JP7775752B2 - Management device, management method, and management program - Google Patents

Description

This disclosure relates to a management device, a management method, and a management program for managing authentication processing.

Facial recognition processing is known as a means of identity verification. In facial recognition processing, a user's facial image is registered in advance, and identity verification is performed by comparing the facial image acquired during authentication with the registered image.

Preliminary registration of a facial image in facial recognition processing is performed by the user using a device such as a smartphone. One known technology for registering facial photos supports efficient registration by determining the suitability of the facial image and then processing the facial photo to suit the medium to be registered (see, for example, Patent Document 1). Another known technology improves authentication accuracy by using multiple facial recognition engines in facial recognition processing (see, for example, Patent Document 2).

JP 2016-81141 A Patent No. 6839313

The technology described in Patent Document 1 above makes it possible to efficiently register facial images to be used on media containing facial images.

However, the technology in Patent Document 1 may not be suitable for registering facial images to be used in facial recognition processing. In facial recognition processing, authentication is performed based on features extracted from a facial image, so when registering a facial image, it is necessary to determine whether the image is one from which features can be extracted (for example, whether the face is included in an appropriate area of the entire image, whether the brightness of the image is appropriate, etc.). For this reason, if the facial image is processed, such as by cropping, to fit the medium after determining its suitability, depending on the degree of processing, the processed image may become unusable for facial recognition processing, and registration may fail. Having to redo the registration due to a failed registration can increase the load on the server and impose a burden on the user.

This disclosure therefore proposes a management device, management method, and management program that allows users to register facial images accurately and with minimal burden on the user.

To solve the above problem, one embodiment of a management device according to the present disclosure includes: a reception unit that receives from a user a registration image that serves as the basis for correct answer data used for matching by each of multiple facial recognition engines in order to execute authentication processing using the multiple facial recognition engines; a quality determination unit that determines for each of the multiple facial recognition engines whether the registration image is of a quality that allows it to be used as correct answer data for the authentication processing of the multiple facial recognition engines; and a registration unit that registers the registration image when it is determined, based on the determination result by the quality determination unit, that the registration image is of a quality that allows it to be used as correct answer data for the authentication processing for all of the multiple facial recognition engines.

FIG. 10 is a diagram illustrating a flow of a registration process according to the embodiment. FIG. 2 is a diagram schematically illustrating a flow of face authentication processing according to the embodiment. FIG. 1 is a diagram (1) for explaining a registration process according to an embodiment. FIG. 10 is a diagram (2) for explaining the registration process according to the embodiment. FIG. 10 is a sequence diagram showing the procedure of a registration process according to the embodiment. FIG. 10 is a sequence diagram showing a procedure of face authentication processing according to the embodiment. 10 is a flowchart illustrating a determination procedure of face authentication processing according to the embodiment. FIG. 2 is a diagram illustrating an example of the configuration of a management device according to the embodiment. FIG. 4 is a diagram illustrating an example of a user information storage unit according to the embodiment. FIG. 4 is a diagram illustrating an example of a quality check item storage unit according to the embodiment. FIG. 4 is a diagram illustrating an example of a face photo storage unit according to the embodiment. FIG. 2 is a diagram illustrating an example of an external service information storage unit according to the embodiment. FIG. 2 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of a management device.

Embodiments of the present disclosure will be described in detail below with reference to the drawings. Note that in the following embodiments, identical components will be designated by the same reference numerals, and duplicate descriptions will be omitted.

1. EMBODIMENTS
(1-1. Example of management process according to embodiment)
1 and 2 schematically show the flow of a management process according to the embodiment. The management process according to the embodiment is executed by a management device 100 included in a management system 1 shown in Fig. 1. As shown in Fig. 1, the management system 1 includes the management device 100, a user terminal 20, and a face authentication provider 50.

The management device 100 is an information processing device that executes the management process according to the embodiment. For example, the management device 100 is a cloud server that can communicate with the user terminal 20 and the face authentication provider 50 via a network.

The user terminal 20 is an information processing terminal used by the user 10. For example, the user terminal 20 is a smartphone, tablet terminal, PC (Personal Computer), etc. The user terminal 20 according to the embodiment is equipped with a camera and is capable of capturing an image of the user 10's face.

Facial authentication provider 50 is a general term for businesses that provide facial authentication engines for performing facial authentication processing. Facial authentication providers 50 include, for example, a first provider that provides a first facial authentication engine 60, a second provider that provides a second facial authentication engine 70, and a third provider that provides a third facial authentication engine 80.

The first provider, second provider, and third provider are businesses that each offer a different facial recognition engine. The facial recognition engines offered by each provider have different characteristics in various respects, such as the method of detecting the area of a face in an image, extracting facial features, and matching features with each other. In other words, each facial recognition engine specializes in different image features (image brightness, the proportion of the area of the image that is occupied by the face, the skin color and facial features of the user to be authenticated, etc.). In the following description, when there is no need to distinguish between the first provider, second provider, and third provider, they may be collectively referred to as facial recognition provider 50.

The management device 100 according to the embodiment increases the accuracy and reliability of authentication by registering and matching a facial image with multiple facial recognition engines when a user 10 registers or authenticates a facial image. In other words, the management device 100 serves as a platform for executing authentication processing using multiple facial recognition engines.

Specifically, in order to execute authentication processes using multiple facial recognition engines, the management device 100 receives from the user 10 a facial image that will be the source of the correct answer data used for matching by each of the multiple facial recognition engines. The management device 100 also provides a processing means that allows the user 10 to process the received facial image. The management device 100 then determines whether the processed image, which is the processed facial image, is of a quality that allows it to be used as correct answer data for the authentication processes of the multiple facial recognition engines.

In this way, the management device 100 uses an image already processed by the user 10 to determine whether it can be used with each facial recognition engine, thereby preventing the user 10 from having to redo the process. The management device 100 may also verify the quality of the facial image for each of multiple facial recognition engines, and register the facial image only if it is verified as being of usable quality for all of the facial recognition engines used for authentication. This allows the management device 100 to perform highly accurate authentication using multiple facial recognition engines, while smoothly proceeding with the registration of facial images, which can often be cumbersome.

This management process will be explained using Figure 1, which explains the process of registering face images to multiple face recognition engines. Figure 1 is a diagram that schematically illustrates the flow of the registration process according to this embodiment.

In the example shown in FIG. 1, user 10 accesses management device 100 using user terminal 20 and requests registration of a facial image to be used in facial authentication (step S1). For example, user 10 requests registration of a facial image via a website provided by management device 100.

When the management device 100 receives the request, it provides the user terminal 20 with a web page or the like for facial image registration. The user 10 takes a picture of themselves using a camera provided on the user terminal 20 and sends the facial image to be registered to the management device 100. Details of facial image registration using a camera will be described later using Figure 3.

The management device 100 stores the facial image acquired from the user 10 in a storage unit as facial photo data 30. At this time, the management device 100 may determine whether the facial image meets the quality required by each facial recognition engine, and store the facial image as facial photo data 30 only if it determines that the quality is met. Furthermore, if the management device 100 determines that the facial image does not meet the quality requirements, it may request the user 10 to retake the photo or adjust the facial image by editing it.

If the facial image satisfies the quality requirements of each facial recognition engine and is eligible for registration, the management device 100 notifies the user 10 of this (step S2).

When the management device 100 acquires the facial photo data 30, it registers the facial photo data 30 in each facial recognition engine. For example, the management device 100 transmits the facial photo data 30 to a first provider having a first facial recognition engine 60, and requests registration to enable the first facial recognition engine 60 to be used for facial recognition of the user 10 (step S3).

The first provider extracts features from the acquired facial photo data 30 through a feature extraction process executed by the first face recognition engine 60 and stores them in the feature storage unit 62. For example, the first face recognition engine 60 extracts the facial features of the user 10 as parameters by hashing the facial image included in the facial photo data 30, and stores the extracted values as features in the feature storage unit 62. After this, the first provider may discard the facial photo data 30 itself. As a result, the first provider does not retain personal information such as the facial photo data 30, but only retains the features, thereby reducing the resources and effort required for data management.

Similarly, the management device 100 transmits facial photo data 30 to the second provider and requests registration to enable the second facial recognition engine 70 to be used for facial recognition of the user 10 (step S4). The second provider, like the first provider, extracts features from the acquired facial photo data 30 and stores them in the feature storage unit 72.

Similarly, the management device 100 transmits facial photo data 30 to the third provider and requests registration to enable the third face authentication engine 80 to be used for facial authentication of the user 10 (step S5). The third provider, like the first and second providers, extracts features from the acquired facial photo data 30 and stores them in the feature storage unit 82.

The management device 100 registers the user's 10 facial photo data 30 for each facial recognition engine to be used. Once registration is complete, the management device 100 associates information such as the user 10, the registered facial photo data 30, and the registered facial recognition engine, and stores the information in a memory unit.

Next, the flow of verifying the identity of a user 10 using facial authentication (matching process) will be described using Figure 2. Figure 2 is a diagram that schematically shows the flow of facial authentication processing according to an embodiment. The management system 1 shown in Figure 2 further includes an authentication terminal 40 and a service provider 200.

The authentication terminal 40 is an information processing terminal installed in a location where identity verification is required. The authentication terminal 40 can communicate with the management device 100 via a network, and for example, sends images taken with a camera equipped on the authentication terminal 40 to the management device 100. The authentication terminal 40 then obtains the authentication result from the management device 100 and notifies the person who requested authentication whether their identity has been verified (whether the face matches a registered facial image). The authentication terminal 40 also determines whether to provide a specified service based on the matching result.

The service provider 200 is a business that provides a variety of services. For example, the service provider 200 manages the authentication terminal 40 and provides a variety of services to users whose identities have been verified. Note that in this disclosure, the term "service" is not limited to commercial services, but is a general term for any mechanism or system that the user 10 intends to use, such as a factory entrance/exit control gate. For example, services include permission to enter and exit a specific facility, attendance management, and financial product settlement. The service provider 200 has user information 212, which is information about users who use the service, and business data 214, which stores the type and content of the service.

In the example of Figure 2, when user 10 attempts to use a service provided by service provider 200, he or she has the authentication terminal 40 photograph the user's image and attempts facial authentication. For example, when user 10 enters a facility where entry is controlled, user 10 requests authentication processing from authentication terminal 40 to verify the user's identity.

When the authentication terminal 40 captures an image of the user 10, it transmits the captured facial image for authentication to the management device 100 (step S11). The management device 100 then transmits the captured facial image for authentication to each facial authentication provider.

For example, the management device 100 transmits the authentication facial image to the first provider and causes the first facial recognition engine 60 to perform facial recognition based on the authentication facial image (step S12). Specifically, the first facial recognition engine 60 compares the features of the registered user 10 with the features extracted from the authentication facial image. The first facial recognition engine 60 then transmits a comparison result (matching result) between the features of the user 10 and the features extracted from the authentication facial image to the management device 100. If the similarity between the features acquired from the first facial recognition engine 60 is higher than a predetermined value, the management device 100 determines that matching between the pre-registered user 10 and the person associated with the authentication facial image (user 10 in this example) has been successful. On the other hand, if the similarity is lower than the predetermined value, the management device 100 determines that matching between the pre-registered user 10 and the person associated with the authentication facial image cannot be performed, and that the person's identity cannot be confirmed.

When face authentication by the first face recognition engine 60 is completed, the management device 100 stores the matching results in the authentication log 32. The first face recognition engine 60 may perform matching after recognizing that the person being matched is user 10 using an ID card or the like, or it may perform matching between the authentication face image and an unspecified number of pre-registered users. In the latter case, the first face recognition engine 60 is expected to extract, as a matching target, a user 10 who is determined to have a higher degree of similarity than other targets as a result of the matching.

Next, the management device 100 sends the authentication facial image to the second provider and has the second face authentication engine 70 perform facial authentication based on the authentication facial image (step S13). When facial authentication is complete, the second face authentication engine 70 sends the matching result to the management device 100. The management device 100 determines whether matching of the user 10 was successful based on the similarity between the feature amounts acquired as the matching result by the second face authentication engine 70 and stores the result in the authentication log 32. Similarly, the management device 100 sends the authentication facial image to the third provider and has the third face authentication engine 80 perform facial authentication based on the authentication facial image (step S14). When facial authentication is complete, the third face authentication engine 80 sends the matching result to the management device 100. The management device 100 determines whether matching of the user 10 was successful based on the similarity between the feature amounts acquired as the matching result by the third face authentication engine 80 and stores the result in the authentication log 32.

Then, the management device 100 transmits the authentication result for the user 10 to the authentication terminal 40 based on the matching results from the multiple face recognition engines (step S15). In other words, the management device 100 transmits to the authentication terminal 40 the result of its determination as to whether or not the service requested by the user 10 may be provided to the user 10.

At this time, the management device 100 may refer to the external service affiliation information 34 to determine the authentication result for the user 10. For example, the external service affiliation information 34 may include the security level required by the external service. In other words, the management device 100 compares the security level required by the service provider 200 with the matching results from multiple face recognition engines, and then transmits the authentication result for the user 10 to the authentication terminal 40 (step S15).

During service operation, various security levels can be set for the service. For example, when using the authentication process according to the embodiment for daily attendance management, if the authentication strength required is too high and authentication errors (situations in which it is difficult to confirm the identity of the user attempting authentication) occur frequently, usability may be reduced even if security is high. On the other hand, when using the authentication process according to the embodiment for payment processing at financial institutions, it is desirable to set the authentication strength extremely high to prevent fraudulent use.

For this reason, the management device 100 manages information such as the authentication strength required for each service. For example, if the service has low authentication strength, the management device 100 may allow the user 10 to use the service if at least one of multiple facial recognition engines has successfully authenticated the user. Alternatively, if the service has high authentication strength, the management device 100 may not allow the user 10 to use the service unless all of the multiple facial recognition engines have successfully authenticated the user.

The management device 100 obtains information regarding the authentication strength and the like from the service provider 200. Then, the management device 100 transmits to the service provider 200 a determination result as to whether the service is available or not, based on the result of matching the authentication face image with the user 10 (step S16). The service provider 200 provides a predetermined service to the user 10 whose identity has been confirmed, based on the determination result by the management device 100 (step S17). As an example, the service provider 200 notifies the user 10 via the authentication terminal 40 that the user 10's identity has been confirmed, and activates the gate opening/closing device to allow the user 10 to enter. Note that the provision of such a service may be performed by the management device 100 entrusted by the service provider 200.

As shown in FIG. 2, the management device 100 determines whether to permit user 10's request based on the authentication results of each of the multiple facial recognition engines that authenticated the facial image. In other words, by using multiple facial recognition engines, the management device 100 improves the accuracy of identity authentication and allows for flexible configuration of authentication strength for services involving authentication. In the above example, the management device 100 acquires the similarity determined by each facial recognition engine and determines whether user 10 has been successfully authenticated by judging the acquired similarity. However, the success or failure of facial recognition may be determined by each facial recognition engine rather than the management device 100. In this case, each facial recognition engine maintains a similarity reference value. Each facial recognition engine then compares the registered features of user 10 with the features extracted from the authentication facial image. If the similarity between the compared features is higher than a predetermined value, the engine determines that matching of user 10 has been successful and transmits the determination result to the management device 100. In other words, the entity that performs the success or failure of facial recognition may be either the management device 100 or each facial recognition engine.

Next, facial image registration according to the embodiment will be described in detail using Figures 3 and 4. Figure 3 is a diagram (1) for explaining the registration process according to the embodiment.

The management device 100 provides a specified registration page to a user 10 who wishes to register a facial image and accepts the registration request. Screen 300 shown in Figure 3 shows a dedicated page for facial image registration displayed on the user terminal 20.

On screen 300, user 10 sets an ID and password for registration and proceeds with the facial image registration process. When user 10 enters the ID and password, screen 300 transitions to screen 302 (step S21).

Screen 302 includes a preview image 304 to be captured with the camera provided on user terminal 20. Management device 100 displays guide 306 on preview image 304. Guide 306 indicates the desired area for the face to occupy in the captured image. Because facial recognition processing includes a step in which the facial recognition engine detects the face from the image, it is desirable for all parts that make up the face to be included in the image. For this reason, management device 100 displays guide 306, such as an indication of the area that the face will occupy and lines that serve as a guide for user 10 to bring their face to the center of the image, to encourage user 10 to take an appropriate photograph.

For example, the user 10 takes a picture of themselves using a camera installed inside (on the screen side of) the user terminal 20, adjusts the image while looking at the preview image 304 so that their face fits within the guide 306, and then presses the capture button 308. When the user 10 takes a picture in accordance with this operation, the management device 100 can obtain the facial image for registration via the user terminal 20.

When the image capture is complete, screen 302 transitions to screen 310 (step S22). At this stage, management device 100 may provide user 10 with editing tools for editing the captured image. Specifically, management device 100 may provide a trimming tool or the like for removing unnecessary portions of the captured image.

For example, if user 10 intends to use a captured image as a passport photo with a specified size, he or she can crop the captured image to the specified size. Furthermore, using the cropping tool, user 10 can also move the captured image. Therefore, if user 10's face is not within the circle of guide 306, user 10 can shift the entire image to adjust the face so that it is within the circle of guide 306. User 10 may also zoom in or out on the image by pinching in or out, adjusting the face to an appropriate size within the circle of guide 306. The management device 100 may also perform the cropping process automatically. For example, the management device 100 detects user 10's face using face detection processing and automatically adjusts the position of the detected face so that the coordinates of the detected face fit within the circle of guide 306. Furthermore, the management device 100 may automatically adjust the size of the detected face so that it fits within the circle of guide 306. Furthermore, the management device 100 may remove any unnecessary parts (such as the background) other than the detected face. In this way, the management device 100 automatically performs trimming, so that the user 10 can automatically obtain an image suitable for registration simply by taking an image that includes their face. This allows the management device 100 to reduce the burden on the user 10 associated with face registration.

Furthermore, the management device 100 may provide other processing means. This will be explained using Figure 4. Figure 4 is a diagram (2) for explaining the registration process according to the embodiment.

When user 10 finishes trimming, management device 100 transitions screen 310 in FIG. 3 to screen 320 shown in FIG. 4. On screen 320, user 10 can adjust the brightness of the entire image. For example, user 10 can adjust the overall brightness to be brighter or darker by operating brightness adjustment bar 322. Furthermore, when user 10 presses automatic brightness adjustment button 324, management device 100 may refer to the brightness of the current image and the reference brightness value required by the facial recognition engine, and automatically adjust the brightness so that it can be registered in the facial recognition engine. This allows user 10 to adjust the image to a brightness that can be registered without complex steps.

When user 10 has finished adjusting the brightness, management device 100 transitions screen 320 to screen 326 (step S31). On screen 326, user 10 can select the background of the image. For example, if user 10 wants to delete an unnecessary background that is included in the captured image, user 10 can change the captured image to processed image 328, in which the background has been changed to a solid white color, by pressing background selection button 330. Alternatively, if user 10 wants to use the captured image as an ID photo with a specified background, user 10 can change the background to a specified background (solid light blue, for example).

When the user 10 has finished adjusting the background, the management device 100 transitions screen 326 to screen 332 (step S32). At this stage, the management device 100 determines the quality of the processed image, which is the captured image after processing has been completed.

As will be described in more detail below, the management device 100 determines for each facial recognition engine whether the processed image meets the criteria that each facial recognition engine requires for a registered image. If the management device 100 determines that the processed image meets the criteria for registration requests from all facial recognition engines, it displays a determination result 336 indicating that the criteria are met. After checking the determination result 336, if the user 10 wishes to register the processed image, they press a save button 334. When the user 10 presses the save button 334, the management device 100 stores the processed image in the memory unit as a registration image to be used for registration.

If the edited image does not meet the criteria, the management device 100 transitions screen 326 to screen 338. On screen 338, the management device 100 displays a determination result 340 indicating that the edited image does not meet the criteria for the registration request of any of the face recognition engines and cannot be registered. As shown in FIG. 4, the management device 100 may also display in determination result 340 the content of the criteria that the edited image did not meet, based on the quality determination result. This allows the user 10 to obtain information on what points to pay attention to when creating a new edited image if they need to redo the shooting or editing.

When the management device 100 saves the processed image in the memory unit as a registration image to be used for registration, it transitions screen 332 to screen 342, displays a facial image registration completion display 344, and notifies the user 10 that registration is complete (step S33).

In this way, the management device 100 determines the quality of the processed image, determining whether it is suitable for registration in the face recognition engine, and therefore prevents situations that cause inconvenience to the user 10, such as cropping after a quality assessment, which could change the assessment result. Furthermore, the management device 100 can perform processing such as cropping and quality assessment all at once on the server-side platform, making it possible to obtain high-quality face images, which can lead to improved accuracy in feature extraction in the subsequent stages.

(1-2. Procedure of management process according to embodiment)
Next, the procedure of the management process according to the embodiment will be described with reference to Fig. 5 to Fig. 7. First, the flow of the registration process will be described with reference to Fig. 5. Fig. 5 is a sequence diagram showing the procedure of the registration process according to the embodiment.

As shown in FIG. 5, the user 10 applies for registration of a facial image via a website or the like provided by the management device 100 (step S40). Next, the user 10 takes a photograph of the facial image to be applied for. Note that if the user 10 has a previously taken image, they may select that image as the image to be used for registration (step S41).

When the user 10 takes a photo or selects an image, the facial image is sent to the management device 100 (step S42). The management device 100 accepts the facial image sent by the user 10 (step S43).

Then, the user 10 uses the processing means provided by the management device 100 to perform a series of processing operations on the facial image. For example, the user 10 performs a trimming operation, such as cutting out the facial portion (step S44). The management device 100 performs trimming operations on the facial image in accordance with the user's operations (step S45).

The user 10 also adjusts the brightness of the facial image using processing means provided by the management device 100 (step S46). The management device 100 adjusts the brightness of the facial image, such as brightening or darkening it, in accordance with the user's operation (step S47).

The user 10 also changes the background of the facial image using processing means provided by the management device 100 (step S48). The management device 100 changes the background of the facial image in accordance with the user's operation (step S49).

When the user 10 has finished processing the facial image and generated the processed image, the user 10 sends a quality check request for the processed image to the management device 100 (step S50). When the quality check request is sent from the user 10, the management device 100 sends the processed image to the face authentication provider 50 (step S51).

The facial authentication provider 50 performs a quality check to determine whether the processed image can be used for authentication processing in the facial authentication engine (step S52). This process is performed for each provider's facial authentication engine. The facial authentication provider 50 transmits the results of the quality check to the management device 100 (step S53).

The management device 100 references the quality check results from multiple facial recognition engines and determines whether there are any problems with all results (step S54). If it determines that there is a quality problem with any of the facial recognition engines (step S54; No), the management device 100 notifies the user 10 that registration is NG and the reason for this, as shown on screen 338 in FIG. 4 (step S55).

On the other hand, if it is determined that there are no quality issues in all face recognition engines (step S54; Yes), the management device 100 notifies the user that the registration judgment is OK, as shown on screen 332 in Figure 4 (step S56).

After confirming the notified results, the user 10 requests the management device 100 to register the authentication face image, for example by pressing the save button 334 displayed on the screen 332 (step S57).

When the management device 100 receives a registration request from the user 10, it registers the facial image whose quality has been judged as a facial image for authentication (step S58). The management device 100 then transmits the registered facial image for authentication to the respective facial authentication provider 50 (step S59). The facial authentication provider 50 reads the facial image for authentication into a facial authentication engine, extracts features, and then associates the features with the user ID and registers them (step S60). The facial authentication provider 50 may then discard the raw data of the acquired facial image for registration.

Next, the authentication process according to the embodiment will be described using Figure 6. Figure 6 is a sequence diagram showing the facial authentication process according to the embodiment.

As shown in FIG. 6, the authentication terminal 40 photographs the user 10 requesting facial authentication and acquires a facial image (step S70). The authentication terminal 40 then transmits the acquired facial image to the management device 100 (step S71).

When the management device 100 acquires a facial image, it sends the acquired facial image to the first face recognition engine 60 (step S72). The first face recognition engine 60 compares the acquired facial image with a registered face image and performs facial recognition processing (step S73). The management device 100 acquires the comparison result (first comparison result) from the first face recognition engine 60 (step S74).

Next, the management device 100 transmits the facial image acquired in step S72 to the second facial recognition engine 70 (step S75). The second facial recognition engine 70 compares the acquired facial image with a registered facial image and performs facial recognition processing (step S76). The management device 100 acquires the comparison result (second comparison result) from the second facial recognition engine 70 (step S77).

The management device 100 similarly sends the facial image to all facial recognition engines in which the facial image for authentication is registered, and obtains all matching results (step S80). In other words, the management device 100 similarly sends facial images to the third facial recognition engine 80 (not shown) and other registered facial recognition engines, and obtains matching results.

The management device 100 then judges the matching result (step S81). As described above, the success or failure of authentication by each facial recognition engine is determined based on whether the similarity between the feature amounts transmitted from the facial recognition engine exceeds a predetermined similarity. Details of the judgment process for determining whether to allow the user 10 to use the service based on multiple authentication judgments will be described later using Figure 7. After making this judgment, the management device 100 transmits the judgment result to the authentication terminal 40 (step S82). The authentication terminal 40 displays the result transmitted from the management device 100 on a screen or the like (step S83).

Next, the determination procedure for face authentication processing according to the embodiment will be described using Figure 7. Figure 7 is a flowchart showing the determination procedure for face authentication processing according to the embodiment.

As shown in FIG. 7, the management device 100 identifies the service that the user intends to use (step S101). For example, the management device 100 identifies the service that the user intends to use based on external service partnership information linked to the authentication terminal 40 and information about the service provider.

Then, the management device 100 refers to the criteria set for the service the user is attempting to use. For example, the management device 100 refers to criteria such as not allowing use of the service unless the matching results are OK in all face recognition engines, based on the authentication strength of the service, or allowing use of the service if the matching result is OK in any one face recognition engine (step S102).

The management device 100 then determines whether the matching results obtained from the multiple facial recognition engines satisfy the service's criteria (step S103). If the service's criteria are satisfied (step S103; Yes), the management device 100 determines that the facial authentication was successful (step S104). In other words, the management device 100 determines that the authenticated user should be permitted to use the service. On the other hand, if the service's criteria are not satisfied (step S103; No), the management device 100 determines that the facial authentication was unsuccessful (step S105). In other words, the management device 100 determines that the authenticated user should not be permitted to use the service.

(1-3. Configuration of management device according to embodiment)
Next, a configuration of the management device 100 that executes the management process according to the embodiment will be described. Fig. 8 is a diagram showing an example of the configuration of the management device 100 according to the embodiment.

As shown in FIG. 8, the management device 100 has a communication unit 110, a memory unit 120, and a control unit 130. The management device 100 may also have an input unit (e.g., a keyboard, a mouse, etc.) that accepts various operations from an administrator who manages the management device 100, and a display unit (e.g., an LCD display, etc.) that displays various information.

The communication unit 110 is realized, for example, by a NIC (Network Interface Card) or a network interface controller. The communication unit 110 is connected to a network N (e.g., the Internet) via a wired or wireless connection, and transmits and receives information to and from the user terminal 20, authentication terminal 40, face authentication provider 50, etc. via the network N. For example, the communication unit 110 may transmit and receive information using any communication standard or technology, such as Wi-Fi (registered trademark), Bluetooth, SIM (Subscriber Identity Module), or LPWA (Low Power Wide Area).

The storage unit 120 is realized, for example, by a semiconductor memory element such as RAM (Random Access Memory) or flash memory, or a storage device such as a hard disk or optical disk. The storage unit 120 has a user information storage unit 121, a quality check item storage unit 122, a facial photo storage unit 123, an authentication log storage unit 124, and an external service information storage unit 125.

The following describes each storage unit in order using Figures 9 to 12. Note that in the examples shown in Figures 9 to 12, information stored in storage unit 120 may be conceptually represented as "A01," but in reality, each piece of information described below is stored in storage unit 120.

The user information storage unit 121 stores information about users who use facial authentication. Figure 9 shows an example of information stored in the user information storage unit 121. Figure 9 is a diagram showing an example of the user information storage unit 121 according to an embodiment. In the example shown in Figure 9, the user information storage unit 121 has items such as "User ID," "Login information," "Facial photo registration," and "External service information."

"User ID" indicates identification information that identifies the user. "Login information" indicates login information required for facial photo registration, such as a password linked to the user ID. "Facial photo registration" indicates whether the user has registered a facial photo. "External service information" indicates information about external services used by the user.

The quality check item storage unit 122 stores information about quality check items for each face recognition engine. Figure 10 is a diagram showing an example of the quality check item storage unit 122 according to an embodiment. In the example shown in Figure 10, the quality check item storage unit 122 has items such as "Check Item," "First Face Recognition Engine," "Second Face Recognition Engine," and "Third Face Recognition Engine."

The quality check items shown in Figure 10 indicate what items each face recognition engine uses to check the quality of a face image and output a result of whether registration is OK or NG. The example shown in Figure 10 shows that the first face recognition engine determines the horizontal, vertical, and tilt blurring of the face angle in the image and determines whether these fall within predetermined standards. In other words, the first face recognition engine requires that the face in the image be facing accurately forward for registration, and this face angle is used as a quality check item. On the other hand, the example in Figure 10 shows that the third face recognition engine checks only tilt blurring, regardless of the horizontal or vertical angle of the face angle in the image. As such, each face recognition engine excels at different facial angles and characteristics, which contributes to differences in authentication results. When the management device 100 receives a registration NG determination from the first face recognition engine, it obtains the check items that were failed. The management device 100 can list the acquired information, for example, as the determination result 340 shown in Figure 4, and notify the user of the items in which the edited image to be registered was inappropriate.

Note that the quality check items shown in Figure 10 are just an example, and the management device 100 may store information related to various quality check items other than the example shown in Figure 10.

The facial photo memory unit 123 stores facial photo data including facial images used in facial authentication. Figure 11 is a diagram showing an example of the facial photo memory unit 123 according to an embodiment. In the example shown in Figure 11, the facial photo memory unit 123 has fields such as "User ID," "Registered facial photo data," "For authentication," and "For ID photo."

"User ID" indicates identification information that identifies a user. "Registered facial photo data" indicates facial photo data registered by the user. "For authentication" indicates facial photo data used for facial authentication. "For ID photo" indicates facial photo data that has been cropped or the background changed for ID photos. In other words, the management device 100 can store a user's facial photo data separately for authentication and ID photos.

The authentication log storage unit 124 stores a log of when a user performs facial authentication. For example, the authentication log storage unit 124 stores the date and time when the user attempted facial authentication, the results of the facial authentication, etc. The authentication log storage unit 124 may also store a log of when the user used the service. For example, the authentication log storage unit 124 may store the user's attendance record, etc.

The external service information storage unit 125 stores information about external services that can be used by a user after verifying their identity through facial authentication or other means. Figure 12 is a diagram showing an example of the external service information storage unit 125 according to an embodiment. In the example shown in Figure 12, the external service information storage unit 125 has fields such as "service ID," "type," and "determination criteria."

"Service ID" indicates identification information that identifies the service. "Type" indicates the type of service. "Determination criteria" indicates the criteria for determining whether a user can use a service based on the authentication strength related to facial recognition. For example, if the determination criteria is "OR determination," the user can use the service if the matching result is OK using any one of the multiple facial recognition engines. If the determination criteria is "AND determination," the user can use the service only if the matching result is OK using all of the multiple facial recognition engines. If the determination criteria is "OK determination using two or more engines," the user can use the service if the matching result is OK using two or more of the multiple facial recognition engines. Note that the determination criteria shown in Figure 12 are just an example, and external services may register various determination criteria in the management device 100 based on their desired authentication strength.

Returning to Figure 8, we will continue the explanation. The control unit 130 is realized by, for example, a CPU (Central Processing Unit), MPU (Micro Processing Unit), GPU (Graphics Processing Unit), etc., executing programs stored within the management device 100 using RAM (Random Access Memory) or the like as a working area. The control unit 130 is also a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

As shown in FIG. 8, the control unit 130 includes a registration processing unit 130A and an authentication processing unit 130B. The registration processing unit 130A controls processing related to the registration of facial images. The registration processing unit 130A includes a reception unit 131, a provision unit 132, a quality determination unit 133, and a registration unit 134. The authentication processing unit 130B controls processing related to authentication processing. The authentication processing unit 130B includes an acquisition unit 135, a transmission unit 136, and a result determination unit 137.

The reception unit 131 receives from the user a facial image that serves as the basis for the correct answer data used for matching by each of the multiple facial recognition engines in order to perform authentication processing using the multiple facial recognition engines. Note that the correct answer data used by the facial recognition engines for matching is not the facial image itself, but rather features extracted from the facial image.

For example, the reception unit 131 provides the user with a page (such as a website) for registering a facial image, and receives the facial image from the user via this page. This facial image is used as a registration image to be registered in the facial recognition engine. Note that if the facial image has been processed using processing means provided by the provision unit 132, which will be described later, the reception unit 131 receives the processed image, which is the image after processing, as the registration image.

The providing unit 132 provides a processing means for the user to process the facial image accepted by the accepting unit 131.

For example, the providing unit 132 provides processing means for changing at least one of the size of a facial image, the area occupied by the face in the facial image, the brightness of the facial image, and the background of the facial image. Specifically, as shown in Figures 3 and 4, the providing unit 132 provides editing tools on a page for registering a facial image that allow the user to perform operations such as trimming, adjusting brightness, and changing the background. Note that the types of processing are not limited to those described above, and the providing unit 132 may provide tools that can perform operations such as tooth whitening and complexion whitening on a facial image. For these operations, the user may operate the tools to adjust the teeth or complexion to a desired color, or the providing unit 132 may automatically adjust them to an appropriate color.

The providing unit 132 may also provide reference information for processing an image into one that is compatible with multiple face recognition engines or the service used by the user after authentication processing. The reference information is, for example, a guide 306, as shown in FIG. 3, that is displayed on the screen of the user terminal 20 to allow the user to process the image into one that is suitable for the user. The guide 306 is displayed based on, for example, the proportion and position of the face contained in the facial image. The reference information may also include horizontal lines to check the parallelism of the face and vertical lines to check the center of the image.

Note that the providing unit 132 does not need to provide all of the processing methods shown in Figures 3 and 4. For example, if it is clear that the user will not use the processed image as an ID photo, the providing unit 132 may skip the background change page, which is mainly used for creating ID photos, and proceed with the registration process.

Furthermore, if it is difficult for the user to select the brightness, size, etc. of the image themselves, the providing unit 132 may perform a process to automatically adjust the brightness and size. That is, the providing unit 132 may convert at least one of the size of the facial image, the area occupied by the face in the facial image, the brightness of the facial image, and the background of the facial image in accordance with the user's request, and automatically generate an edited image that can be used as correct answer data for the authentication process of multiple facial recognition engines. In this case, the providing unit 132 may, for example, refer to the quality check item storage unit 122 to obtain information such as the brightness required for the facial image, the image size, and the position where the face should be located in the image. The providing unit 132 then automatically edits the facial image to meet these requests and generates an edited image. In this case, the providing unit 132 may use known technology, such as a process to detect faces included in an image. This allows the providing unit 132 to generate an edited image that ensures the required quality without requiring the user's effort.

Furthermore, if the quality determination unit 133 (described below) determines that a predetermined quality check item related to the processed image does not meet the quality requirements, the providing unit 132 may convert the information in the processed image related to the quality check item so that the quality requirements are met. For example, if the quality determination unit 133 determines that the brightness of the processed image is insufficient, the providing unit 132 may automatically convert the processed image to be brighter so that the quality requirements are met, and generate a converted image. In this case, the providing unit 132 may present the converted image to the user once, or may automatically replace the original processed image with the converted image and proceed with the registration process.

The quality determination unit 133 determines whether the facial images accepted by the acceptance unit 131 or the registration images, such as processed images that are facial images processed by the processing means, are of a quality that allows them to be used as correct answer data for the authentication processes of multiple facial recognition engines.

Specifically, the quality determination unit 133 determines for each of the multiple face recognition engines whether the registration image is of a quality that allows it to be used as correct answer data for the recognition processes of the multiple face recognition engines.

More specifically, the quality determination unit 133 determines whether the registration image satisfies the criteria for the specified quality check items set for each of the multiple face recognition engines, and based on the determination results, determines whether the registration image is of a quality that allows it to be used as correct answer data for the recognition processes of the multiple face recognition engines.

The registration unit 134 registers the registration image if, based on the judgment result by the quality judgment unit 133, it is judged that the registration image is of a quality that can be used as correct answer data for the authentication process for all of the multiple face recognition engines.

If the quality determination unit 133 determines that any of the specified quality check items related to the registration image does not meet the quality standard, the registration unit 134 may notify the user which quality check item does not meet the standard. For example, the registration unit 134 notifies the user which quality check item does not meet the standard by displaying the screen 338 and determination result 340 shown in FIG. 4 on the user terminal 20.

If the registration unit 134 determines, based on the determination result by the quality determination unit 133, that the registration image is not of a quality that allows it to be used as correct answer data for the authentication process for any of the multiple face recognition engines, it notifies the user that the registration image cannot be registered as an authentication face image. In other words, if there are multiple face recognition engines specified for a service, etc., the registration unit 134 registers only face images that can be registered in all of the face recognition engines. This allows the registration unit 134 to ensure the safety of the face recognition process.

Furthermore, when registering a registration image, the registration unit 134 may store, in association with the registration image, a second facial image that differs from the registration image in at least one of the following: facial image size, area occupied by the face in the facial image, brightness of the facial image, and background of the facial image. Specifically, when registering a user, the registration unit 134 may store a facial image for an ID photograph together with a facial image for authentication. This allows the management device 100 to provide the facial image for an ID photograph to the service side as needed, such as for creating an ID card for the service.

The acquisition unit 135 acquires a facial image from the user to be used to execute authentication processing on multiple facial recognition engines. For example, the acquisition unit 135 acquires a facial image to be used to execute authentication processing via an authentication terminal 40 that has captured an image of the user.

The transmission unit 136 transmits the facial image acquired by the acquisition unit 135 to each of the multiple facial recognition engines.

Note that the transmission unit 136 does not necessarily need to transmit the facial image to all facial recognition engines, depending on the characteristics of the acquired facial image and the service request. Some facial recognition engines may have high accuracy in matching bright images (e.g., images taken during the day) or dark images (e.g., images taken at night), or may be engines that have been trained to have high accuracy in matching specific races. For this reason, if the acquired facial image is brighter or brighter than a predetermined reference value, or if the facial image depicts a specific race, the transmission unit 136 may preferentially transmit the facial image to a facial recognition engine that has high accuracy for such situations. The service that the user intends to use after authentication may specify a specific facial recognition engine (e.g., a facial recognition engine that is highly reliable for the service). In such cases, the transmission unit 136 may select the facial recognition engine to which the facial image is to be transmitted depending on the type of user request (i.e., the service the user intends to use).

In other words, the transmission unit 136 may select which face recognition engine to send the face image to based on information about the face image or a user request. For example, the transmission unit 136 may select which face recognition engine to send the face image to based on the brightness of the face image or user characteristic information (skin color, race, etc.) included in the face image.

The result determination unit 137 determines whether to grant the user's request based on the number of face recognition engines that successfully matched the face image with the correct answer data.

For example, the result determination unit 137 determines whether to permit a user's request based on whether the number of face recognition engines among multiple face recognition engines that successfully matched the face image with the correct data satisfies the criteria set by the service used by the user after the authentication process. Specifically, the result determination unit 137 references the external service information storage unit 125, and if a matching result is obtained that meets the criteria required by the service, it determines that the user's identity has been authenticated and permits use of the service. Note that if the service does not specify criteria, the result determination unit 137 may permit the user's request if matching is successful with any face recognition engine (OR determination), or may permit the user's request if matching is successful with all face recognition engines (AND determination).

In addition, if the facial image is sent only to a specific facial recognition engine by the transmission unit 136, the result determination unit 137 may determine whether to permit the user's request based on the authentication result of the facial recognition engine to which the facial image was sent.

(2. Modifications of the embodiment)
(2-1. Equipment configuration)
In the above embodiment, an example is shown in which the user terminal 20 is used to register a face image and the authentication terminal 40 is used to perform authentication processing in the management system 1. However, the configuration and roles of the devices in the management system 1 can be changed as appropriate.

For example, when a user attempts to use a service on a website displayed on the user terminal 20, the user terminal 20 may take on the role of the authentication terminal 40. That is, the user terminal 20 may send a photographed facial image of the user to the management device 100 and execute facial authentication processing for the user. For example, if the user terminal 20 receives a result from the management device 100 indicating that the facial authentication is successful, it may perform operations that occur after service usage is permitted, such as making the service that the user attempted to access displayable.

In addition, in the above embodiment, an example was shown in which each facial recognition provider is operated by a different business operator than the management device 100, and each facial recognition provider is operated by a different business operator. However, the management device 100 may execute the processing of the embodiment in an on-premise environment in which multiple facial recognition engines function on its own, rather than receiving facial recognition engines from a facial recognition provider. In this case, the management device 100 may be equipped with multiple facial recognition engines with different characteristics, for example, by generating the multiple facial recognition engines using different learning methods. This allows the management device 100 to execute management processing using multiple facial recognition engines without necessarily relying on multiple businesses. In addition, the management device 100 does not necessarily have to be a cloud server, but may function as a platform for managing multiple facial recognition engines in a system built on a local network.

(3. Other Embodiments)
The processing according to the above-described embodiment may be implemented in various different forms other than the above embodiment.

For example, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown.

Furthermore, the components of each device shown in the figure are functional concepts and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

Furthermore, the above-described embodiments and variations can be combined as appropriate to the extent that the processing content is not contradictory.

Furthermore, the effects described in this specification are merely examples and are not limiting, and other effects may also be present.

(4. Effects of the management device according to the present disclosure)
As described above, the management device (management device 100 in the embodiment) according to the present disclosure includes a reception unit (reception unit 131 in the embodiment), a provision unit (provision unit 132 in the embodiment), and a quality determination unit (quality determination unit 133 in the embodiment). The reception unit receives from a user a facial image that serves as the basis for supervised data used for matching by each of a plurality of facial recognition engines in order to execute authentication processing by the plurality of facial recognition engines. The provision unit provides processing means that allows the user to process the facial image received by the reception unit. The quality determination unit determines whether the processed image, which is a facial image processed by the processing means, is of a quality that can be used as supervised data for the authentication processing of the plurality of facial recognition engines.

In this way, the management device according to the present disclosure provides a means for processing facial images received from a user, and also judges the quality of the processed images to determine whether they can be used for authentication processing by a facial recognition engine. In this way, the management device 100 can perform processing such as trimming and quality assessment processing all at once on the server-side platform, making it possible to obtain high-quality facial images, which can lead to improved accuracy in feature extraction in the subsequent stage. Furthermore, by checking the quality of the processed images, the management device can prevent the need to retake images, thereby reducing the burden on the user and enabling accurate facial image registration.

The providing unit also provides reference information for processing the image into a processed image that is compatible with multiple face recognition engines or the service used by the user after authentication processing.

In this way, by providing users with reference information indicating the face size, etc. along with the processing method, the management device can standardize the size and quality of registration images received from users, allowing for smooth registration.

The providing unit also provides processing means for converting at least one of the size of the face image received by the receiving unit, the area occupied by the face in the face image, the brightness of the face image, and the background of the face image.

In this way, the management device provides a means for users to process images they have taken, thereby providing an environment in which users can edit images as they wish.

In addition, the providing unit converts at least one of the size of the face image accepted by the accepting unit, the area occupied by the face in the face image, the brightness of the face image, and the background of the face image in accordance with the user's request, and generates a processed image that can be used as correct answer data for the authentication processes of multiple face recognition engines.

In this way, the management device can automatically process facial images, making it possible to generate processed images that meet the required quality without requiring the user to take the time and effort.

In addition, if the quality determination unit determines that a predetermined quality check item related to the processed image does not meet the quality, the providing unit converts the information in the processed image related to the predetermined quality check item so that the quality meets the quality.

In this way, the management device can automatically convert images to maintain quality, allowing it to generate processed images that meet the required quality without requiring the user to go through the trouble.

The management device may also be configured to include an acquisition unit (acquisition unit 135 in this embodiment), a transmission unit (transmission unit 136 in this embodiment), and a result determination unit (result determination unit 137 in this embodiment). The acquisition unit acquires a facial image from the user to cause multiple facial recognition engines to execute authentication processing. The transmission unit transmits the facial image acquired by the acquisition unit to each of the multiple facial recognition engines. The result determination unit determines whether to permit the user's request based on the authentication results of each of the multiple facial recognition engines that authenticated the facial image.

In this way, the management device performs authentication processing using multiple face recognition engines. This allows the management device to improve authentication accuracy and enhance security, as well as provide flexible authentication methods, such as setting different criteria for each service.

The result determination unit also determines whether to grant the user's request based on the number of face recognition engines among the multiple face recognition engines that successfully matched the face image with the correct answer data.

In this way, the management device performs authentication using multiple facial recognition engines, making it possible to perform authentication that takes advantage of the strengths of various facial recognition engines, such as a facial recognition engine that is strong in certain environments or a facial recognition engine that is strong for certain races.

The result determination unit also determines whether to grant the user's request based on whether the number of face recognition engines among the multiple face recognition engines that successfully matched the face image with the correct answer data satisfies the determination criteria set by the service used by the user after the authentication process.

In this way, the management device can determine whether to grant a user's request based on the service's criteria, allowing it to perform flexible authentication processing according to the authentication strength and needs of the service, rather than simply granting the user's identity based on a successful match by one facial recognition engine.

The transmission unit also selects which face recognition engine to send the face image to based on information about the face image or the user's request. The result determination unit determines whether to grant the user's request based on the authentication result of the face recognition engine to which the face image was sent.

In this way, the management device can take advantage of the advantage of using multiple facial recognition engines and selectively use facial recognition engines based on the image characteristics that each engine excels at. This allows the management device to perform authentication with greater consideration for safety, by using only highly accurate facial recognition engines.

The transmission unit also selects which face recognition engine to send the facial image to based on the brightness of the facial image or the user's feature information contained in the facial image.

In this way, the management device can select a facial recognition engine based on the characteristics of the image, allowing it to selectively transmit facial images that each facial recognition engine is good at.

The management device may also be configured to include a reception unit, a quality determination unit, and a registration unit (registration unit 134 in this embodiment). The reception unit receives from the user a registration image that serves as the source of correct answer data used for matching by each of the multiple face recognition engines in order to execute authentication processing using the multiple face recognition engines. The quality determination unit determines for each of the multiple face recognition engines whether the registration image is of a quality that allows it to be used as correct answer data for the authentication processing of the multiple face recognition engines. The registration unit registers the registration image when it determines, based on the determination result by the quality determination unit, that the registration image is of a quality that allows it to be used as correct answer data for the authentication processing for all of the multiple face recognition engines.

In this way, the management device registers only facial images that meet the quality requirements of all facial recognition engines used. This allows the management device to smoothly carry out authentication processes that use multiple facial recognition engines.

The quality assessment unit also determines whether the registration image satisfies the criteria for the specified quality check items set for each of the multiple face recognition engines, and based on the assessment results, determines whether the registration image is of a quality that allows it to be used as correct answer data for the recognition processes of the multiple face recognition engines.

In this way, the management device sets items to be checked in the quality assessment and performs quality assessment in accordance with the items. This allows the management device to reliably register face images of a quality that can be used by the face recognition engine.

In addition, if the quality determination unit determines that any of the specified quality check items related to the registration image do not meet the quality standards, the registration unit notifies the user which quality check items do not meet the standards.

In this way, the management device notifies the user that the quality does not meet the requirements for each item, allowing the user to easily understand how to correct the registration image.

Furthermore, if the registration unit determines, based on the judgment result by the quality judgment unit, that the registration image is not of a quality that allows it to be used as correct answer data for the authentication process for any of the multiple face recognition engines, it notifies the user that the registration image cannot be registered as an authentication face image.

In this way, the management device can notify the user that registration was not possible with one of the facial recognition engines, encouraging the user to properly register with all facial recognition engines.

In addition, when registering a registration image, the registration unit stores a second facial image (e.g., an image for a passport photo) that differs from the registration image in at least one of the following: size of the facial image, area occupied by the face in the facial image, brightness of the facial image, and background of the facial image, in association with the registration image.

In this way, the management device may store images for ID photos separately from images for authentication. This allows the management device to respond flexibly as a platform, such as by providing facial images for ID photos to the service side as needed, such as when creating ID cards for the service.

(5. Hardware Configuration)
Information devices such as the management device 100 and user terminal 20 according to the above-described embodiments are realized by a computer 1000 having a configuration such as that shown in FIG. 13 . The following description will be given using the management device 100 according to the embodiment as an example. FIG. 13 is a hardware configuration diagram showing an example of a computer 1000 that realizes the functions of the management device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, a HDD (Hard Disk Drive) 1400, a communication interface 1500, and an input/output interface 1600. The components of the computer 1000 are connected by a bus 1050.

The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400 and controls each component. For example, the CPU 1100 loads programs stored in the ROM 1300 or HDD 1400 into the RAM 1200 and executes processing corresponding to the various programs.

ROM 1300 stores boot programs such as the BIOS (Basic Input Output System) executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

HDD 1400 is a computer-readable recording medium that non-temporarily records programs executed by CPU 1100 and data used by such programs. Specifically, HDD 1400 is a recording medium that records a program that executes the management processing related to the present disclosure, which is an example of program data 1450.

The communication interface 1500 is an interface that allows the computer 1000 to connect to an external network 1550 (e.g., the Internet). For example, the CPU 1100 receives data from other devices and transmits data generated by the CPU 1100 to other devices via the communication interface 1500.

The input/output interface 1600 is an interface for connecting the input/output device 1650 and the computer 1000. For example, the CPU 1100 receives data from input devices such as a keyboard or mouse via the input/output interface 1600. The CPU 1100 also transmits data to output devices such as a display, speaker, or printer via the input/output interface 1600. The input/output interface 1600 may also function as a media interface that reads programs and the like recorded on a specified recording medium. Examples of media include optical recording media such as DVDs (Digital Versatile Discs) and PDs (Phase Change Rewritable Disks), magneto-optical recording media such as MOs (Magneto-Optical Disks), tape media, magnetic recording media, and semiconductor memories.

For example, when the computer 1000 functions as the management device 100 according to an embodiment, the CPU 1100 of the computer 1000 executes a management processing program loaded onto the RAM 1200, thereby realizing the functions of the control unit 130 and the like. The HDD 1400 also stores programs for executing the management processing according to the present disclosure and data in the storage unit 120. The CPU 1100 reads and executes program data 1450 from the HDD 1400, but as another example, the CPU 1100 may also obtain these programs from another device via the external network 1550.

The above describes in detail the embodiments of the present application based on the drawings, but these are merely examples, and the present invention can be implemented in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the Disclosure of the Invention section.

1 Management system 10 User 20 User terminal 40 Authentication terminal 50 Face authentication provider 60 First face authentication engine 70 Second face authentication engine 80 Third face authentication engine 100 Management device 110 Communication unit 120 Storage unit 121 User information storage unit 122 Quality check item storage unit 123 Facial photo storage unit 124 Authentication log storage unit 125 External service information storage unit 130 Control unit 131 Reception unit 132 Provision unit 133 Quality judgment unit 134 Registration unit 135 Acquisition unit 136 Transmission unit 137 Result judgment unit 200 Service provider

Claims (7)

a reception unit that receives, from a user, a registration image that is a source of correct answer data that each of the plurality of face recognition engines uses for matching in order to execute an authentication process using the plurality of face recognition engines;
a quality determination unit that determines, for each of the plurality of face recognition engines, whether the registration image is of a quality that allows it to be used as correct answer data for the recognition process of the plurality of face recognition engines;
a registration unit that registers the registration image when it is determined based on the determination result by the quality determination unit that the registration image has a quality that can be used as correct answer data for authentication processing for all of the plurality of face recognition engines; and
A management device comprising: The quality determination unit
determining whether the registration image satisfies standards for predetermined quality check items set for each of the plurality of face recognition engines, and determining, based on the determination result, whether the registration image is of a quality that can be used as correct answer data for the recognition processing of the plurality of face recognition engines;
The management device according to claim 1 . The registration unit
If the quality determination unit determines that any of the predetermined quality check items related to the registration image does not satisfy the quality standard, the user is notified of which quality check item does not satisfy the standard.
3. The management device according to claim 2. The registration unit
If it is determined based on the determination result by the quality determination unit that the registration image is not of a quality that can be used as correct answer data for authentication processing for any of the plurality of face recognition engines, notify the user that the registration image cannot be registered as an authentication face image.
4. The management device according to claim 1, wherein the management device is a device for managing a plurality of data. The registration unit
When registering the registration image, a second face image that is different from the registration image in at least one of the size of the face image, the area occupied by the face in the face image, the brightness of the face image, and the background of the face image is stored in association with the registration image.
5. The management device according to claim 1, wherein the management device is a device for managing a plurality of data. The computer
In order to execute authentication processing by a plurality of face recognition engines, a registration image is received from a user, which serves as a source of correct answer data used for matching by each of the plurality of face recognition engines;
determining, for each of the plurality of face recognition engines, whether the registration image is of a quality that allows it to be used as correct answer data for the recognition process of the plurality of face recognition engines;
If it is determined based on the result of the determination that the registration image is of a quality that can be used as correct answer data for authentication processing for all of the plurality of face recognition engines, the registration image is registered.
A management method comprising: Computer,
a reception unit that receives, from a user, a registration image that is a source of correct answer data that each of the plurality of face recognition engines uses for matching in order to execute an authentication process using the plurality of face recognition engines;
a quality determination unit that determines, for each of the plurality of face recognition engines, whether the registration image is of a quality that allows it to be used as correct answer data for the recognition process of the plurality of face recognition engines;
a registration unit that registers the registration image when it is determined based on the determination result by the quality determination unit that the registration image has a quality that can be used as correct answer data for authentication processing for all of the plurality of face recognition engines; and
A management program that causes the device to function as a management device comprising: