. The CPU 201 implements various operations by loading a program or the like required for executing the processing from the ROM 203 or the external memory 212 into the RAM 202 and executing the loaded program.

  An input controller 205 controls input from a keyboard (KB) 209, a camera device 210 (imaging device), a pointing device such as a mouse (not shown), or the like. A video controller 206 controls display on a display such as a CRT display (CRT) 211. In addition, although it is described as CRT 211 in FIG. 2, the display is not limited to the CRT, and may be another display such as a liquid crystal display. These are used by the administrator as needed.

  A memory controller 207 is installed in an external storage device (hard disk (HD)), a flexible disk (FD), or a PCMCIA card slot that stores a boot program, various applications, font data, user files, edit files, various data, and the like. It controls access to an external memory 212 such as a CompactFlash (registered trademark) memory connected via an adapter.

  A communication I / F controller 208 connects and communicates with an external device via a network (for example, the LAN 130 shown in FIG. 1) and executes communication control processing on the network. For example, communication using TCP / IP is possible.

  Note that the CPU 201 enables display on the CRT 211 by executing outline font rasterization processing in a display information area in the RAM 202, for example. Further, the CPU 201 enables a user instruction with a mouse cursor or the like (not shown) on the CRT 211.

  Various programs to be described later for implementing the present invention are recorded in the external memory 212, and are executed by the CPU 201 by being loaded into the RAM 202 as necessary. Furthermore, the definition file and various information tables used when the above program is executed are also stored in the external memory 212, and a detailed description thereof will be given later.

  Next, a functional block diagram of the trail transmission terminal 100, the trail inspection terminal 110, and the trail management server 120 of the present invention will be described with reference to FIG.

  The detailed control that each functional block processes will be described with reference to the flowcharts described later.

  First, the functional configuration of the trail transmission terminal 100 will be described.

  The video input unit 101 acquires a video from the camera device 210 and transmits the video to the personal authentication unit 102. When the processing of the personal authentication unit 102 is completed, the video is transmitted to the event detection unit 106.

  The personal authentication unit 102 supplies the face frame (still image) sent from the image input unit 101 and the feature amount of the feature amount data acquired from the feature amount data storage unit 104 to the face recognition unit 103, and the face recognition unit 103. The possibility (authentication level) of the teleworker in the image is calculated as "high", "medium", and "low" from the face identification result obtained from the. When the authentication level is "high", the feature amount used for authentication is specified as the feature amount used for event detection. In the case of “medium” and “low”, the face image and its temporary feature amount are acquired from the frame and stored in the feature amount data storage unit 104.

  The face recognition unit 103 performs face detection on the frame sent from the personal authentication unit 102 or the event detection unit 106. Further, the degree of similarity with the designated feature amount is calculated for the detected face.

The feature amount data storage unit 104 stores feature amount data including a face image and its feature amount.

  The characteristic amount data transmitting unit 105 transmits the characteristic amount data transmitted from the personal authentication unit 102 to the characteristic amount data receiving unit 121 of the trail management server 120 via the communication I / F controller 208.

  The event detection unit 106 supplies the frame of the video acquired from the video input unit 101 and the feature amount data specified by the personal authentication unit to the face recognition unit 103, and based on the face recognition result obtained from the face recognition unit 103. Detects events such as seating, leaving, spoofing, and peering. The trail of the detected event is transmitted to the trail control unit 107.

  The trail control unit 107 stores the trail obtained from the event detection unit 106 in the trail storage unit 108. When a specific transmission condition is satisfied (for example, 3 minutes have elapsed since the leaving event occurred), the trail recorded in the trail storage unit 108 is transmitted to the trail transmission unit 109. Further, the trail that has been transmitted or is no longer necessary to be transmitted (for example, a seating event has occurred within 3 minutes after the leaving event occurred) is deleted from the trail storage unit 108.

  The trail storage unit 108 stores the trail of the event.

  The trail transmission unit 109 transmits the trail obtained from the trail control unit 107 to the trail reception unit 125 of the trail management server 120 via the communication I / F controller 208.

  The characteristic amount data updating unit 10A receives the result of the characteristic amount data management operation processing unit 124 of the trail management server 120 and updates the characteristic amount data of the characteristic amount data storage unit 104.

  Next, the functional configuration of the trail inspection terminal 110 will be described.

  The feature amount data management operation unit 111, through the feature amount data management operation processing unit 124 of the trail management server 120, browses the feature amount data, the approval status (waiting for approval, approval, denial, return) and the identifier. The association (identification ID) is updated.

  The trail auditing operation unit 112 browses the trail of the event and the statistical information of the labor situation derived from the event via the trail auditing operation processing unit 127 of the trail management server 120.

  The update notification receiving unit 113 receives the update notification from the update notification transmitting unit of the trail management server 120.

Finally, the functional configuration of the trail management server 120 will be described.

  The characteristic amount data receiving unit 121 receives the characteristic amount data transmitted from the characteristic amount data transmitting unit 105 of the trail transmitting terminal 100, and stores it in the characteristic amount data storage unit 122. In addition, the update notification transmission unit 123 is requested to notify that the new feature amount data has been registered.

  The feature amount data storage unit 122 stores the feature amount data received by the feature amount data receiving unit 121. In addition, the information of the identifier associated with the identification ID of the feature amount data is stored.

  The update notification sending unit 123, when receiving the feature amount data and the trail, sends the update notification to the update notification receiving unit 113 of the trail auditing terminal 110.

  The characteristic amount data management operation receiving unit 124 receives a command from the characteristic amount data management operating unit 111 of the trail inspection terminal 110, displays the characteristic amount data of the characteristic amount data storage unit 122 on the screen, and displays the characteristic amount data in the screen. Process the operation.

  The trail receiving unit 125 receives the trail transmitted from the trail transmitting unit 109 of the trail transmitting terminal 100 and stores it in the trail storage unit 126. When the trail event is “spoofing” or “peeping”, the update notification transmission unit 123 is requested to notify that the security incident trail has been registered.

  The trail storage unit 126 stores the trails of labor events such as “seating”, “leaving”, and security incidents such as “spoofing” and “looking into”.

  The trail auditing operation processing unit 127 receives a command from the trail auditing operating unit 112 of the trail auditing terminal 110, displays the trail of the trail storage unit 126, statistical information of labor and labor calculated from the trail, and operates the trail. To process.

  The account storage unit 128 stores the account information of the teleworker and the administrator.

  Note that the teleworker and the administrator also have a function of performing account authentication required for using the system and a function of registering those account information, but detailed description thereof is omitted because it is out of the gist of the present invention. ..

  The overall flow of the telework management system according to this embodiment will be described below for each authentication level based on personal authentication.

  First, the case where the authentication level is "high" will be described.

  The trail transmission terminal 100 performs personal authentication on the video acquired from the camera device 210 using the authentication feature amount data, and calculates the authentication level. When the authentication level is "high", detection of an event is started using the authentication feature amount data. When an event is detected, the trail is sent to the trail management server 120.

  The trail management server 120 stores the trail received from the trail sending terminal 100, and when the trail is a security incident trail, sends an update notification regarding the registration of the security incident trail to the trail auditing terminal 110.

  The trail inspection terminal 110 receives the update notification from the trail management server 120, displays the trail, and accepts an operation on the trail as necessary. It also displays statistical information about labor events.

  Next, a case where the authentication level is “medium” will be described.

  The trail transmitting terminal 100 performs personal authentication on the camera image using the authentication feature amount data, and calculates the authentication level. When the authentication level is “medium”, the temporary feature amount data is calculated from the current video and transmitted to the trail management server 120, and the event detection is started by the temporary feature amount data.

  The trail management server 120 stores the temporary characteristic amount data received from the trail transmission terminal 100, and transmits an update notification regarding characteristic amount data registration to the trail inspection terminal 110.

  The trail inspection terminal 110 receives the update notification from the trail management server 120, and approves the temporary feature amount data. When there is no particular problem, the approval status is set to “approval”, and when the feature amount data is used for authentication in the future, the related identifier is set. If the feature amount data is from a third party, the approval status is set to "deny". If the feature data is for the teleworker himself but cannot be regarded as suitable for authentication, the approval status is set to "Send back".

  The trail management server 120 processes the characteristic amount data operation received from the trail inspection terminal 110.

  The trail operation terminal 100 updates the characteristic amount data stored in the terminal in response to the change in the characteristic amount data of the trail management server 120.

  The trail transmitting terminal 100 replaces the feature amount data used for event detection with the authentication feature amount data when the approval status of the temporary feature amount data used for event detection is “denial”. If necessary, lock the information processing terminal. If the approval status of the temporary feature amount data used for event detection is "send back", the individual authentication is performed again and the feature amount data used for event detection is updated.

  Next, a case where the authentication level is “low” will be described.

  The trail transmission terminal 100 performs personal authentication on the camera image using the registered authentication feature amount data, and calculates the authentication level. When the authentication level is "low", detection of an event is started using the authentication feature amount data. Also, the temporary feature amount data is calculated from the current video and transmitted to the trail management server 120.

  The trail management server 120 stores the temporary characteristic amount data received from the trail transmission terminal 100, and transmits an update notification regarding characteristic amount data registration to the trail inspection terminal 110.

  The trail inspection terminal 110 receives the update notification from the trail management server 120, and approves the temporary feature amount data. When there is no particular problem, the approval status is set to “approval”, and when the feature amount data is used for authentication in the future, the related identifier is set. If the feature amount data is from a third party, the approval status is set to "deny". If the feature amount data belongs to the teleworker himself but cannot be regarded as suitable for authentication, the approval status is set to "Send back".

  The trail management server 120 processes the characteristic amount data operation received from the trail inspection terminal 110.

  The trail operation terminal 100 updates the characteristic amount data stored in the terminal in response to the change in the characteristic amount data of the trail management server 120.

  When the approval status of the transmitted temporary characteristic amount data is “approved”, the trail transmitting terminal 100 replaces the characteristic amount data used for event detection with the temporary characteristic amount data. Further, when the approval status of the transmitted temporary feature amount data is “denial”, the information processing terminal is locked if necessary. If the approval status of the temporary feature amount data used for event detection is "send back", personal authentication is performed again and the feature amount data used for event detection is updated.

  Hereinafter, with reference to FIG. 4, a process in the resident application that operates on the trail transmission terminal 100 used by the teleworker in the telework management system of this embodiment will be described.

  The process shown in the flowchart of FIG. 4 is a process in which the CPU 201 of the trail transmission terminal 100 reads and executes a predetermined control program.

  In step S401, when the user logs in to the trail transmission terminal 100, the trail transmission terminal 100 activates the resident application, and logs in to the trail management server 120 in the background with the account ID and password of the teleworker. The trail management server 120 compares the information of the teleworker (FIG. 9) stored in the account storage unit 128, and if they match, permits the login. The account ID and password are set by the user when the resident application is first started, and the set values are used thereafter.

  In step S402, the possibility that the user using the trail transmission terminal 100 is a teleworker registered in the trail management server 120 is calculated, and the feature amount data used for event detection in step S403 is determined depending on the result. .. Details will be described with reference to FIG.

  In step S403, an event (labor event such as “seating” or “leaving” or a security incident such as “spoofing” or “peeping”) is detected and the trail is transmitted to the trail management server 120. Details will be described with reference to FIG.

  In step S404, the user logs out from the trail transmission terminal 100, and the trail transmission terminal 100 logs out from the trail management server 120 in the background.

  Hereinafter, with reference to FIG. 5, details of the personal authentication process of 402 in FIG. 4 will be described. The processing shown in the flowchart of FIG. 5 is executed by the CPU 201 of the trail transmission terminal 100 storing the program acquired from the ROM 203 in the RAM 202.

  In step S501, user operations other than the processes occurring in steps S502 to S515 are locked. In addition, the user is notified that the face is to be authenticated, and the user is urged to see the center of the CRT 211 in the posture of performing normal work. In other words, encourage them to take a normal posture when doing business.

  In steps S502 to S507, face identification is repeated for the frames captured by the camera device until the RAM 202 stores the face identification results for N frames (FIG. 14). In this way, the face identification processing is performed on a plurality of frames, because it may happen that a good or bad result may be obtained by only one face identification result for one frame. This is what you do to do that. However, it is not always necessary to use a plurality of frames, and face recognition processing may be performed once for one frame.

  Note that the specific numerical values of N cases are set in advance and are values such as 5 cases and 10 cases.

  In step S503, a frame input is received from the camera device 210, and the information (FIG. 12) is stored in the RAM 202.

  In step S504, face detection is performed on the frame acquired in step S503. The obtained face detection result (FIG. 13) is stored in the RAM 202.

  In step S505, it is determined whether the number of faces detected in step S504 is one.

  When the number of detected faces is one (step S505: YES), the process proceeds to step S506, and otherwise the process proceeds to step S502.

  In step S506, a face image is acquired from the frame based on the face detection result obtained in step S504. Then, with respect to the face image, face identification is performed using a discriminator that has learned (a characteristic amount of) authentication characteristic amount data.

  The obtained face identification result (FIG. 14) is stored in the RAM 202. When there are a plurality of pieces of authentication feature amount data associated with the same identifier, the classifier is made to learn them as the same identification target.

  When there are multiple identifiers, they are learned as different identification targets. The target to be identified here is the same as that of the teleworker, but the presence or absence of glasses and makeup, the difference in the environment in which work is performed (such as the lighting environment and the positional relationship between the camera and the face), etc. It is a categorized work environment. At the first time, it is considered that the authentication feature amount data used here does not exist. In that case, in step S508, the face identification result in which the degree of similarity that will be calculated as the authentication level “medium” is set is generated and stored in the RAM 202. Remember.

  Then, it is determined whether or not the number of times of photographing has reached N, and if it has reached N, the process proceeds to step S508. If the number has not reached N, the processes of steps S503 to S506 are repeated (step S507).

  In step S508, a representative face identification result is selected from the face identification results stored in the RAM 202, temporary feature amount data (FIG. 11) is generated therefrom, and the temporary feature amount data is stored in the RAM 202.

  As an example of selecting a representative face identification result, there is a method of selecting a face identification result having a similarity degree closest to the average value of the similarity degrees of N face identification results.

  If the degree of similarity between the generated temporary feature amount data and the authentication feature amount data exceeds the threshold A (first threshold value), it is assumed that the teleworker is authenticated, and the generated temporary feature amount data is authenticated. Set the level to "high". If the degree of similarity is less than the threshold value A and exceeds the threshold value B (second threshold value), the authentication level is set to "medium", and if it is less than the threshold value B, the authentication level is set to "low".

  Here, the threshold value A is a value of the degree of similarity in which authentication is performed by the authentication feature amount data, and if the degree of similarity is equal to or more than that value, it is guaranteed that the persons are substantially the same person. If so, it is a value of the degree of similarity considered to be high for the person himself. This threshold differs depending on the face recognition technology used and the like.

  When a plurality of identifiers are registered in the discriminator, the average value of the similarities is calculated separately, and the face identification result of the identifier having the largest value is selected. After the generation of the temporary feature amount data, all the frames, face detection results, and face identification results stored in the RAM 202 are deleted.

  In step S509, the authentication level of the temporary feature amount data calculated in step S508 is determined.

  As a result of the determination, if the authentication level of the temporary feature amount data is “high”, the process proceeds to step S510.

  Otherwise (authentication level is medium or low), the process proceeds to step S511.

  In step S510, the RAM 202 stores the authentication feature amount data used in step S506 as the feature amount data used when detecting an event.

  When there are a plurality of identifiers, the authentication feature amount data of the identifier having the largest average similarity value calculated in step S508 is set as the feature amount data used when detecting an event. In addition, if registration of a plurality of identifiers is permitted in event detection, all authentication feature amount data may be set to be used in event detection.

  The case where a plurality of identifiers exist means a case where a plurality of authentication feature amount data are registered. For example, there is a case where two types of authentication feature amount data of a face wearing glasses and authentication feature amount data of a face not wearing glasses are registered.

  Then, the process proceeds to step S516. The process of step S516 will be described later.

  The processing when the authentication level is determined to be medium or low in step S509 will be described.

  In step S511, the authentication result and the face image of the temporary feature amount data are displayed for the user to confirm. When the authentication level is “medium”, it is confirmed that the temporary feature amount data is used to detect the event and that the feature amount data is recorded in the management server. If the authentication level is “low”, confirm that the authentication was not successful and that the administrator is notified to approve the event detection using the temporary feature amount data.

  Specifically, the user is prompted to confirm by displaying the screen shown in FIG. Then, the confirmation result from the user is accepted.

  In step S512, if the confirmation result received from the user in step S511 is “OK”, the process proceeds to step S513.

  When the confirmation result is OK, when the authentication level is medium, the fact that the temporary feature amount data is used to detect the event and the feature amount data is recorded in the management server is approved. When the result of is received. When the authentication level is low, if the result of accepting that authentication was not successful or that notification is given to the administrator to approve that event detection can be performed using temporary feature amount data is received. Is.

  If the confirmation result indicates that re-authentication is accepted, the process proceeds to S502 and face authentication is performed again.

  If the confirmation result indicates that cancellation is accepted, the process transitions to step S510.

  In step S513, the temporary feature amount data calculated in step S508 is registered in the trail management server 120. Details of this processing will be described with reference to the flowchart of FIG.

  In step S514, if the authentication level of the temporary feature amount data is "medium", the process proceeds to step S515, and if it is "low", the process proceeds to step S510.

  In step S515, the temporary feature amount data calculated in step S508 is stored in the RAM 202 as feature amount data used when detecting an event. If registration of a plurality of identifiers is permitted in event detection, all authentication feature amount data may be set to be used in addition to the temporary feature amount data.

  In this way, by using the temporary feature amount data for event detection, the authentication accuracy is better than when using the previously acquired authentication feature amount data for event detection, and events such as “seating” and “spoofing” can be performed more accurately. You will be able to detect.

  In step S516, the lock of the user operation performed in step S501 is released. Then, the processing of this flowchart is ended.

  FIG. 16 shows an example of a screen operated by the user in the personal authentication process.

  FIG. 16A is an example of a screen displayed on the display unit of the trail transmission terminal 100 in step S501.

  FIG. 16B is an example of a screen displayed on the display unit of the trail transmission terminal 100 when the authentication level is determined to be high in step S509.

  FIG. 16C is an example of a screen displayed on the display unit of the trail transmission terminal 100 when the authentication level is determined to be low in step S509. As shown in FIG. 16C, an OK button, a cancel button, and a re-authentication button are included, and the processing (determination) of step S512 is performed according to the button pressed by the user.

  FIG. 16D is an example of a screen displayed on the display unit of the trail transmission terminal 100 when it is determined that the authentication level is medium in step S509. Similar to FIG. 16C, FIG. 16D also includes an OK button, a cancel button, and a re-authentication button, and the process (determination) of step S512 is performed according to the button pressed by the user.

  Next, with reference to FIG. 6, details of registration and approval processing of the temporary feature amount data in step S512 of FIG. 5 will be described.

  Of the processes shown in the flowchart of FIG. 6, the process of the trail transmitting terminal 100 is executed by the CPU 201 of the trail transmitting terminal 100 storing the program acquired from the ROM 203 in the RAM 202. Further, the processing of the trail inspection terminal 110 is executed by the CPU 201 of the trail inspection terminal 110 storing the program acquired from the ROM 203 in the RAM 202. The processing of the trail management server 120 is executed by the CPU 201 of the trail management server 120 storing the program acquired from the ROM 203 in the RAM 202.

  In step S601, the trail transmission terminal 100 transmits the temporary feature amount data calculated in step S508 to the trail management server 120. At the same time, the temporary characteristic amount data is stored in the characteristic amount data storage unit 104.

  In step S602, the trail management server 120 receives the temporary characteristic amount data transmitted by the trail transmitting terminal 100 and stores it in the characteristic amount data storage unit 122. Then, the trail transmission terminal 100 and the trail management server 120 operate asynchronously, the trail transmission terminal 100 transitions to the process of step S514 of the personal authentication process (FIG. 5), and the trail management server 120 transitions to the process of step S603. To do. The processing of the trail transmission terminal 100 (from S514 onward) is as described above.

  In step S603, the trail management server 120 acquires from the account storage unit 128 the information (FIG. 8) of the administrator of the teleworker corresponding to the teleworker ID of the temporary feature amount data 100. Then, the approval request notification of the newly registered temporary feature amount data is transmitted to the trail inspection terminal 110 of the administrator. A typical transmission means is e-mail, but any method may be used. After the transmission, the trail management server 120 waits for a new command.

  In step S604, the trail inspection terminal 110 receives the approval request notification transmitted from the trail management server 120.

  In step S605, the trail inspection terminal 110 displays the screen shown in FIG. 17 on the display unit, allows the administrator to confirm the face image of the temporary feature amount data (FIG. 11) on the trail management server 120, and approves by the administrator. Accept the operation.

  When the administrator judges that the owner of the face image displayed on the display unit is the teleworker himself and allows event detection by the temporary feature amount data (that is, when an instruction to approve from the administrator is accepted), Change the approval status to "Approval".

  If the administrator determines that the owner of the face image is the teleworker himself, but it is not permitted to use it for event detection (that is, if the instruction to cancel the approval is received), the approval status is set to "Send back". Change to ".

  When the administrator determines that the owner of the face image is a third party other than the teleworker (that is, when the administrator accepts an instruction to reject), the approval status is changed to “denied”.

  When the administrator determines that the owner of the face image is the teleworker himself and registers the face image as the authentication feature amount data used for personal authentication in the future, the approval status is changed to “approval” and the identifier (FIG. ) Is accepted. When specifying an identifier, a new identifier can be specified in addition to an existing identifier. When designating an existing identifier, it is also possible to clear the identifiers of other feature amount data to which the identifier is set and to use only the feature amount data being edited as the authentication feature amount data of that identifier. FIG. 17 shows an example of a screen operated by the user in updating the characteristic amount data.

  Here, the screen shown in FIG. 17 will be described.

  FIG. 17A is a screen displayed on the display unit of the trail inspection terminal 110 in step S604. When the administrator selects data whose approval status is “registration”, the screen shown in FIG. 17B is displayed.

  The screen of FIG. 17B receives an instruction from the administrator whether to approve the feature amount data selected on the screen of (A) (whether to approve the feature amount data used for event detection).

  When the instruction to approve is received, the screen shown in FIG. 17C is displayed. In the screen shown in FIG. 17C, an instruction as to whether to approve the use as the characteristic amount data for authentication is accepted.

  When an instruction to approve the use as the characteristic amount data for authentication is given, the screen shown in FIG. 17D is displayed and the selection of the identifier is accepted.

  When the selection of the identifier is accepted and the OK button is pressed, the screen shown in FIG. 17E is displayed.

  The screen shown in FIG. 17E is a screen for setting the feature amount data associated with the identifier.

The above is the explanation of the screen shown in FIG.

  In step S606, the trail management server 120 updates the feature amount data according to the approval operation by the administrator accepted in step S605.

  In step S607, the trail transmission terminal 100 updates the corresponding temporary feature amount data stored in the feature amount data storage unit 104 in response to the update of the temporary feature amount data in step S606 by the trail management server 120. That is, it is a process of synchronizing the data stored in the trail management server 120 with the data stored in the trail transmitting terminal 100.

  If the temporary feature amount data updated in step S606 does not exist in the feature amount data storage unit 104, the information is acquired from the trail management server 120. Further, even when the authentication feature amount data updated in step S606 is the feature amount data, the feature amount data is updated.

  In step S608, the approval status of the temporary feature amount data is determined.

  If the approval status is “remand”, the process proceeds to step S609.

  If the approval status is “denial”, the process proceeds to step S610.

  If the approval status is “approval”, the process proceeds to step S611.

  In step S609, in response to the temporary characteristic amount data being returned, the trail transmission terminal 100 performs the same personal authentication process as in step S402 again to determine the characteristic amount data used for event detection.

  In step S610, the trail transmission terminal 100 performs processing such as screen lock of the information terminal in response to the denial of the temporary feature amount data. In other words, the administrator has determined that the face image in the temporary feature data is not the face image of the teleworker himself.Therefore, by locking the screen, it is possible to prevent operations other than the teleworker himself from operating the trail transmission terminal. Take measures.

  Note that the screen lock processing executed here is assumed to take security measures such as notifying the warning such as sounding an error sound and saving the camera image as a video even if the screen lock is not performed. is doing. Detailed description of unlocking the screen is omitted because it is out of the scope of the present invention.

  In step S611, when the authentication level of the changed temporary feature amount data is “low” (step S611: TRUE), the process proceeds to step S612 and the feature amount data used for event detection is updated with the temporary feature amount data. I do. That is, the contents set in the process of step S510 are updated.

  If the authentication level is "medium" (step S611: FALSE), the event is detected in the already-accepted temporary feature amount data (step S515), and the process is terminated.

  In step S612, the trail transmission terminal 100 updates the feature amount data used for event detection to the temporary feature amount data acquired on the current day from the authentication feature amount data set in step S510. It should be noted that if registration of a plurality of identifiers is permitted in event detection, the temporary characteristic amount data may be set to be used in addition to the authentication characteristic amount data in use.

  As a result, spoofing is less likely to occur than when the authentication feature amount data is used.

  Hereinafter, details of the event detection in step S403 in FIG. 4 will be described with reference to FIG. 7. This processing is executed by the CPU 201 of the trail transmission terminal 100 storing the program acquired from the ROM 203 in the RAM 202. The event detection process of steps S701 to S709 and the trail transmission process of steps S710 to S713 operate asynchronously. This processing is all executed in the back end and does not involve user operation.

  First, the event detection process of steps S701 to S709 will be described.

  In step S701, it is confirmed whether or not there is an application termination command, and if there is no application termination command (step S701: NO), the process proceeds to step S702. If there is an application termination command (step S701: YES), the process of this flowchart is terminated, and the process proceeds to step S404.

  In step S702, input of a frame (image) from the camera device 210 is accepted, and the information (FIG. 12) is stored in the RAM 202.

  When the event is detected in step S707, the face detection and face identification results of a predetermined number (M) of frames are used. Therefore, if M frames are stored in the RAM 202, the oldest frame and the associated frame are related. The face detection result and the face identification result are deleted from the RAM 202.

  In step S703, face detection is performed on the frame acquired in step S702. The obtained face detection result (FIG. 13) is stored in the RAM 202.

  In steps S704 to S706, face identification is performed on the face detected in step S703. Upon completion, the process transitions to step S707.

  In step S705, one face image is acquired from the frame based on the face detection result obtained in step S703, and the feature amount data used for event detection calculated in the personal authentication process (FIG. 4) for the face image. Face recognition is performed using a classifier that has learned (feature amount of). The obtained face identification result (FIG. 14) is stored in the RAM 202. When there are a plurality of feature amount data associated with the same identifier, the discriminator is made to learn them as the same discrimination target. When there are multiple identifiers, they are learned as different identification targets. The target to be identified here is the same as that of the teleworker, but the presence or absence of glasses and makeup, the difference in the environment in which work is performed (such as the lighting environment and the positional relationship between the camera and the face), etc. It is a categorized work environment.

  In step S707, the current event (seating, leaving, spoofing, looking into) is calculated from the face detection result and the face identification result of the plurality of frames stored in the RAM 202, and the trail is stored in the RAM 202.

  As a simple example, for a plurality of frames, the number of face detection results of each frame is checked, and when the number of detected faces is 0, the number of frames is the highest. It can be said that it is long, so it is judged that he / she is absent.) When the number of frames with the most two faces is the most, "Peeking in" (Since two or more faces are detected, it is judged that he / she is looking in.) And

  Also, when the number of detected faces is the highest in one frame, the number of frames whose face identification result similarity is above a certain value and below the certain value is checked, and when there are many former cases, "seating" (only the teleworker himself) If there are a lot of the latter, it is said to be “spoofing” (only the person other than the teleworker is shown).

  This calculation method may be set arbitrarily according to the accuracy and tendency of the results of face detection and face identification. Alternatively, the discriminator that has learned the tendency of event occurrence may be used for the determination.

  In step S708, if the event of the trail calculated in step S707 and the event of the trail detected immediately before have the same value (that is, the situation does not change), the process proceeds to step S701, and if they differ (that is, the situation Has changed, and some event has occurred), the process proceeds to step S709.

  In step S709, the trail is stored in the trail storage unit 108, and the process proceeds to step S701.

  Subsequently, the trail transmission process of steps S710 to S713 will be described.

  In step S710, it is confirmed whether or not there is an application termination command, and if there is no application termination command (step S710: NO), the process proceeds to step S711. If there is an application termination command (step S710: YES), the process of this flowchart is terminated, and the process proceeds to step S404.

  In step S711, the latest trail stored in the trail storage unit 108 is confirmed, and it is determined whether the trail transmission conditions are satisfied.

  As an example of the transmission condition, unlike the event of the trail that was transmitted last, the latest trail is stored in the RAM 202, assuming that the trail must be transmitted if a certain time has elapsed from the date and time when the trail was detected. If the fixed time has not passed, it is determined that the transmission is unnecessary.

  This elapsed time is set for each event depending on the accuracy of face recognition. For example, if spoofing can be easily detected by mistake and if peeping can be detected with high accuracy, a trail of a spoofing event is sent when spoofing is detected for 30 seconds, and a peep event is detected when spoofing is detected for 5 seconds. Set the time until the trail is sent differently depending on the event, such as sending the trail.

  The trail transmitted last is stored in the RAM 202, and the initial value is "leave". As a result, even if the person is seated but "spoofing" or "away" is frequently mistakenly detected, if "seating" can be detected immediately after that, the events that have occurred up to that point will be managed as noise. It will not be sent to or stored in the server.

  In step S712, it is determined whether there is a trail to be sent from the history of the trail detected after the trail was last sent.

  For example, if “spoofing” and “away” occur alternately more than once in a short period of time (eg, every 1 second), it can be estimated that “spoofing” occurs (leaving away within 1 second). Since it is unnatural to repeat the process of sitting and sitting, it is considered that the detection of leaving the seat is an erroneous detection, and it can be judged that spoofing continues, so it is necessary to send the event of the first "spoofing". It is determined and stored in the RAM 202.

  In addition, if “spoofing” occurs between the leaving events, it can be presumed that a third party looked into the teleworker for a while and left immediately, so it is necessary to send the trail. Then, it is stored in the RAM 202.

  By determining the necessity of transmission from the history of the trail as in step S712, it is possible to dig up the trail requiring transmission that was overlooked in step S711.

In step S713, the trail determined to be necessary in steps S711 and S712 is transmitted to the management server 120. At this time, the new trail of the detection date and time is stored in the RAM 202 as the trail of the last transmission.

  As described above, the process shown in the flowchart of FIG. 7 is a process that is continuously executed until the application ends.

  8-15 is a data configuration diagram showing an example of a data table in the telework management system of the present embodiment.

  FIG. 8 is a diagram showing an example of a data table in which manager information is registered, and manager information (ID, name, mail address, etc.) is stored.

  FIG. 9 is a diagram showing an example of a data table in which teleworker information is registered, in which information such as a teleworker ID, a name of the teleworker, a mail address of the teleworker, an ID of an administrator corresponding to the teleworker, and the like are stored. The administrator registered here is notified of a request for approval of the temporary feature amount data (S513).

  FIG. 10 is a diagram showing an example of a data table in which identifier information is registered, in which information such as a teleworker ID, an identification ID, and a name is stored. In the example of FIG. 10, two types of authentication feature amount data are registered in the teleworker with the teleworker ID “1”.

  FIG. 11 is a diagram showing an example of a data table in which feature amount data is registered. In the example of FIG. 11, four feature amount data of the teleworker with the teleworker ID “1” are registered. The administrator has approved the feature amount data of the feature amount data ID “1”, ID “2”, and ID “3”. Further, with respect to the feature amount data of ID “1” and ID “2”, since the identification ID is registered, it is used as personal identification data as the feature amount data for authentication.

  FIG. 12 is a diagram showing an example of a data table in which frame information is registered. This table is data registered in the processing of steps S503 and S702. It is composed of data such as frame ID, image, size, acquisition date and time.

  FIG. 13 is a diagram showing an example of a data table in which face detection results are registered. Information of the face detected from each frame registered in FIG. 12 is registered.

  FIG. 14 is a diagram showing an example of a data table in which face identification results are registered.

  FIG. 15 is a diagram showing an example of a data table in which trail information is registered. This is the data registered in step S709. It is composed of the date and time of detection, the trail image, the content of the event, and the like.

  FIG. 18 is a diagram showing an example of a data table in which the first threshold value and the second threshold value for obtaining the authentication level are registered.

16 and 17 are screen images showing an example of a screen operated by the user in the telework management system of this embodiment.

  As described above, in the present invention, when the similarity between the face image captured at the time of starting the telework and the authentication face image approved by the administrator in advance is high (the similarity is higher than the first threshold value). Is high), that is, when the authentication level in the present embodiment is high, an event is detected using the face image for authentication. This eliminates the need for the administrator to judge whether the teleworker is the person each time the teleworker starts teleworking, and the burden on the administrator can be reduced. In addition, the teleworker does not need to submit an approval request to the administrator, which reduces the burden.

  The degree of similarity between the face image captured at the time of starting the telework and the face image for authentication approved in advance by the administrator is medium (the degree of similarity is lower than the first threshold value and higher than the second threshold value). In the case), that is, when the authentication level in this embodiment is medium, event detection is performed using the face image captured at the start of the telework. Further, the administrator is made to confirm the face image taken at the time of starting the telework, and an instruction as to whether or not to use the face image for event detection is accepted. Also, as a face image for future authentication, the selection whether to use the face image captured at the start of the telework is accepted, and if there is an instruction to use the face image for future authentication, the face image is Register as a face image for authentication.

  As described above, when the degree of similarity is medium, there is a certain possibility that the teleworker is the person himself.Therefore, false detection of spoofing can be reduced by performing event detection by the face image captured at the start of teleworking. It will be possible. In addition, by having the administrator confirm the face image taken at the start of the telework and accepting the selection whether it can be used for event detection continuously, it is possible to minimize the impact of the security incident if the teleworker is not the person himself. Is possible.

  In addition, if the administrator determines that he / she is the teleworker himself and may use it for authentication, the face image taken at the start of the telework can be used as an authentication face image to change the face over time. It is possible to register a corresponding authentication face image.

  The degree of similarity between the face image captured at the time of starting the telework and the face image for authentication approved in advance by the administrator is low (when the degree of similarity is lower than the second threshold value), that is, the authentication in the present embodiment. If the level is low, event detection is performed using the face image for authentication. If the administrator confirms the face image captured at the start of telework, and the approval is obtained as the face image used for event detection, the face image captured at the start of telework is used for event detection. If there is an instruction to use the face image for future authentication, the face image is registered as a face image for authentication.

  As described above, when the degree of similarity is low, it is unlikely that the person is the teleworker himself. Therefore, it is possible to suppress the influence of a security incident or the like by first detecting the event with the face image for authentication. In addition, when the administrator approves the event, the face image captured at the start of the telework is used to detect an event, so that it is possible to prevent a decrease in convenience due to erroneous detection.

  In addition, if the administrator determines that he / she is the teleworker himself and can use it for authentication, the face image taken at the start of the telework can be used as the authentication face image to change the face over time. It is possible to register a corresponding authentication face image.

  It is needless to say that the structure and contents of the various data described above are not limited to this, and may be composed of various structures and contents according to the use and purpose.

  Further, the program in the present invention is a program that causes a computer to execute the processes of FIGS. 4 to 7. The program in the present invention may be a program for each process of FIGS. 4 to 7.

  As described above, the recording medium recording the program that realizes the functions of the above-described embodiments is supplied to the system or apparatus, and the computer (or CPU or MPU) of the system or apparatus stores the program stored in the recording medium. It goes without saying that the object of the present invention can also be achieved by reading and executing.

  In this case, the program itself read from the recording medium realizes the novel function of the present invention, and the recording medium recording the program constitutes the present invention.

  As a recording medium for supplying the program, for example, a flexible disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a DVD-ROM, a magnetic tape, a non-volatile memory card, a ROM, an EEPROM, and a silicon. A disk or the like can be used.

  Further, not only the functions of the above-described embodiments are realized by executing the program read by the computer, but also the OS (operating system) or the like running on the computer is actually executed based on the instructions of the program. It goes without saying that a case where a part or all of the processing is performed and the functions of the above-described embodiments are realized by the processing is also included.

  Furthermore, after the program read from the recording medium is written in the memory provided in the function expansion board inserted in the computer or the function expansion unit connected to the computer, the function expansion board is instructed based on the instruction of the program code. Needless to say, this also includes the case where the CPU or the like included in the function expansion unit performs some or all of the actual processing and the functions of the above-described embodiments are realized by the processing.

  Further, the present invention may be applied to a system including a plurality of devices or an apparatus including one device. Further, it goes without saying that the present invention can be applied to the case where it is achieved by supplying a program to a system or an apparatus. In this case, by reading the recording medium storing the program for achieving the present invention into the system or device, the system or device can enjoy the effects of the present invention.

  Further, by downloading and reading a program for achieving the present invention from a server, a database or the like on a network using a communication program, the system or apparatus can enjoy the effects of the present invention. It should be noted that the present invention also includes all configurations that combine the above-described embodiments and modifications thereof.

100 Trail Sending Terminal 110 Trail Auditing Terminal 120 Trail Management Server

Claims (9)

Acquisition means for acquiring an image taken by the imaging device,
Recording means for recording that a security incident has occurred, on condition that a person other than the user relating to the face image registered in advance is reflected in the image acquired by the acquisition means,
Equipped with
The recording unit is further configured such that the user's absent state detected based on the determination result of whether or not the face image registered in advance in the image acquired by the acquisition unit is included in the image continues for a predetermined time. In this case, the information processing system records the fact that the user is in an away state. The recording means records that a security incident has occurred on the condition that a person other than the user relating to the face image registered in advance is reflected in the image acquired by the acquisition means for a predetermined time. The information processing system according to claim 1, wherein: Acquisition means for acquiring an image taken by the imaging device,
In the image acquired by the acquisition unit, a recording unit that records that a security incident has occurred, provided that a person other than the user relating to the face image registered in advance is continuously displayed for a predetermined time,
Equipped with
The recording means further records a leaving state of the user detected based on a determination result of whether or not the user is included in the face image registered in advance in the image acquired by the acquisition means. Information processing system. The recording means records that a security incident of a peep has occurred when a person other than the user is reflected in the pre-registered face image together with the user. The information processing system according to any one of 1. The recording means records that a security incident of spoofing has occurred when the user related to the pre-registered face image is not reflected and a person other than the user is reflected. The information processing system according to any one of claims 1 to 4. An acquisition step of acquiring an image captured by the imaging device,
A recording step of recording that a security incident has occurred, on condition that a person other than the user relating to the face image registered in advance is reflected in the image acquired by the acquisition step,
Equipped with
In the recording step, the away state of the user, which is detected based on the determination result of whether or not the face image registered in the image acquired in the acquisition step is included in the image, continues for a predetermined time. In this case, the information processing method is characterized in that the fact that the user is away from the seat is recorded. An acquisition step of acquiring an image captured by the imaging device,
In the image acquired by the acquisition step, a recording step of recording that a security incident has occurred, provided that a person other than the user involved in the face image registered in advance is continuously displayed for a predetermined time,
Equipped with
The recording step further records the away state of the user, which is detected based on the determination result of whether or not the face image registered in the image acquired in the acquisition step is included in the face image. Information processing method. Computer,
Acquisition means for acquiring an image taken by the imaging device,
The image acquired by the acquisition unit is caused to function as a recording unit that records that a security incident has occurred, on condition that a person other than the user relating to the face image registered in advance is reflected.
The recording means further causes the user to leave the seat, which is detected based on the determination result of whether or not the face image registered in advance in the image acquired by the acquisition means includes the user, for a predetermined time. In this case, a program that functions as a means for recording the fact that the user is away from the seat. Computer,
Acquisition means for acquiring an image taken by the imaging device,
Functioning as a recording unit that records the occurrence of a security incident on the condition that a person other than the user associated with the face image registered in advance is reflected in the image acquired by the acquisition unit for a predetermined time. Let
The recording means further functions as means for recording the away status of the user detected based on the determination result of whether or not the face image registered in advance in the image acquired by the acquisition means includes the user. A program to let you.

Images