JP7409437B2 - Information processing device, information processing method, and program - Google Patents

Description

The present invention relates to personal authentication technology using facial images.

One of the security techniques using biometric data is a personal authentication technique using a person's facial image.

An example of a technology related to personal authentication technology using a person's face image is disclosed in, for example, Patent Document 1 listed below. In Patent Document 1 listed below, when data to be compared with face image data registered in a dictionary has poor image quality, the matching process is performed after correcting the area of poor image quality, thereby achieving highly accurate matching processing. The technology has been disclosed.

Japanese Patent Application Publication No. 2005-084824

Personal authentication technology based on a person's face is used, for example, at the entrance (gate, door, etc.) of a place where the number of people who can enter is restricted. In this case, identification information for identifying the person, such as a facial image of the person who has the authority to enter or features of that image, must be registered in the database in advance, but identification information for all persons must be registered in advance. Sometimes they are not prepared. In this case, a person whose personal authentication fails at an entrance gate or the like will have to go through a procedure to register identification information. A technique is desired to shorten the time required for such procedures.

An object of the present invention is to provide a technique that reduces the time required to register identification information used in personal authentication based on a person's face.

According to the invention,
Extracting means for extracting a plurality of facial images of the same person from a moving image or a plurality of still images generated by the imaging means;
Selection means for selecting a face image whose suitability as identification information for identifying the person is equal to or higher than a first reference value from among the plurality of face images extracted by the extraction means;
Candidate image determining means for determining facial image candidates to be used in the registration process of the person's identification information based on the qualification of the facial image selected by the selecting means;
display processing means for displaying the face image candidates determined by the candidate image determination means on a screen used in the registration process;
An information processing device is provided.

According to the invention,
The computer is
Extract multiple facial images of the same person from a video,
Selecting, from among the plurality of extracted face images, a face image whose suitability as identification information for identifying the person is equal to or higher than a first reference value;
determining facial image candidates to be used in the registration process of the person's identification information based on the qualification level of the selected facial image;
displaying the determined facial image candidates on a screen used in the registration process;
A method for determining person identification information is provided.

According to the invention,
A program is provided that causes a computer to execute the above-described person identification information determination method.

According to the invention,
a cutting means for cutting out a face image of another person who is photographed together with a specific person from the image;
Registration means for registering identification information for identifying the other person using the face image of the other person extracted by the extraction means or its feature amount;
An information processing device is provided.

According to the invention,
The computer is
Cut out facial images of other people who appear with a specific person from the image,
registering identification information for identifying the other person using the cut out face image of the other person or its feature amount;
A method for registering person identification information is provided.

According to the invention,
A program is provided that causes a computer to execute the above-described person identification information registration method.

According to the present invention, it is possible to shorten the time required to register identification information used in personal authentication based on a person's face.

1 is a block diagram conceptually showing the functional configuration of an information processing device in a first embodiment. FIG. FIG. 2 is a block diagram conceptually showing the functional configuration of an information processing device in a second embodiment. FIG. 3 is a diagram showing an example of information stored in a storage unit. 1 is a diagram conceptually showing a hardware configuration of an information processing device. FIG. 3 is a block diagram conceptually showing the functional configuration of an information processing device in a third embodiment. 2 is a flowchart showing a first specific example of processing executed by the information processing device. FIG. 3 is a diagram showing an example of a screen displayed by a display processing unit. 12 is a flowchart illustrating the flow of candidate image determination processing in S110. 3 is a flowchart for explaining the flow of notification processing executed by a notification unit. It is a figure showing an example of a screen displayed by notification processing by a notification part. It is a figure which shows an example of the screen displayed by the notification process by a notification part. It is a figure showing an example of a screen displayed by notification processing by a notification part. It is a flowchart which shows the 2nd specific example of the process performed by an information processing apparatus. It is a flowchart which shows the 3rd specific example of the process performed by an information processing apparatus. FIG. 3 is a block diagram conceptually showing the functional configuration of an information processing device according to a fourth embodiment. 12 is a flowchart illustrating the flow of processing executed by the information processing apparatus according to the fourth embodiment. FIG. 7 is a block diagram conceptually showing the functional configuration of an information processing device according to a fifth embodiment. 12 is a flowchart illustrating the flow of processing executed by the information processing apparatus of the fifth embodiment. FIG. 7 is a block diagram conceptually showing the functional configuration of an information processing device according to a sixth embodiment. 1 is a diagram conceptually showing a hardware configuration of an information processing device. 12 is a flowchart illustrating the flow of processing executed by the information processing apparatus according to the sixth embodiment.

Embodiments of the present invention will be described below with reference to the drawings. Note that in all the drawings, similar components are denoted by the same reference numerals, and descriptions thereof will be omitted as appropriate. Furthermore, unless otherwise specified, each block in each block diagram represents a configuration of a functional unit rather than a configuration of a hardware unit.

[First embodiment]
[Functional configuration]
FIG. 1 is a block diagram conceptually showing the functional configuration of an information processing device 10 in the first embodiment. As shown in FIG. 1, the information processing device 10 of this embodiment includes an extraction section 110, a selection section 120, a candidate image determination section 130, and a display processing section 140.

The extraction unit 110 extracts a plurality of facial images related to the same person from a moving image or a plurality of still images. For example, the extraction unit 110 may extract images related to the same person from each of a plurality of frame images that make up a video by using a known image processing algorithm that tracks the same object (person) over different frames. can. The extraction unit 110 stores the extracted facial images for each person in, for example, a memory (not shown).

The selection unit 120 determines, for each of the plurality of facial images extracted by the extraction unit 110, the degree of suitability as identification information for identifying the person (the degree to which the facial image is appropriate as information for identifying the person). Calculate.

For example, the selection unit 120 can calculate the degree of eligibility based on at least one of the degree of face-likeness and the image quality of the extracted face image. For example, when calculating the degree of eligibility based on the degree of face-likeness, the selection unit 120 can use a function or table that uses the direction of the face and the degree of inclination as parameters. The selection unit 120 can calculate the orientation and degree of inclination of the face based on the appearance (positional relationship) of feature points such as eyes, nose, and mouth, for example. In this case, the closer to the front, the higher the degree of eligibility. Further, the selection unit 120 can calculate the degree of eligibility using a function or table that uses as a parameter the proportion of feature points that characterize the face, such as eyes, nose, and mouth, that are hidden or difficult to see. In this case, the higher the percentage of feature points that characterize the face, such as the eyes, nose, and mouth, that are hidden or difficult to see, the lower the eligibility level becomes. In addition, when calculating the eligibility level based on the image quality of the face image, the selection unit 120 may use a function that uses factors related to image quality as parameters, such as the degree of blurring of the image, the degree of blur of the subject, and the brightness of the image. You can use the table. In this case, the worse the image quality is, for example, the image is strongly blurred, the subject is significantly blurred, there are many dark areas in the image, etc., the lower the qualification level becomes. The selection unit 120 then selects the image based on the degree of face-likeness, such as the orientation and inclination of the face, or the visibility of facial feature points, and the image quality, such as the degree of blurring of the image, the degree of blurring of the subject, and the brightness of the image. The final eligibility level can be determined by integrating the calculated eligibility levels.

The selection unit 120 selects, from among the plurality of face images extracted by the extraction unit 110, a face image whose suitability calculated as described above is equal to or greater than the first reference value. The first reference value used by the selection unit 120 is stored in advance in a memory or storage device (not shown), for example.

The candidate image determining unit 130 determines facial image candidates to be used in the registration process of person identification information, based on the suitability of the facial image selected by the selecting unit 120. Specifically, the candidate image determining unit 130 determines the facial image with the highest degree of eligibility among the facial images selected by the selecting unit 120 as the facial image candidate to be used in the registration process of person identification information.

The display processing unit 140 displays the face image determined by the candidate image determination unit 130 as a “candidate face image used in the registration process of person identification information” on one of the screens used in the registration process.

As described above, in this embodiment, among a plurality of face images related to the same person extracted from a video, a face image whose "qualification level as person identification information" is equal to or higher than a predetermined reference value (first reference value) is selected. It is selected and displayed on the screen used in the identification information registration process. As a result, when an administrator or the like operates a terminal to register identification information, for example, there is no need to select an appropriate facial image, and the time required for the identification information registration process can be shortened.

[Second embodiment]
In this embodiment, the first embodiment will be described in further detail.

[Functional configuration]
FIG. 2 is a block diagram conceptually showing the functional configuration of the information processing device 10 in the second embodiment. The information processing device 10 of this embodiment further includes a storage unit 150 in addition to the configuration of the first embodiment. The first face image or its feature amount data can be used to identify a face image area of the same person among a plurality of frame images making up a moving image. The storage unit 150 stores a face image (hereinafter also referred to as a “first face image”) displayed as a “face image candidate used in the registration process of person identification information” on the screen displayed by the display processing unit 140. ) or its feature amount and the qualification degree of the first face image are stored in association with each other (eg, FIG. 3). FIG. 3 is a diagram illustrating an example of information stored in the storage unit 150. FIG. 3 shows an example in which the storage unit 150 stores feature data of a first face image and information indicating the qualification of the face image in association with each other for each person.

In the present embodiment, the candidate image determining unit 130 uses the extracting unit 110 to extract a second facial image of the same person from a video ( For example, it is determined whether the image is extracted from the next frame image). When the second face image (next frame image) is extracted by the extraction unit 110, the selection unit 120 calculates the eligibility degree of the second face image. Note that when the qualification level of the second facial image extracted by the extraction unit 110 is equal to or higher than the first reference value, the second image is treated as a "face image having a qualification level equal to or higher than the first reference value". Selected by the selection unit 120. Then, when the second image is selected by the selection unit 120 as a “face image having a qualification level equal to or higher than the first reference value”, the candidate image determination unit 130 selects the first face image and the second face image. The qualifications are compared, and the one with the higher qualification is determined as the facial image candidate to be used in the registration process. By repeating the above process, the candidate image determining unit 130 can finally determine the image with the highest degree of qualification as the facial image candidate used in the registration process.

[Hardware configuration]
Each functional component of the information processing device 10 may be realized by hardware that implements each functional component (e.g., a hardwired electronic circuit), or by a combination of hardware and software (e.g., (e.g., a combination of an electronic circuit and a program that controls it). A case in which each functional component of the information processing device 10 is realized by a combination of hardware and software will be further described below.

FIG. 4 is a diagram conceptually showing the hardware configuration of the information processing device 10. As shown in FIG. As shown in FIG. 4, the information processing device 10 includes a bus 101, a processor 102, a memory 103, a storage device 104, an input/output interface 105, and a network interface 106.

The bus 101 is a data transmission path through which the processor 102, memory 103, storage device 104, input/output interface 105, and network interface 106 exchange data with each other. However, the method for connecting the processor 102, memory 103, storage device 104, input/output interface 105, network interface 106, etc. to each other is not limited to bus connection.

The processor 102 is an arithmetic device such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). The memory 103 is a main storage device implemented using RAM (Random Access Memory), ROM (Read Only Memory), or the like. The storage device 104 is an auxiliary storage device implemented using an HDD (Hard Disk Drive), an SSD (Solid State Drive), a memory card, or the like.

The storage device 104 stores program modules that implement each functional component of the information processing apparatus 10 (extraction unit 110, selection unit 120, candidate image determination unit 130, display processing unit 140). The processor 102 reads each of these program modules into the memory 103 and executes them, thereby realizing the functions corresponding to each program module. Further, the storage device 104 can be used as the storage unit 150 described above.

The input/output interface 105 is an interface for connecting the information processing device 10 and peripheral devices. When the information processing device 10 is configured as an integrated device with an entrance gate or a security door, an imaging device 20 whose imaging range includes the vicinity of the entrance gate or security door is connected to the input/output interface 105. Furthermore, if the information processing device 10 is an administrator terminal located away from an entrance gate or a security door, an imaging device 20 for capturing a face image of a person is separately connected to the input/output interface 105. may have been done. In addition, there are input devices such as display output devices such as LCD (Liquid Crystal Display) and CRT (Cathode Ray Tube) displays, input devices such as keyboards and mice, and touch panels that combine these devices. It is connected to the information processing device 10 via the output interface 105.

The network interface 106 is an interface for connecting the information processing device 10 to a communication network such as a LAN (Local Area Network) or a WAN (Wide Area Network). Note that the method of connecting to the communication network may be a wireless connection or a wired connection. As shown in FIG. 4, the information processing device 10 can connect to a communication network via the network interface 106 and communicate with other terminals (not shown). For example, if the information processing device 10 is an administrator terminal located far from the entrance gate or security door, the information processing device 10 may be connected via the network interface 106 to the imaging device 20 whose imaging range includes the vicinity of the entrance gate or security door. Connected for communication. Note that when the imaging device 20 is connected to another device (not shown), the information processing device 10 first communicates with the other device via the network interface 106. Then, the information processing device 10 can acquire information on the video captured by the imaging device 20 via the other device. Further, in this case, the information processing device 10 can control the imaging device 20 via the other device.

As described above, according to this embodiment, the same effects as in the first embodiment can be obtained.

[Third embodiment]
This embodiment has the same configuration as the first or second embodiment except for the following points. Note that the following description will be based on the configuration of the second embodiment (FIG. 2).

[Functional configuration]
FIG. 5 is a block diagram conceptually showing the functional configuration of the information processing device 10 in the third embodiment. As shown in FIG. 5, the information processing device 10 of this embodiment further includes a notification unit 160.

If the selection unit 120 does not detect a face image with a qualification level equal to or higher than the first reference value within a predetermined time, the notification unit 160 sends an analysis result to at least a portion of the face image extracted by the extraction unit 110. The instruction information is generated based on the instruction information. Then, the notification unit 160 notifies the user of the instruction information via a predetermined output device such as a display, a speaker, or an indicator light.

[Hardware configuration]
The information processing device 10 of this embodiment has the same hardware configuration as that described in the second embodiment (eg, FIG. 4). The storage device 104 of this embodiment further stores a program module that implements the functions of the notification section 160 described above, and when the processor 102 executes this program module, the functions of the notification section 160 are realized.

[Operation example]
The flow of processing executed by the information processing device 10 of this embodiment will be described using some specific examples.

<First specific example>
FIG. 6 is a flowchart showing a first specific example of processing executed by the information processing device 10. In this specific example, an example will be shown in which the operation of the information processing device 10 is executed by an administrator or a person registered with identification information operating a predetermined terminal.

First, the extraction unit 110 detects an operation that starts registration processing of person identification information (S102). The "operation to start the registration process of person identification information" includes, for example, the administrator's pressing of a predetermined button (the button that starts the registration process prepared on the screen), the administrator's login operation (ID and password (input operations such as inputting information such as inputting a special card and having a card reader read a special card), and inputting necessary information (name, department, one-time password, etc.) by a registered person for identification information. The extraction unit 110 can receive operations via an input device (keyboard, touch panel, etc.) connected to the input/output interface 105. Further, if a separate terminal is provided that accepts an operation to start the registration process of person identification information, the extraction unit 110 communicates with the terminal via the network interface 106 to start the registration process of the person identification information. An operation to start can be detected. The extraction unit 110 instructs the imaging device 20 to start capturing a moving image in response to the detection of the registration processing start operation (S104). Note that if the imaging device 20 is always activated, the process of S104 may not be executed.

Then, the extraction unit 110 acquires a moving image (frame image) from the imaging device 20 (S106). The extraction unit 110 uses a known image processing algorithm to extract a region of a person's face (face image) from the frame image acquired in the process of S106 (S108). Here, facial images of multiple different people may be extracted. Then, a candidate image determination process as shown in FIG. 8, which will be described later, is executed using the face image extracted in the process of S108 (S110). Note that when facial images of a plurality of different people are extracted in the process of S108, candidate image determination processing is executed for each of the plurality of people.

As a result of executing the candidate image determination process, if face image candidates to be used in the identification information registration process are determined for all persons (S112: YES), the display processing unit 140 displays the screen ( Example: FIG. 7) is displayed on the display for the administrator or registered person (S114). FIG. 7 is a diagram showing an example of a screen displayed by the display processing section 140. On the screen in FIG. 7, facial image candidates to be used in the registration process of person identification information are displayed for each of the three people. In addition, the screen shown in FIG. 7 includes a screen element (attribute information field) 62 that allows selection of attribute information of each person to be linked to the identification information, in addition to face image candidates used in the registration process of person identification information. Displayed. In addition, in the registration process of person identification information, the face image itself displayed on the screen of FIG. 7 or the feature quantity that can be extracted from the face image can be registered, but from the viewpoint of privacy etc. Preferably, it is configured to register. In the screen element 62, for example, various information (name, department, etc.) input by the person to be registered for identification information in the process of S102 is set as attribute information of the person. Note that the screen element 62 may be configured to allow additional input of other attribute information. In addition, the display processing unit 140 further includes a screen element (delete button) 64 for deleting a face image of a person who is not a registration target in order to cope with the case where the face image of a person who is not a registration target is displayed by mistake. The screen may also be displayed. In addition, the information processing device 10 uses the face image itself or its features determined by the candidate image determination unit 130 as the identification information of the person, without displaying the screen as shown in FIG. 7. It may be configured to automatically register in a database referenced in the authentication process. In this case, the display processing unit 140 may display a screen for confirming registered information, instead of displaying a screen as shown in FIG. 7. In this case, the database administrator or the like can additionally input attribute information of the person by using a screen such as the one shown in FIG. 7 after registering the identification information in the database.

On the other hand, if the facial image candidate used in the identification information registration process has not been determined for at least one person (S112: NO), the notification unit 160 notifies instruction information so that an appropriate facial image can be acquired. A process (hereinafter also referred to as "notification process") to guide the user is executed. This notification process will be described later.

In this specific example, a video of the registered person is shot in parallel in response to the operation of the terminal by the administrator or the registered person of identification information. Thereby, the time can be shortened compared to the case where facial images of the person to be registered with identification information are photographed sequentially.

<<Candidate image determination process>>
A specific flow of the candidate image determination process in S110 will be illustrated using FIG. 8. FIG. 8 is a flowchart illustrating the flow of candidate image determination processing in S110.

First, the selection unit 120 calculates the eligibility of the face image (S202). This face image is the face image extracted in the process of S108 described above with reference to FIG. For example, as described in the first embodiment, the selection unit 120 can calculate the eligibility of the face image using various functions and tables. Then, the selection unit 120 determines whether the eligibility degree calculated in S202 is equal to or greater than the first reference value R1 (S204).

If the eligibility calculated in S202 is less than the first reference value R1 (S204: NO), the candidate image determining unit 130 checks whether a predetermined time has elapsed or a predetermined termination operation has been performed. (S218). If the predetermined time has elapsed or if a predetermined termination operation has been performed (S218: YES), the determination process of S112 in FIG. 6 is executed. On the other hand, if the predetermined time has not elapsed and the predetermined termination operation has not been executed (S218: NO), a new frame image is acquired as a new processing target. Then, the process is repeated from S202 on the new face image extracted from the new frame image.

On the other hand, if the eligibility calculated in S202 is equal to or greater than the first reference value R1 (S204: YES), the selection unit 120 notifies the candidate image determination unit 130 of the determination result in S204. In response to the notification from the selection unit 120, the candidate image determination unit 130 refers to the storage unit 150 and determines whether face image candidates of the same person are already stored in the storage unit 150. is determined (S206). Specifically, the candidate image determining unit 130 uses the first face image or its feature amount stored in the storage unit 150 and the second face image extracted in the process of S108 described in FIG. 6 above. Alternatively, it can be determined whether or not a facial image candidate of the same person is already stored in the storage unit 150 by comparing the feature amount.

If candidates for facial images of the same person are already stored in the storage unit 150 (S206: YES), the candidate image determining unit 130 reads the qualification degree of the first facial image stored in the storage unit 150, It is compared with the eligibility of the second face image calculated in the process of S202 (S208). Then, the candidate image determining unit 130 selects the one of the two facial images with a higher degree of eligibility as a facial image candidate to be used in the registration process of identification information of the person. Specifically, if the qualification degree of the second face image is greater than the qualification degree of the first face image (S210: YES), the candidate image determination unit 130 determines that the candidate image is extracted by the extraction unit 110 in the process of S108. The facial image obtained is selected as a facial image candidate to be used as identification information. At this time, the candidate image determining unit 130 replaces the first face image or its feature amount and information regarding the qualification degree stored in the storage unit 150 with the second face image or its feature amount and information regarding the qualification degree. The information is updated using the information (S212). On the other hand, if the qualification level of the first face image is equal to or higher than the qualification level of the second image (S210: NO), the candidate image determination unit 130 selects the first face image stored in the storage unit 150 or The information regarding the feature amount and eligibility level is maintained as is.

Note that the comparison process in S208 is executed each time the extraction unit 110 detects a new face image of the same person that has a qualification level equal to or higher than the first reference value R1. Then, the storage unit 150 may be updated multiple times according to the comparison result between the new face image qualification level and the face image qualification level stored in the storage unit 150. The storage unit 150 stores the face image with the highest degree of qualification at the current moment for each person.

On the other hand, if the candidate face image of the same person is not stored in the storage unit 150 (S206: NO), the face image extracted by the extraction unit 110 in the process of S108 is used as the face image to be used for the identification information registration process. Select as a candidate. At this time, the candidate image determination unit 130 updates the storage unit 150 using the face image or its feature extracted by the extraction unit 110 in the process of S108 and information regarding the eligibility degree (S212).

When the information in the storage unit 150 is updated, the display processing unit 140 updates the display content of the screen as shown in FIG. 7, for example, using the face image extracted by the extraction unit 110 in the process of S108 ( S214).

The candidate image determining unit 130 then determines whether a predetermined termination condition for the candidate image determining process is satisfied. Specifically, the candidate image determination unit 130 determines whether the eligibility degree of the face image calculated in S202 is equal to or higher than the second reference value R2, which is larger than the first reference value R1 (S216). If the eligibility degree of the face image calculated in S202 is equal to or higher than the second reference value R2 (S216: YES), the candidate image determining unit 130 ends the iterative process from S106. As a result, facial images having a qualification level equal to or higher than the second reference value R2 are determined as facial image candidates to be used in the identification information registration process. By doing so, when a facial image with sufficient qualification for a certain person is found, the process of selecting a facial image for that person is completed. This can be expected to have the effect of reducing the overall processing amount.

On the other hand, if the eligibility degree of the face image calculated in S202 is less than the second reference value R2 (S126: NO), the candidate image determining unit 130 determines whether a predetermined time has elapsed or a predetermined termination operation (as shown in the figure) is performed. Further, it is determined whether or not (such as pressing an end button) has been executed (S218). If the predetermined time has elapsed or if a predetermined termination operation has been performed (S218: YES), the candidate image determining unit 130 terminates the repeated processing from S106. As a result, the face image (the face image stored in the storage unit 150) having the highest degree of eligibility at that time is determined as the face image candidate to be used in the identification information registration process. By doing this, even if a facial image with sufficient qualification is not found for a certain person, once a facial image with a certain degree of qualification is found, the process of selecting a facial image for that person is completed. . This can be expected to have the effect of reducing the overall processing amount. On the other hand, if the predetermined time has not elapsed and the predetermined termination operation has not been executed (S218: NO), a new frame image is acquired as a new processing target. Then, the process is repeated from S202 on the new face image extracted from the new frame image.

<<Notification processing>>
FIG. 9 is a flowchart for explaining the flow of notification processing executed by the notification unit 160.

Based on the face images that were not determined as face image candidates, the notification unit 160 analyzes the cause of lowering the eligibility of the face images (S302). Then, the notification unit 160 creates instruction information based on the cause determined through the analysis (S304). For example, assume that the reason for lowering the eligibility level was "out of focus of the face image." If the notification unit 160 determines that the cause is "out of focus of the face image," it provides instruction information for correcting the registrant's standing position with respect to the camera (for example, "a little out of focus") based on the degree of out of focus. (e.g., information that includes a voice message such as "Please stand back."). For example, suppose that the reason for lowering the eligibility level was ``the orientation or inclination of the face (such as the face facing downward)''. If the notification unit 160 determines that the cause is the "direction or inclination of the face," the notification unit 160 provides instructional information (for example, "Please look at the landmark in front of you") to correct the direction or inclination of the registered person's face. (e.g., information that includes audio messages such as Messages, or instructions to activate buzzers or indicator lights to attract attention). For example, suppose that the cause of lowering the eligibility level was "wearing sunglasses, masks, etc." If the notification unit 160 determines that the cause is "wearing sunglasses or a mask," the notification unit 160 sends instruction information (for example, a voice saying "Please take off your sunglasses or mask") prompting the registered person to take off his sunglasses or mask. information, including messages). For example, assume that the cause of lowering the eligibility level was "shaking of the subject." If the notification unit 160 determines that "subject blur" is the cause, the notification unit 160 provides instruction information for correcting the subject blur (for example, information including a voice message such as "Please stand still for a moment"). Create.

The notification unit 160 may generate instruction information that allows a person for whom a facial image candidate could not be determined to be identified. A screen (eg, FIG. 10) that notifies only the persons for whom face image candidates have been determined may be displayed on the display for the registered person. In addition, the notification unit 160 displays a screen (for example, FIG. 11, FIG. 12) for the registered person to notify the registered person of a person for whom a facial image candidate has been determined and a person for whom a facial image candidate has not been determined. It may be displayed on the display. In FIG. 12, an example is shown in which a panoramic view of the image currently generated by the imaging device 20 is displayed on the display for the registered person, and a predetermined mark is placed on a person whose face image candidate could not be determined. ing. Further, at this time, the notification unit 160 may further display instruction information (such as "Please remove the mask" in the example of FIG. 12) based on the cause determined by the analysis on the screen. In addition, the notification unit 160 sends at least one of the person for whom a facial image candidate has been determined and the person for whom a facial image candidate has not been determined to voice data (for example, a voice message such as "2 out of 3 people can be registered"). (data) may be configured to further output.

Then, the notification unit 160 transmits the instruction information generated in S304 to a predetermined output device, and causes the output device to execute a notification process based on the instruction information (S306). For example, the notification unit 160 outputs the above-mentioned instruction information to an output device such as a monitor or a speaker for the registered person, and provides a notification to guide the registered person via the output device. Thereby, even when the administrator is not nearby (for example, when the administrator is absent), the registered person can be guided so that an appropriate facial image can be obtained.

Further, the notification unit 160 may be configured to output instruction information to an output device for an administrator. In this case, based on the instruction information from the notification unit 160, a blinking operation of an indicator light provided for the administrator and an operation of outputting a predetermined voice message on the administrator's terminal are executed. Thereby, it is possible to notify the administrator that the face image of the registered person has not been captured properly. After confirming this notification, the administrator can guide the registered person to obtain an appropriate facial image.

<Second specific example>
FIG. 13 is a flowchart showing a second specific example of processing executed by the information processing device 10. This specific example shows an example in which the information processing device 10 selects face image candidates based on a moving image (or a plurality of still images) generated by an imaging device 20 provided near an entrance to a specific area.
More specifically, information processing is performed using a video (or multiple still images) generated by an imaging device 20 such as a surveillance camera installed near an entrance gate or security door that prevents unauthorized persons from entering. An example will be shown in which the device 10 selects facial image candidates.

First, the imaging device 20 provided near the entrance gate captures a video in the vicinity of the entrance gate (for example, the passageway toward the entrance gate) (S402). Next, a computing device built into the entrance gate executes personal authentication processing using the face image of the person in the video shot in the process of S402, and determines whether the person is allowed to pass through the entrance gate. (S404). Here, if the personal authentication process is successful (S404: authentication successful), the entrance gate opens (S406) and the person can pass through the entrance gate. On the other hand, if the personal authentication process fails (S404: authentication failure), the video used in the personal authentication process is transmitted to the extraction unit 110 (S408). When the personal authentication process at the entrance gate fails, the extraction unit 110 acquires a video generated by the imaging device 20 and extracts a facial image from the video (S410). The processing after S412 is the same as the processing after S110 in the first specific example.

In this specific example, when the personal authentication process at the entrance gate fails, a moving image generated by the imaging device 20 is transmitted to the extraction unit 110. This video is used for personal authentication processing to determine whether or not a person can enter the entrance gate. That is, in this specific example, the information processing device 10 uses a video that has been previously acquired in a process (personal authentication process) that is different from the process of registering person identification information. Thereby, there is no need to provide a step of photographing a person's face image again, and as a result, an effect of shortening the processing time can be expected.

<Third specific example>
FIG. 14 is a flowchart showing a third specific example of processing executed by the information processing device 10. In this specific example, face image candidates to be used for personal identification information registration processing are determined based on the shooting of a moving image or a plurality of still images by the imaging device 20, regardless of the presence or absence of a special trigger such as a failure of personal authentication processing. The following is an example of the flow in which is automatically selected.

The extraction unit 110 communicates with an imaging device 20 provided near an entrance gate, a security door, etc., and acquires a moving image (frame image) generated by the imaging device 20 (S502). Next, the extraction unit 110 extracts a region of the person's face (face image) from the acquired frame image using a known image processing algorithm (S504). The selection unit 120 and the candidate image determination unit 130 execute image candidate determination processing as shown in FIG. 8 (S506). As a result of the processing in S506, if facial image candidates to be used in the identification information registration process are determined, the candidate image determining unit 130 displays a list of the determined facial images on the display of the administrator terminal (S508). The administrator checks the facial images displayed in the list and performs a facial image selection operation (S510). The information processing device 10 additionally registers the selected face image or identification information including its feature amount in a predetermined database (S512). Note that the candidate image determining unit 130 can delete a face image from the list after determining that it is not a face image to be used in the identification information registration process after a predetermined period of time has passed since the face image was displayed in the list.

As described above, in this specific example, a list of facial image candidates determined by the candidate image determination unit 130 for a person who passed in front of the imaging device 20 is displayed on the screen of the administrator terminal. The administrator can check the facial image candidates that are coming up one after another and register the necessary facial images in the database as information for personal authentication. With this configuration as well, when registering identification information to be used for personal authentication, there is no need to photograph and select an appropriate facial image, and the time required for identification information registration processing can be shortened.

[Fourth embodiment]
[Functional configuration]
FIG. 15 is a block diagram conceptually showing the functional configuration of the information processing device 10 according to the fourth embodiment. As shown in FIG. 15, the information processing device 10 of this embodiment further includes a determination section 170 and a registration section 180.

The determination unit 170 determines whether a pre-registered face image of a specific person exists among the face images extracted from the video by the extraction unit 110. When a facial image of a specific person is detected by the determining unit 170, the registration unit 180 registers the facial image determined by the candidate image determining unit 130 based on the facial images of other people extracted together with the specific person. Identify candidates and perform registration processing.

[Hardware configuration]
The information processing device 10 of this embodiment has the same hardware configuration as that described in the second embodiment (eg, FIG. 4). The storage device 104 of this embodiment further stores program modules that implement the functions of the determination unit 170 and the registration unit 180 described above, and when the processor 102 executes these program modules, the determination unit 170 and the registration unit 180 are executed. The functions of the registration unit 180 are realized.

[Operation example]
The flow of processing executed by the information processing device 10 of the fourth embodiment will be described using FIG. 16. FIG. 16 is a flowchart illustrating the flow of processing executed by the information processing device 10 of the fourth embodiment.

First, the imaging device 20 provided near the entrance gate captures a video in the vicinity of the entrance gate (for example, the passageway toward the entrance gate) (S602). The extraction unit 110 always or periodically acquires a moving image (frame image) generated by the imaging device 20 (S604). Then, the extraction unit 110 extracts a region of the person's face (face image) from the acquired frame image using a known image processing algorithm (S606). The information processing apparatus 10 then executes candidate image determination processing as described using FIG. 8 (S608). When a facial image candidate is determined in the process of S608, information including the facial image or feature amount is stored in the storage unit 150.

Next, after the information is stored in the storage unit 150, the determination unit 170 determines whether a pre-registered face image of a specific person exists among the face images of people extracted by the extraction unit 110 at another timing. It is determined whether or not (S610). The specific person is, for example, a manager who performs registration processing of identification information at an entrance gate. Identification information of a specific person is stored in advance in the memory 103, storage device 104, or the like. The determining unit 170 can determine whether a facial image of the specific person exists among the extracted facial images, based on the identification information of the specific person. Further, the determination unit 170 can detect the presence of a person other than the specific person based on the identification information of the specific person.

If the face image of a specific person registered in advance is not detected (S610: NO), the process described in the subsequent process is skipped. On the other hand, if a pre-registered face image of a specific person is detected (S610: YES), the determination unit 170 notifies the registration unit 180 that the face image of the specific person has been detected. The registration unit 180 refers to the storage unit 150 using the face image of another person or its feature amount extracted together with the face image of the specific person in the process of S610, and registers the identification information about the person in the process of registering identification information. It is confirmed whether or not face image candidates to be used are stored (S612).

Regarding the above-mentioned other person, if the candidate face image used in the identification information registration process is stored in the storage unit 150 (S612: YES), the registration unit 180 stores the face image candidates stored in the storage unit 150. Identification information is generated based on the facial image candidates and registered in a predetermined database (S614). On the other hand, if the face image candidate used in the identification information registration process for the other person is not stored in the storage unit 150 (S612: NO), the registration unit 180 does not execute the registration process.

As described above, in this embodiment, the validity of the person who is authorized to pass through the entrance gate is guaranteed by the presence of a specific person. This makes it possible to register identification information used for personal authentication with a simple operation of taking a photograph with a specific person.

[Fifth embodiment]
[Functional configuration]
FIG. 17 is a block diagram conceptually showing the functional configuration of the information processing device 10 of the fifth embodiment. The information processing device 10 of this embodiment further includes a group information adding section 190.

If the extraction unit 110 detects a facial image of another person within a predetermined time after the extraction unit 110 detects a facial image of one person, the group information adding unit 190 applies information to the one person and the other person. group information indicating that they belong to the same group.

[Hardware configuration]
The information processing device 10 of this embodiment has the same hardware configuration as that described in the second embodiment (eg, FIG. 4). The storage device 104 of this embodiment further stores a program module that realizes the functions of the group information adding section 190 described above, and when the processor 102 executes this program module, the functions of the group information adding section 190 are realized. Realized.

[Operation example]
The flow of processing executed by the information processing device 10 of the fifth embodiment will be described using FIG. 18. FIG. 18 is a flowchart illustrating the flow of processing executed by the information processing device 10 of the fifth embodiment.

First, the group information adding unit 190 starts a timer in accordance with the timing at which the first person's face image is detected in the process of S106 (S702). The group information adding unit 190 monitors whether or not the face image of the second person is detected within a predetermined period of time counted by the timer. If the count time of the timer passes the predetermined time without detecting the face image of the second person (S704: NO), the process of this embodiment ends. On the other hand, if the face image of another person is detected before the timer count time passes the predetermined time (S704: YES), the group information adding unit 190 detects the face image of the first person and the second person. Group information to be added to the face image is generated (S706). The group information is, for example, information indicating a specific group such as a department or a family. The group information may be a unique identifier arbitrarily assigned on the system. Note that if the face images of three or more people are detected before the timer count time elapses for a predetermined time, the group information adding unit 190 detects the face images of the three or more people. Manage as a target for group information.

Next, the group information adding unit 190 monitors whether the identification information registration process has been executed using the face image detected in the above process (S708). If the identification information registration process is executed using the detected face image (S708: YES), the group information adding unit 190 adds the group information generated in the process of S706 to the newly registered identification information. Grant (S710).

As described above, according to the present embodiment, identification information of a plurality of people can be easily linked and managed as the same group. For example, the same group information can be linked to the identification information of a plurality of administrators as the specific person described in the fourth embodiment. In this case, in the fourth embodiment, control such as enabling registration processing to be executed is possible when a certain percentage or more (for example, all of the administrators) of a plurality of administrators belonging to the same group are detected. This reduces the possibility of a situation where an administrator accidentally ends up in the same image and the personal authentication information of an unintended person is mistakenly registered in the database, thereby strengthening security. I can do it.

[Sixth embodiment]
[Functional configuration]
FIG. 19 is a block diagram conceptually showing the functional configuration of the information processing device 30 of the sixth embodiment. As shown in FIG. 19, the information processing device 30 includes a cutting section 310 and a registration section 320.

The cutting unit 310 cuts out facial images of other people who are photographed together with a specific person from the image. The specific person is, for example, an administrator who manages identification information used for personal authentication. The cutting unit 310 uses the face image of a specific person registered in advance or its feature amount to extract other people other than the specific person from the image in the same manner as described in the fourth embodiment. can cut out face images. Specifically, a known image processing algorithm is used to detect a face area in an image, and the feature values of the detected face area are combined with the feature values of a pre-registered face image of a specific person. By comparing the images, the extraction unit 310 can extract the face image of the specific person's face of another person. The registration unit 320 uses the other person's face image cut out by the cutout unit 310 or its feature amount to register identification information for identifying the other person.

[Hardware configuration]
Each functional component of the information processing device 30 may be realized by hardware (e.g., a hardwired electronic circuit) that implements each functional component, or by a combination of hardware and software (e.g., (e.g., a combination of an electronic circuit and a program that controls it). A case in which each functional component of the information processing device 30 is realized by a combination of hardware and software will be further described below.

FIG. 20 is a diagram conceptually showing the hardware configuration of the information processing device 30. As shown in FIG. As shown in FIG. 20, the information processing device 30 includes a bus 301, a processor 302, a memory 303, a storage device 304, an input/output interface 305, and a network interface 306.

The bus 301 is a data transmission path through which the processor 302, memory 303, storage device 304, input/output interface 305, and network interface 306 exchange data with each other. However, the method of connecting the processor 302, memory 303, storage device 304, input/output interface 305, network interface 306, etc. to each other is not limited to bus connection.

The processor 302 is an arithmetic device such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). The memory 303 is a main storage device implemented using RAM (Random Access Memory), ROM (Read Only Memory), or the like. The storage device 304 is an auxiliary storage device implemented using an HDD (Hard Disk Drive), an SSD (Solid State Drive), a memory card, or the like.

The storage device 304 stores program modules that implement each functional component (extracting unit 310, registration unit 320) of the information processing device 30. The processor 302 reads each of these program modules into the memory 303 and executes them, thereby realizing the functions corresponding to each program module.

The input/output interface 305 is an interface for connecting the information processing device 30 and peripheral devices. When the information processing device 30 is configured as an integrated device with an entrance gate or a security door, the input/output interface 305 is connected to the imaging device 20 whose imaging range includes the vicinity of the entrance gate or security door. Furthermore, if the information processing device 30 is an administrator terminal located away from an entrance gate or a security door, an imaging device 20 for capturing a face image of a person is separately connected to the input/output interface 105. may have been done. In addition, there are input devices such as display output devices such as LCD (Liquid Crystal Display) and CRT (Cathode Ray Tube) displays, input devices such as keyboards and mice, and touch panels that combine these devices. It is connected to the information processing device 30 via the output interface 105.

The network interface 306 is an interface for connecting the information processing device 30 to a communication network such as a LAN (Local Area Network) or a WAN (Wide Area Network). Note that the method of connecting to the communication network may be a wireless connection or a wired connection. As shown in FIG. 20, the information processing device 30 can connect to a communication network via a network interface 306 and communicate with other terminals (not shown). For example, if the information processing device 30 is an administrator terminal located far from the entrance gate or security door, the information processing device 30 may be connected to the imaging device 20 whose imaging range includes the vicinity of the entrance gate or security door via the network interface 306. Connected for communication. Note that when the imaging device 20 is connected to another device (not shown), the information processing device 30 first communicates with the other device via the network interface 306. Then, the information processing device 30 can acquire information on the video captured by the imaging device 20 via the other device. Further, in this case, the information processing device 30 can control the imaging device 20 via the other device.

[Operation example]
The flow of processing executed by the information processing device 30 of the sixth embodiment will be described using FIG. 21. FIG. 21 is a flowchart illustrating the flow of processing executed by the information processing device 30 of the sixth embodiment.

When the extraction unit 310 acquires an image in which a specific person and another person are photographed (S802), the extraction unit 310 extracts identification information of the specific person (a facial image of the specific person or The plurality of facial images included in the image are divided into facial images of a specific person and facial images of other people using the feature amount (S804). The cutout section 310 transfers the cut out face image of another person to the registration section 320. Note that the cutting unit 310 can use the identification information of other registered persons to identify other persons whose identification information has already been registered, and further exclude the facial image of the specified person.

The registration unit 320 generates the face image of the other person (or its feature amount) received in the process of S804, and registers it in a predetermined database as identification information of the other person (S806). Note that the information processing device 30 can link attribute information to the registered identification information later, for example, via a screen as illustrated in FIG. 7 .

As described above, according to the present embodiment, personal authentication information can be registered in the database by a simple action of appearing in an image with a specific person.

Although the embodiments of the present invention have been described above with reference to the drawings, these are merely examples of the present invention, and various configurations other than those described above may also be adopted.

Further, in the plurality of flowcharts used in the above description, a plurality of steps (processes) are described in order, but the order of execution of the steps executed in each embodiment is not limited to the order of the description. In each embodiment, the order of the illustrated steps can be changed within a range that does not affect the content. Furthermore, the above-described embodiments can be combined as long as the contents do not conflict with each other.

Part or all of the above embodiments may be described as in the following additional notes, but are not limited to the following.
1.
Extracting means for extracting a plurality of facial images of the same person from a moving image or a plurality of still images generated by the imaging means;
Selection means for selecting a face image whose suitability as identification information for identifying the person is equal to or higher than a first reference value from among the plurality of face images extracted by the extraction means;
Candidate image determining means for determining facial image candidates to be used in the registration process of the person's identification information based on the qualification of the facial image selected by the selecting means;
display processing means for displaying the face image candidates determined by the candidate image determination means on a screen used in the registration process;
An information processing device comprising:
2.
further comprising a storage means for storing a first face image displayed as a candidate for the face image on the screen or its feature amount in association with the qualification degree of the first face image;
The candidate image determining means includes:
Determining whether a second face image related to the same person has been extracted by the extraction means based on the first face image or its feature amount stored in the storage means;
When the second face image is selected by the selection means as a face image having a degree of qualification equal to or higher than the first reference value, one of the first face images and the second face image having the higher degree of qualification determining the face image as a candidate for the face image to be used in the registration process;
1. The information processing device described in .
3.
The imaging means includes the vicinity of the entrance to the specific area in the imaging range.
1. or 2. The information processing device described in .
4.
The entrance includes an entrance gate or a security door.
3. The information processing device described in .
5.
The video is a video generated by the imaging means for use in personal authentication processing at the entrance gate.
4. The information processing device described in .
6.
The extracting means acquires the video captured by the imaging means and extracts the plurality of facial images when the personal authentication process fails.
5. The information processing device described in .
7.
The extraction means instructs the imaging means to start capturing the moving image in response to the start operation of the registration process.
1. to 6. The information processing device according to any one of the above.
8.
When the qualification level of the selected facial image is equal to or higher than a second reference value which is larger than the first reference value, the candidate image determining means selects the face image having a qualification level equal to or higher than the second reference value. Confirm as a candidate
1. to 7. The information processing device according to any one of the above.
9.
The candidate image determining means is configured to determine whether a face image is selected within the predetermined time if the selection means does not select a face image having a qualification level equal to or higher than a second reference value which is larger than the first reference value within a predetermined time. determining the face image with the highest degree of eligibility among the face images as the candidate;
1. to 7. The information processing device according to any one of the above.
10.
If the selection means does not detect a facial image having a qualification equal to or higher than the first reference value within a predetermined time, instruction information is provided based on the analysis result of at least a portion of the facial image extracted by the extraction means. further comprising notification means for generating the instruction information and notifying the instruction information via a predetermined output device;
1. to 9. The information processing device according to any one of the above.
11.
The display processing means causes the screen to include and display a screen element that makes it possible to select attribute information of the person to be linked to the identification information, in addition to face image candidates used in the registration process of the person's identification information.
1. to 10. The information processing device according to any one of the above.
12.
a determining means for determining whether a pre-registered specific person's face image exists among the person's face images extracted from the video by the extraction unit;
When the facial image of the specific person is detected by the determining unit, the facial image candidate determined by the candidate image determining unit is determined based on the facial images of other people extracted together with the specific person. a registration means for specifying and executing the registration process;
1. to 11. The information processing device according to any one of the above.
13.
When a face image of another person is further detected within a predetermined time after a face image of one person is detected, the same group information is added to the one person and the other person. further comprising means;
1. to 12. The information processing device according to any one of the above.
14.
The computer is
Extract multiple facial images of the same person from a video,
Selecting, from among the plurality of extracted face images, a face image whose suitability as identification information for identifying the person is equal to or higher than a first reference value;
determining facial image candidates to be used in the registration process of the person's identification information based on the qualification level of the selected facial image;
displaying the determined facial image candidates on a screen used in the registration process;
A method for determining person identification information, including:
15.
The computer,
further comprising a storage means for storing a first face image displayed as a candidate for the face image on the screen or its feature amount in association with the qualification degree of the first face image;
Determining whether a second face image related to the same person has been extracted based on the first face image or its feature amount stored in the storage means,
If the second face image is selected as a face image having a degree of qualification equal to or higher than the first reference value, the one with the higher degree of qualification among the first face image and the second face image is registered. Decide as a facial image candidate to be used in processing,
14. The method for determining person identification information described in .
16.
the computer acquires the video from an imaging means whose imaging range includes the vicinity of an entrance to a specific area;
14. or 15. The method for determining person identification information described in .
17.
The entrance includes an entrance gate or a security door.
16. The method for determining person identification information described in .
18.
The video is a video generated by the imaging means for use in personal authentication processing at the entrance gate.
17. The method for determining person identification information described in .
19.
the computer acquires the video captured by the imaging means and extracts the plurality of facial images when the personal authentication process fails;
18. The method for determining person identification information described in .
20.
the computer instructs the imaging means to start capturing the moving image in response to the registration processing start operation;
14. to 19. The method for determining person identification information according to any one of the above.
21.
If the degree of qualification of the selected facial image is equal to or higher than a second reference value which is larger than the first reference value, the computer determines the face image having the degree of qualification equal to or higher than the second reference value as the candidate. let,
14. to 20. The method for determining person identification information according to any one of the above.
22.
When the computer has not selected a face image having a qualification level equal to or higher than a second reference value that is larger than the first reference value within a predetermined time period, determining a highly qualified face image as the candidate;
14. to 20. The method for determining person identification information according to any one of the above.
23.
The computer generates instruction information based on an analysis result of at least a portion of the extracted facial images when a facial image having a qualification level equal to or higher than the first reference value is not detected within a predetermined time. , notifying the instruction information via a predetermined output device;
14. to 22. The method for determining person identification information according to any one of the above.
24.
The computer causes the screen to include and display a screen element that allows selection of attribute information of the person to be linked to the identification information, in addition to face image candidates used in registration processing of the person's identification information;
14. to 23. The method for determining person identification information according to any one of the above.
25.
The computer,
Determining whether a pre-registered specific person's face image exists among the person's face images extracted from the video,
As a result of the determination, if a facial image of the specific person is detected, the determined candidate for the facial image is identified based on the facial images of other people extracted together with the specific person, and the facial image candidate is identified. Execute the registration process,
14. to 24. The method for determining person identification information according to any one of the above.
26.
The computer,
If a face image of another person is further detected within a predetermined time after a face image of one person is detected, the same group information is assigned to the one person and the other person;
14. to 25. The method for determining person identification information according to any one of the above.
27.
to the computer, 14. to 26. A program that executes the method described in any one of the above.
28.
a cutting means for cutting out a face image of another person who is photographed together with a specific person from the image;
Registration means for registering identification information for identifying the other person using the face image of the other person extracted by the extraction means or its feature amount;
An information processing device comprising:
29.
The computer is
Cut out facial images of other people who appear with a specific person from the image,
registering identification information for identifying the other person using the cut out face image of the other person or its feature amount;
A method for registering person identification information, including:
30.
to the computer, 29. A program that executes the method described in .

10 Information processing device 101 Bus 102 Processor 103 Memory 104 Storage device 105 Input/output interface 106 Network interface 110 Extraction unit 120 Selection unit 130 Candidate image determination unit 140 Display processing unit 150 Storage unit 160 Notification unit 170 Determination unit 180 Registration unit 190 Group information Adding unit 20 Imaging device 30 Information processing device 301 Bus 302 Processor 303 Memory 304 Storage device 305 Input/output interface 306 Network interface 310 Extracting unit 320 Registration unit

Claims (11)

Extracting means for extracting a plurality of facial images of the same person from a moving image or a plurality of still images generated by the imaging means;
selection means for selecting a face image having a degree of eligibility as identification information for identifying the person from among the plurality of face images related to the same person extracted by the extraction means;
Candidate image determining means for determining facial image candidates to be used in the registration process of the person's identification information based on the qualification of the facial image selected by the selecting means;
determination means for determining whether a face image of a person registered in advance is detected from among the face images extracted by the extraction means;
If the face image extracted by the extraction means is a face image of a pre-registered person and is a face image of a specific person, the same person extracted together with the specific person may be Registration means for registering identification information for identifying the person using the facial image candidates determined by the candidate image determination means ;
analysis means for analyzing the face image extracted by the extraction means when a face image related to the same person having a qualification level equal to or higher than the first reference value is not detected within a predetermined time;
generating instruction information based on the analysis result of the analysis means, displaying the person for whom the facial image candidate could be determined and the person for whom the facial image candidate could not be determined via a predetermined output device; notification means for further displaying a predetermined mark and the instruction information to a person whose face image candidate could not be determined;
An information processing device comprising: The registration means detects the person registered in advance by the determination means, and when the face image of another person is detected within a predetermined time after the face image of the person is detected. , registering identification information identifying the other person;
The information processing device according to claim 1. The registration means registers identification information for identifying another person who is photographed together with the particular person when the determination means detects a plurality of the particular persons registered in advance.
The information processing device according to claim 1 or 2. The identification information is a face image or a feature amount of a person;
The information processing device according to any one of claims 1 to 3. The specific person is a person registered in advance as a person with management authority;
The information processing device according to any one of claims 1 to 4. Further comprising a storage means for storing the first face image determined as the face image candidate or its feature amount in association with the qualification degree of the first face image,
The candidate image determining means includes:
Determining whether a second face image related to the same person has been extracted by the extraction means based on the first face image or its feature amount stored in the storage means;
When the second face image is selected by the selection means as a face image having a degree of qualification equal to or higher than the first reference value, one of the first face images and the second face image having the higher degree of qualification determining the face image as a candidate for the face image to be used in the registration process;
The information processing device according to any one of claims 1 to 5 . When the qualification level of the selected facial image is equal to or higher than a second reference value which is larger than the first reference value, the candidate image determining means selects the face image having a qualification level equal to or higher than the second reference value. Confirm as a candidate
The information processing device according to any one of claims 1 to 6 . The candidate image determining means is configured to determine whether a face image is selected within the predetermined time if the selection means does not select a face image having a qualification level equal to or higher than a second reference value which is larger than the first reference value within a predetermined time. determining the face image with the highest degree of eligibility among the face images as the candidate;
The information processing device according to any one of claims 1 to 7 . When a face image of another person is further detected within a predetermined time after a face image of one person is detected, the same group information is added to the one person and the other person. further comprising means;
The information processing device according to any one of claims 1 to 8 . At least one computer
Extracting multiple facial images of the same person from a video or multiple still images generated by an imaging means,
Selecting a face image whose eligibility as identification information for identifying the person is equal to or higher than a first reference value from among the plurality of extracted face images related to the same person;
determining facial image candidates to be used in the registration process of the person's identification information based on the eligibility level of the selected facial image;
Determining whether or not a pre-registered person's face image is detected from the extracted face images,
When the extracted face image is a face image of a person registered in advance and is a face image of a specific person, the face determined for the same person extracted together with the specific person. Register identification information that identifies the person using image candidates ,
If a face image related to the same person having a qualification level equal to or higher than the first reference value is not detected within a predetermined time, analyzing the extracted face image;
Generate instruction information based on the result of the analysis, display the person for whom the facial image candidate was determined and the person for whom the facial image candidate could not be determined via a predetermined output device, and display the facial image candidate for the person for whom the facial image candidate could not be determined. further displaying a predetermined mark and the instruction information to the person for whom the candidate cannot be determined;
Information processing methods that include at least one computer,
extraction means for extracting a plurality of facial images of the same person from a moving image or a plurality of still images generated by the imaging means;
Selection means for selecting a face image having a degree of eligibility as identification information for identifying the person from among the plurality of face images related to the same person extracted by the extraction means, a first reference value or more;
Candidate image determining means for determining facial image candidates to be used in the registration process of the person's identification information based on the qualification of the facial image selected by the selecting means;
determination means for determining whether a face image of a person registered in advance is detected from among the face images extracted by the extraction means;
If the facial image extracted by the extracting means is a facial image of a pre-registered person and is a facial image of a specific person, the facial image of another person who is photographed together with the specific person. a registration means for registering identification information for identifying the
analysis means for analyzing the face image extracted by the extraction means when a face image related to the same person having a qualification level equal to or higher than the first reference value is not detected within a predetermined time;
generating instruction information based on the analysis result of the analysis means, displaying the person for whom the facial image candidate could be determined and the person for whom the facial image candidate could not be determined via a predetermined output device; notification means for further displaying a predetermined mark and the instruction information to a person whose face image candidate could not be determined;
A program to function as

Images