JP7719474B2 - Authentication System - Google Patents

Description

Application of Article 30, Paragraph 2 of the Patent Act Published in the conference room of Property Agent Co., Ltd. on March 12, 2019 Published in the conference room of Toreta Co., Ltd. on August 5, 2019 Published in the conference room of OYO TECHNOLOGY & HOSPITALITY JAPAN Co., Ltd. on August 9, 2019 Published in the conference room of Property Agent Co., Ltd. on August 29, 2019 Published in the conference room of Japan Taxi Co., Ltd. on August 29, 2019 Published in the conference room of Property Agent Co., Ltd. on September 3, 2019 Published in the conference room of Yahoo Japan Corporation on September 9, 2019 Published in the conference room of LINE Corporation on September 13, 2019 Published in the conference room of Property Agent Co., Ltd. on September 19, 2019 Published in the conference room of Toyoko Inn IT Customer Attraction Solutions Co., Ltd. on October 2, 2019 Published in the conference room of Exware Co., Ltd. on October 3, 2019 Published in the conference room of Property Agent Co., Ltd. on October 3, 2019 Published in the conference room of APA Group Corporation on October 3, 2019 Published in the conference room of Property Agent Co., Ltd. on October 23, 2019 Published in the conference room of Mitsui Fudosan Co., Ltd. on October 29, 2019 Published in the conference room of Mitsui & Co., Ltd. on October 31, 2019 Published in the conference room of Property Agent Co., Ltd. on October 31, 2019 Published in the conference room of Daiwa House Industry Co., Ltd. on November 1, 2019 Published in the conference room of Property Agent Co., Ltd. on November 6, 2019 Published in the conference room of Persol Innovation Co., Ltd. on November 28, 2019 Published in the conference room of Minnano Taxi Co., Ltd. on December 2, 2019 Published in the conference room of Tokyu Corporation on December 18, 2019 Published in the conference room of JCB Co., Ltd. on December 23, 2019 Released on December 25, 2019 in the conference room of Change Co., Ltd.

The present invention relates to an authentication system.

Conventionally, a facial authentication system that performs authentication based on facial data is known, which performs identity authentication by comparing input facial data with pre-registered facial data (see, for example, Patent Documents 1 and 2).

The facial recognition system described in Patent Document 1 authenticates a target person using an image of the face portion in an image captured by a camera. In addition, the facial recognition system described in Patent Document 2, for example, when four facial images are registered, two are designated as facial patterns for ensuring accuracy, one is designated as a facial pattern for absorbing disturbance components, and one is designated as a facial pattern to be updated. When a new facial pattern is registered, the facial pattern to be updated that has the second-lowest similarity to the newly registered facial pattern is deleted from the four pre-registered facial patterns. In other words, by leaving the facial pattern for absorbing disturbance components that has the lowest similarity to the newly registered facial pattern, facial recognition adapts to environmental variations.

Japanese Patent Application Laid-Open No. 2019-197426 Japanese Patent Application Laid-Open No. 2006-72540

While the installation of authentication engines that use facial recognition is becoming commonplace, the facial recognition systems of Patent Documents 1 and 2 cannot perform facial recognition with an authentication engine that does not have facial data registered. As a result, in order to perform authentication using multiple authentication engines, the user must register facial data for each of the multiple authentication engines, which is time-consuming and stressful.

The present invention was made with these points in mind, and aims to provide an authentication system that can easily perform face authentication using multiple face recognition engines.

The authentication system of the present invention comprises a first imaging means for acquiring facial image data of a user to be used as a comparison standard; multiple facial recognition devices for comparing the user's face with the comparison standard and determining whether or not to provide the service requested by the user; and a distribution server for accepting the facial image data acquired by the first imaging means and transmitting and receiving data to and from each of the facial recognition devices. The feature amount used as the comparison standard in each of the facial recognition devices is generated based on the facial image data acquired by the first imaging means, and the feature amount data used as the comparison standard is registered in a storage device provided in each of the facial recognition devices.

The authentication system of the present invention makes it easy to perform facial recognition using multiple facial recognition engines.

FIG. 1 is a diagram illustrating an example of a face authentication system according to an embodiment of the present invention and an authentication engine disposed at each service facility. 4 is a flowchart showing the processing executed when a face image of a user is registered by the face authentication system shown in FIG. 1 . 10 is a flowchart showing an example of processing content executed when authenticating a user by the authentication engine and face authentication system shown in FIG. 1 . FIG. 10 is a diagram illustrating another example of a face authentication system and an authentication engine disposed at each service center according to an embodiment of the present invention. 5 is a flowchart showing the processing content executed when registering a face image of a user by the face authentication system shown in FIG. 4 . 5 is a flowchart showing an example of processing content executed when authenticating a user by the authentication engine and face authentication system shown in FIG. 4 . FIG. 10 is a diagram illustrating yet another example of a face authentication system and an authentication engine disposed at each service center according to an embodiment of the present invention. 8 is a flowchart showing the processing content executed when registering a face image of a user by the face authentication system shown in FIG. 7 . 8 is a flowchart showing an example of processing content executed when authenticating a user by the authentication engine and face authentication system shown in FIG. 7 . FIG. 10 is a diagram showing an initial screen displayed on a user terminal. FIG. 10 is a diagram showing a registration screen displayed on a user terminal. FIG. 10 is a diagram showing a registration screen displayed on a user terminal. FIG. 10 is a diagram showing a service addition screen displayed on a user terminal. FIG. 10 is a diagram showing an authentication history screen displayed on a user terminal. FIG. 10 is a diagram showing a detailed screen of an authentication history displayed on a user terminal. FIG. 10 is a diagram illustrating another example of a face authentication system according to an embodiment of the present invention and an authentication engine disposed in each company.

Embodiments of the present invention will now be described with reference to the drawings. Figures 1 to 15 show a face authentication system according to this embodiment and authentication engines located at each service provider.

As shown in FIG. 1, authentication engines 30A, 30B, and 30C that authenticate users are located at each service facility, such as a restaurant, hotel, transportation facility, office building, apartment complex, or convenience store. While FIG. 1 illustrates three authentication engines 30A, 30B, and 30C, two or more authentication engines may be used. A facial authentication system 10 installed in a company separate from each service facility is communicatively connected to each authentication engine 30A, 30B, and 30C via a network such as the Internet. A user terminal 20, such as a smartphone owned by a user, is communicatively connected to the facial authentication system 10 and each authentication engine 30A, 30B, and 30C via a network such as the Internet. Details of the facial authentication system 10 and each authentication engine 30A, 30B, and 30C are described below.

The facial authentication system 10 is composed of, for example, a computer, and includes a processor 12 such as a CPU, memory 16, and a communication unit 18. The processor 12 includes a feature extraction means 14 that extracts features of the user's facial image corresponding to each authentication engine 30A, 30B, and 30C as hash values based on facial image data received from the user terminal 20, and a registration means 13 that registers the extracted features of the user's facial image. The processor 12 executes a program stored in the memory 16, causing the feature extraction means 14 to extract features of the user's facial image corresponding to each authentication engine 30A, 30B, and 30C as hash values. Specifically, the feature extraction means 14 extracts hash values calculated from the received user's facial image data using a predetermined hash function as the features of the user's facial image. Note that even if the user's facial image data is the same, the features of the user's facial image may differ depending on the type of authentication engine 30A, 30B, and 30C. This is because different service providers, such as business companies, use different specifications for the authentication engines 30A, 30B, and 30C. Therefore, the feature extraction means 14 extracts features of the user's facial image for each of the authentication engines 30A, 30B, and 30C. That is, from one facial image data set, feature values of multiple users corresponding to each of the authentication engines 30A, 30B, and 30C are extracted. Furthermore, by executing a program stored in the memory 16, the processor 12 causes the registration means 13 to associate the feature values (specifically, hash values) of the user's facial image for each of the authentication engines 30A, 30B, and 30C extracted by the feature extraction means 14 with the user's identification information and the identification information of the authentication engines 30A, 30B, and 30C and store them in the memory 16. The programs executed by the processor 12 are not limited to those stored in the memory 16. Processing may be performed in each of the feature extraction means 14 and the registration means 13 by the processor 12 executing a program transmitted to the face authentication system 10 from an external device or a program stored on a recording medium that is detachably attached to the face authentication system 10.

As described above, the memory 16 stores the features (specifically, hash values) of the user's facial image extracted by the feature extraction means 14 in association with the user's identification information and the identification information of the authentication engines 30A, 30B, and 30C. As described above, the features of the user's facial image extracted by the feature extraction means 14 may differ depending on the type of authentication engine 30A, 30B, and 30C. For this reason, the feature extraction means 14 extracts the features of the user's facial image for each authentication engine 30A, 30B, and 30C. As a result, the features of the user's facial image extracted by the feature extraction means 14 must also be stored in the memory 16 in association with each authentication engine 30A, 30B, and 30C. The memory 16 also stores the user's identification information in association with the service provider selected by the user. As described above, the memory 16 also stores programs for causing the processor 12 to perform various processes. The processor 12 also transmits and receives signals via a communication unit 18 to authentication engines 30A, 30B, 30C located at each service facility or a user terminal 20 via a network such as the Internet.

Each of the authentication engines 30A, 30B, 30C located at each service facility is composed of, for example, a computer, and each authentication engine 30A, 30B, 30C has a processor 32A, 32B, 32C such as a CPU, memory 36A, 36B, 36C, an imaging unit 38A, 38B, 38C, a processing unit 40A, 40B, 40C, and a communication unit 42A, 42B, 42C. The processors 32A, 32B, 32C have feature extraction means 34A, 34B, 34C that extract features of the user's facial image as hash values based on the user's facial image data captured by the imaging unit 38A, 38B, 38C, and authentication means 35A, 35B, 35C. The processors 32A, 32B, and 32C execute programs stored in memories 36A, 36B, and 36C to cause feature extraction means 34A, 34B, and 34C to extract features of the user's facial image as hash values. Specifically, the feature extraction means 34A, 34B, and 34C extract hash values calculated from the received user's facial image data using a predetermined hash function as feature quantities of the user's facial image. The processors 32A, 32B, and 32C also execute programs stored in memories 36A, 36B, and 36C to perform user authentication in authentication means 35A, 35B, and 35C. Details of this processing will be described later. Note that the programs executed by the processors 32A, 32B, and 32C are not limited to those stored in memories 36A, 36B, and 36C. Various processes may be performed in the feature extraction means 34A, 34B, 34C and the authentication means 35A, 35B, 35C by processors 32A, 32B, 32C executing programs transmitted to authentication engines 30A, 30B, 30C from an external device or programs stored on recording media removably attached to authentication engines 30A, 30B, 30C. Furthermore, each of authentication engines 30A, 30B, 30C is not limited to corresponding to a single service provider. For example, authentication engine 30A may correspond to multiple service providers.

Memories 36A, 36B, and 36C are also configured to store pre-registered user identification information in association with the features of the user's facial image. As described above, memories 36A, 36B, and 36C are also configured to store programs that cause processors 32A, 32B, and 32C to perform various processes. Image capture units 38A, 38B, and 38C each have a camera, for example, and are configured to capture an image of the user to obtain facial image data of the user.

Furthermore, processing units 40A, 40B, and 40C are configured to perform various processes for authenticated users. For example, if authentication engines 30A, 30B, and 30C are installed in an office building or apartment complex, processing units 40A, 40B, and 40C will unlock doors at entrances and exits of the office building or apartment complex when a user is authenticated. Furthermore, if authentication engines 30A, 30B, and 30C are installed in restaurants, hotels, transportation facilities, convenience stores, and other facilities, they enable cashless payment when paying fees at these service facilities. In this case, authentication engines 30A, 30B, and 30C send payment information to the server of a financial institution or credit card company, and the payment amount is automatically debited from the user's bank account or added to the credit card statement. Furthermore, processors 32A, 32B, and 32C are configured to send and receive signals with face authentication system 10 or user terminal 20 via a network such as the Internet via communication units 42A, 42B, and 42C.

Furthermore, in each authentication engine 30A, 30B, 30C, the user's facial image is captured by the imaging unit 38A, 38B, 38C, allowing the feature quantities of this user's facial image to be registered in each authentication engine 30A, 30B, 30C. Specifically, when the user's facial image is captured by the imaging unit 38A, 38B, 38C when the feature quantities of the user's facial image are registered in each authentication engine 30A, 30B, 30C, the processor 32A, 32B, 32C extracts the feature quantities of the user's facial image as hash values using feature extraction means 34A, 34B, 34C based on the user's facial image data captured by the imaging unit 38A, 38B, 38C. The extracted feature quantities of the user's facial image (specifically, hash values) are then stored in memory 36A, 36B, 36C. In this manner, the feature quantities of the user's facial image are registered in each authentication engine 30A, 30B, 30C.

A facial recognition app can be installed on the user terminal 20 from an online store or the like. Once such a facial recognition app is installed, the user can use the user terminal 20 to register facial image data, register the service provider from which the service will be used, and so on. The processing details of such a facial recognition app will be described later. Note that such a facial recognition app may be provided by the facial recognition system 10, or may be provided by a system separate from the facial recognition system 10.

In this embodiment, the facial authentication system 10 and the authentication engines 30A, 30B, and 30C located at each service facility are linked via an API (application programming interface). This makes it easier to configure each of the authentication engines 30A, 30B, and 30C systems than if each were configured independently.

Next, the processing performed when authenticating a user using the face authentication system 10 and each authentication engine 30A, 30B, and 30C will be explained using Figures 2, 3, and 10 to 12.

First, we will explain the process by which a user registers facial image data in the facial authentication system 10 using the user terminal 20. First, the user installs a facial authentication app on the user terminal 20. The initial screen of such a facial authentication app is the screen shown in Figure 10. The user first registers using such a facial authentication app on the user terminal 20. Specifically, when the user presses the account button on the screen shown in Figure 10, the user registration screen shown in Figure 11 appears. When the user enters registration information such as name, date of birth, phone number, email address, and password on such a user registration screen, checks the box indicating agreement to the terms of use, and then presses the registration button, the facial image capture screen shown in Figure 12 appears. When the user captures a facial image using the user terminal 20 on such a capture screen, the various information entered on the user registration screen and the user's facial image data are transmitted from the user terminal 20 to the facial authentication system 10. In this way, the processor 12 of the facial authentication system 10 receives the facial image data from the user terminal 20 (STEP 1). The processor 12 of the face authentication system 10 also receives from the user terminal 20 the identification information of the user terminal 20, as well as registration information such as the user's name, date of birth, telephone number, email address, and password entered into the user terminal 20. The processor 12 also issues a user ID as the user's identification information, and stores this issued user ID in the memory 16.

Next, the processor 12 of the facial authentication system 10 extracts facial image features corresponding to each authentication engine 30A, 30B, and 30C as hash values using the feature extraction means 14 based on the facial image data received from the user terminal 20 (STEP 2). At this time, the feature extraction means 14 may extract different facial image features for each authentication engine 30A, 30B, and 30C. Therefore, the feature extraction means 14 extracts the user's facial image features for each authentication engine 30A, 30B, and 30C. The feature extraction means 14 also extracts only the user's facial image features corresponding to the authentication engines 30A, 30B, and 30C of the service facility pre-selected by the user. For example, if a user is permitted to use facial image data for the service facility where authentication engine 30A is installed, but is not permitted to use facial image data for the service facility where authentication engine 30B is installed, the feature extraction means 14 extracts only the user's facial image features corresponding to authentication engine 30A. As described above, the memory 16 stores the user's identification information and the service provider selected by the user in association with each other. The processor 12 then causes the registration means 13 to store the facial image features extracted by the feature extraction means 14 corresponding to each authentication engine 30A, 30B, and 30C in the memory 16 of the face authentication system 10 in association with the user ID (user identification information) and the identification information of the authentication engines 30A, 30B, and 30C (STEP 3). In this manner, registration of the user's facial image captured by the user terminal 20 is completed. Furthermore, information related to the user's facial image features stored in the memory 16 is transmitted from the face authentication system 10 to the authentication engines 30A, 30B, and 30C of the service provider selected by the user (STEP 4). At this time, the user's facial image features corresponding to these authentication engines 30A, 30B, and 30C are transmitted to the authentication engines 30A, 30B, and 30C. The authentication engines 30A, 30B, and 30C store information related to the features of the user's facial image transmitted from the facial authentication system 10 in memory 36A, 36B, and 36C in association with the user's identification information.

Next, the process of authenticating a user in each authentication engine 30A, 30B, 30C will be described. When user authentication becomes necessary at the service facility where each authentication engine 30A, 30B, 30C is installed, the user's facial image data is first acquired by capturing an image of the user using the imaging units 38A, 38B, 38C of the authentication engines 30A, 30B, 30C (STEP 11). Furthermore, in the authentication engines 30A, 30B, 30C, the processors 32A, 32B, 32C extract the features of the user's facial image as hash values using the feature extraction means 34A, 34B, 34C based on the acquired facial image data (STEP 12). Then, processors 32A, 32B, and 32C authenticate the user by comparing the features (specifically, hash values) of the user's facial image extracted by feature extraction means 34A, 34B, and 34C with the features (specifically, hash values) of the user's facial image stored in memories 36A, 36B, and 36C (STEP 13). More specifically, if the match rate between the features of the user's facial image extracted by feature extraction means 34A, 34B, and 34C and the features of the user's facial image stored in memories 36A, 36B, and 36C exceeds a predetermined threshold (e.g., 80%), authentication means 35A, 35B, and 35C authenticate the user. As mentioned above, memories 36A, 36B, and 36C store pre-registered user identification information and the features of the user's facial image in association with each other.

When the authentication means 35A, 35B, and 35C authenticate the user ("YES" in STEP 14), the processors 32A, 32B, and 32C enable the respective processing units 40A, 40B, and 40C to implement the services corresponding to the authentication engines 30A, 30B, and 30C (STEP 15). Specifically, as described above, if the authentication engines 30A, 30B, and 30C are located in an office building or an apartment complex, the processing units 40A, 40B, and 40C unlock doors at entrances and exits of the office building or apartment complex when the user is authenticated. Furthermore, if the authentication engines 30A, 30B, and 30C are located in restaurants, hotels, transportation facilities, convenience stores, and other facilities, they enable cashless payment when paying fees at these service facilities. Note that two-step authentication may be performed when cashless payment is performed. Thereafter, processors 32A, 32B, and 32C of authentication engines 30A, 30B, and 30C transmit information related to the service usage status to face authentication system 10 (STEP 17). As a result, information related to the service usage status at each service provider is stored in memory 16 for each user in face authentication system 10.

On the other hand, if the features of the user's facial image extracted by feature extraction means 34A, 34B, 34C do not substantially match the features of the user's facial image stored in memory 36A, 36B, 36C and the user cannot be authenticated by authentication means 35A, 35B, 35C ("NO" in STEP 14), processors 32A, 32B, 32C disable the service corresponding to authentication engine 30A, 30B, 30C using each processing unit 40A, 40B, 40C (STEP 16). In this case, processors 32A, 32B, 32C of authentication engines 30A, 30B, 30C also transmit information related to the service usage status (specifically, information that the user attempted to be authenticated by authentication engine 30A, 30B, 30C but was not authenticated and was therefore unable to use the service) to face authentication system 10 (STEP 17).

With this authentication method, even if the features of a user's facial image are registered in one service provider's authentication engine (e.g., authentication engine 30A) but not in another service provider's authentication engine (e.g., authentication engine 30B), the features of the user's facial image can be stored in memory 16 of facial authentication system 10 and in memories 36A, 36B, and 36C of each authentication engine 30A, 30B, and 30C in association with the identification information of authentication engines 30A, 30B, and 30C. This allows a service provider that does not have the user's facial image features registered to capture the user's facial image with an imaging unit and authenticate the user. In this case, the user does not need to register facial image data in all of the multiple authentication engines, thereby reducing the user's effort.

The facial authentication system 10 and facial authentication method according to this embodiment are not limited to those shown in Figures 1 to 3. Other examples of the facial authentication system 10 and facial authentication method according to this embodiment will be described using Figures 4 to 6. Note that in the facial authentication system 10 and each authentication engine 30A, 30B, and 30C shown in Figure 4, the same components as those in the facial authentication system 10 and each authentication engine 30A, 30B, and 30C shown in Figure 1 will be assigned the same reference numerals and their description will be omitted.

As shown in FIG. 4, the processor 12 of the facial authentication system 10 includes a feature extraction means 14 that extracts features of the user's facial image corresponding to each authentication engine 30A, 30B, and 30C as hash values based on facial image data received from the user terminal 20, a registration means 13 that registers the extracted features of the user's facial image, and an authentication means 15 that authenticates the user based on the features (specifically, hash values) of the user's facial image captured by the imaging units 38A to 38C of each authentication engine 30A, 30B, and 30C. By executing a program stored in memory 16, the processor 12 stores in memory 16 the features (specifically, hash values) of the user's facial image extracted by the feature extraction means 14 in the registration means 13 in association with the user's identification information and the identification information of the authentication engines 30A, 30B, and 30C. The processor 12 also executes a program stored in memory 16, which causes the authentication means 15 to compare the features (specifically, hash values) of the user's facial image captured by the imaging units 38A-38C of each authentication engine 30A, 30B, and 30C with the features (specifically, hash values) of the user's facial image corresponding to each authentication engine 30A, 30B, and 30C stored in memory 16, thereby authenticating the user. Note that the programs executed by the processor 12 are not limited to those stored in memory 16. Processors 12 may execute a program transmitted to the facial authentication system 10 from an external device or a program stored on a recording medium removably attached to the facial authentication system 10, thereby performing processing in the feature extraction means 14, registration means 13, and authentication means 15.

Each of the authentication engines 30A, 30B, 30C located at each service facility is composed of, for example, a computer, and each authentication engine 30A, 30B, 30C has a processor 32A, 32B, 32C such as a CPU, memory 36A, 36B, 36C, imaging unit 38A, 38B, 38C, processing unit 40A, 40B, 40C, and communication unit 42A, 42B, 42C. The processors 32A, 32B, 32C have feature extraction means 34A, 34B, 34C that extract features of the user's facial image as a hash value based on the user's facial image data captured by the imaging unit 38A, 38B, 38C. Note that in the example shown in Figure 4, the processors 32A, 32B, 32C do not have authentication means 35A, 35B, 35C as shown in Figure 1. The processors 32A, 32B, and 32C execute programs stored in the memories 36A, 36B, and 36C to cause the feature extraction means 34A, 34B, and 34C to extract features of the user's facial image as hash values. Specifically, the feature extraction means 34A, 34B, and 34C extract hash values calculated from the received user's facial image data using a predetermined hash function as the feature of the user's facial image. Note that the programs executed by the processors 32A, 32B, and 32C are not limited to those stored in the memories 36A, 36B, and 36C. Various processes may be performed in the feature extraction means 34A, 34B, and 34C by the processors 32A, 32B, and 32C executing programs transmitted to the authentication engines 30A, 30B, and 30C from an external device or programs stored on a recording medium detachably attached to the authentication engines 30A, 30B, and 30C. Additionally, in the example shown in Figure 4, memories 36A, 36B, and 36C are not configured to store the features of the user's facial image.

In the example shown in Figure 4, the facial authentication system 10 and the authentication engines 30A, 30B, and 30C located at each service facility are linked via an API (application programming interface). This makes it easier to configure each of the authentication engines 30A, 30B, and 30C systems than if each were configured independently.

Next, the processing steps performed when authenticating a user using the face authentication system 10 and each authentication engine 30A, 30B, and 30C shown in Figure 4 will be explained using Figures 5 and 6.

First, we will explain the process by which a user registers facial image data in the facial authentication system 10 using the user terminal 20. The specific method by which a user captures a facial image using the user terminal 20 has already been explained, so it will not be explained here. When a user initially registers using such a facial authentication app on the user terminal 20, various information entered on the user registration screen and the user's facial image data are transmitted from the user terminal 20 to the facial authentication system 10. In this way, the processor 12 of the facial authentication system 10 receives the facial image data from the user terminal 20 (STEP 21). The processor 12 of the facial authentication system 10 also receives from the user terminal 20 the identification information of the user terminal 20 and the registration information entered into the user terminal 20, such as the user's name, date of birth, telephone number, email address, and password. The processor 12 also issues a user ID as the user's identification information and stores this issued user ID in memory 16.

Next, the processor 12 of the facial authentication system 10 extracts facial image features corresponding to each authentication engine 30A, 30B, and 30C as hash values using the feature extraction means 14 based on the facial image data received from the user terminal 20 (STEP 22). At this time, the feature extraction means 14 extracts the user's facial image features for each authentication engine 30A, 30B, and 30C, and the feature extraction means 14 extracts the user's facial image features for each authentication engine 30A, 30B, and 30C. Furthermore, the feature extraction means 14 extracts only the user's facial image features corresponding to the authentication engines 30A, 30B, and 30C of the service provider pre-selected by the user. Then, the processor 12 causes the registration means 13 to store the facial image features corresponding to each authentication engine 30A, 30B, and 30C extracted by the feature extraction means 14 in the memory 16 of the facial authentication system 10 in association with the user ID (user identification information) and the identification information of the authentication engines 30A, 30B, and 30C (STEP 23). In this way, registration of the user's facial image captured by the user terminal 20 is completed. Note that in the example shown in FIG. 4, information related to the features of the user's facial image stored in memory 16 is not transmitted from the facial authentication system 10 to the authentication engines 30A, 30B, and 30C of the service provider selected by the user.

Next, the process of authenticating a user in each authentication engine 30A, 30B, 30C will be described. When user authentication becomes necessary at the service facility where each authentication engine 30A, 30B, 30C is installed, first, the user's facial image data is acquired by capturing an image of the user using the imaging units 38A, 38B, 38C of the authentication engines 30A, 30B, 30C (STEP 31). Furthermore, in the authentication engines 30A, 30B, 30C, the processors 32A, 32B, 32C extract the features of the user's facial image as hash values using the feature extraction means 34A, 34B, 34C based on the acquired facial image data (STEP 32). Then, the processors 32A, 32B, and 32C transmit the features (specifically, hash values) of the user's facial image extracted by the feature extraction means 34A, 34B, and 34C to the processor 12 of the face authentication system 10 via the communication units 42A, 42B, and 42C (STEP 33). When the processor 12 of the face authentication system 10 receives information related to the features of the user's facial image from the authentication engines 30A, 30B, and 30C, it also receives information related to the features of the user's facial image transmitted only from the authentication engines 30A, 30B, and 30C of the service provider selected by the user, which is stored in the memory 16. In the face authentication system 10, the processor 12 authenticates the user by comparing the features (specifically, hash values) of the user's facial image received from the authentication engines 30A, 30B, and 30C with the features (specifically, hash values) of the user's facial image stored in the memory 16 using the authentication means 15 (STEP 34). More specifically, if the match rate between the feature amounts of the user's facial image received from authentication engines 30A, 30B, and 30C and the feature amounts of the user's facial image stored in memory 16 exceeds a predetermined threshold (e.g., 80%), authentication means 15 authenticates the user. As described above, memory 16 stores pre-registered user identification information and identification information for authentication engines 30A, 30B, and 30C in association with the feature amounts of the user's facial image.

When the authentication means 15 authenticates the user ("YES" in STEP 35), information related to the authentication result is transmitted from the processor 12 of the facial authentication system 10 to the authentication engines 30A, 30B, and 30C via the communication unit 18 (STEP 36). The processors 32A, 32B, and 32C of the authentication engines 30A, 30B, and 30C, which have received the information related to the authentication result, enable the respective processing units 40A, 40B, and 40C to implement the service corresponding to the authentication engine 30A, 30B, and 30C (STEP 37). The processors 32A, 32B, and 32C of the authentication engines 30A, 30B, and 30C then transmit information related to the service usage status to the facial authentication system 10. As a result, information related to the service usage status at each service provider is stored in the memory 16 for each user in the facial authentication system 10.

On the other hand, if the features of the user's facial image received from authentication engines 30A, 30B, and 30C do not substantially match the features of the user's facial image stored in memory 16 and the authentication means 15 is unable to authenticate the user ("NO" in STEP 35), information related to the authentication result is sent from processor 12 of face authentication system 10 to authentication engines 30A, 30B, and 30C via communication unit 18 (STEP 38). Then, processors 32A, 32B, and 32C of authentication engines 30A, 30B, and 30C that have received the information related to the authentication result disable the service corresponding to authentication engine 30A, 30B, and 30C via their respective processing units 40A, 40B, and 40C (STEP 39). In this case, too, the processors 32A, 32B, and 32C of the authentication engines 30A, 30B, and 30C send information related to the usage status of the service (specifically, information that the user attempted to be authenticated by the authentication engines 30A, 30B, and 30C but was not authenticated and was unable to use the service) to the face authentication system 10.

With this authentication method, even if the features of a user's facial image are registered in one service provider's authentication engine (e.g., authentication engine 30A) but not in another service provider's authentication engine (e.g., authentication engine 30B), by storing the features of the user's facial image in memory 16 of face authentication system 10 in association with the identification information of authentication engines 30A, 30B, and 30C, the user can be authenticated by capturing an image of the user's face with an imaging unit, even at a service provider where the features of the user's facial image are not registered. In this case, the user does not need to register facial image data in all of the multiple authentication engines, thereby saving the user effort.

Furthermore, further examples of the face authentication system 10 and face authentication method according to this embodiment will be described using Figures 7 to 9. Note that in the face authentication system 10 and each authentication engine 30A, 30B, and 30C shown in Figure 7, the same components as those in the face authentication system 10 and each authentication engine 30A, 30B, and 30C shown in Figures 1 and 4 will be assigned the same reference numerals and their description will be omitted.

7, the processor 12 of the facial authentication system 10 includes a feature extraction means 14 that extracts features of the user's facial image corresponding to each authentication engine 30A, 30B, and 30C as hash values based on facial image data received from the user terminal 20, a registration means 13 that registers the extracted features of the user's facial image, and an authentication means 15 that authenticates the user based on the features (specifically, hash values) of the user's facial image captured by the imaging units 38A to 38C of each authentication engine 30A, 30B, and 30C. By executing a program stored in the memory 16, the processor 12 is configured to store in the memory 16 the features (specifically, hash values) of the user's facial image extracted by the feature extraction means 14 in the registration means 13 in association with the user's identification information and the identification information of the authentication engines 30A, 30B, and 30C. The processor 12 also executes a program stored in memory 16, which causes the authentication means 15 to compare the features (specifically, hash values) of the user's facial image captured by the imaging units 38A-38C of each authentication engine 30A, 30B, and 30C with the features (specifically, hash values) of the user's facial image corresponding to each authentication engine 30A, 30B, and 30C stored in memory 16, thereby authenticating the user. Note that the programs executed by the processor 12 are not limited to those stored in memory 16. Processors 12 may execute a program transmitted to the facial authentication system 10 from an external device or a program stored on a recording medium removably attached to the facial authentication system 10, thereby performing processing in the feature extraction means 14, registration means 13, and authentication means 15.

Each of the authentication engines 30A, 30B, and 30C located at each service facility is composed of, for example, a computer, and each authentication engine 30A, 30B, and 30C has a processor 32A, 32B, and 32C such as a CPU, memory 36A, 36B, and 36C, an imaging unit 38A, 38B, and 38C, a processing unit 40A, 40B, and 40C, and a communication unit 42A, 42B, and 42C. The processors 32A, 32B, and 32C have feature extraction means 34A, 34B, and 34C that extract features of the user's facial image as a hash value based on the user's facial image data captured by the imaging unit 38A, 38B, and 38C. Note that in the example shown in FIG. 7, the processors 32A, 32B, and 32C do not have feature extraction means 34A, 34B, and 34C and authentication means 35A, 35B, and 35C as shown in FIG. 1. Additionally, in the example shown in Figure 7, memories 36A, 36B, and 36C are not configured to store feature amounts of the user's facial image.

In the example shown in Figure 7, the facial authentication system 10 and the authentication engines 30A, 30B, and 30C located at each service facility are linked via an API (application programming interface). This makes it easier to configure each of the authentication engines 30A, 30B, and 30C systems than if each were configured independently.

Next, the processing steps performed when authenticating a user using the face authentication system 10 and the authentication engines 30A, 30B, and 30C shown in Figure 7 will be explained using Figures 8 and 9.

First, we will explain the process by which a user registers facial image data in the facial authentication system 10 using the user terminal 20. The specific method by which a user captures a facial image using the user terminal 20 has already been explained, so it will not be explained here. When a user initially registers using such a facial authentication app on the user terminal 20, various information entered on the user registration screen and the user's facial image data are transmitted from the user terminal 20 to the facial authentication system 10. In this way, the processor 12 of the facial authentication system 10 receives the facial image data from the user terminal 20 (STEP 41). The processor 12 of the facial authentication system 10 also receives from the user terminal 20 the identification information of the user terminal 20 and the registration information entered into the user terminal 20, such as the user's name, date of birth, telephone number, email address, and password. The processor 12 also issues a user ID as the user's identification information and stores this issued user ID in memory 16.

Next, the processor 12 of the facial authentication system 10 extracts facial image features corresponding to each authentication engine 30A, 30B, and 30C as hash values using the feature extraction means 14 based on the facial image data received from the user terminal 20 (STEP 42). At this time, the feature extraction means 14 extracts the user's facial image features for each authentication engine 30A, 30B, and 30C, and the feature extraction means 14 extracts the user's facial image features for each authentication engine 30A, 30B, and 30C. Furthermore, the feature extraction means 14 extracts only the user's facial image features corresponding to the authentication engines 30A, 30B, and 30C of the service provider pre-selected by the user. Then, the processor 12 causes the registration means 13 to store the facial image features corresponding to each authentication engine 30A, 30B, and 30C extracted by the feature extraction means 14 in the memory 16 of the facial authentication system 10 in association with the user ID (user identification information) and the identification information of the authentication engines 30A, 30B, and 30C (STEP 43). In this way, registration of the user's facial image captured by the user terminal 20 is completed. Note that in the example shown in FIG. 7, information related to the features of the user's facial image stored in memory 16 is not transmitted from the facial authentication system 10 to the authentication engines 30A, 30B, and 30C of the service provider selected by the user.

Next, the process of authenticating a user in each authentication engine 30A, 30B, 30C will be described. When user authentication becomes necessary at the service facility where each authentication engine 30A, 30B, 30C is installed, the user's facial image data is first obtained by capturing an image of the user using the imaging units 38A, 38B, 38C of the authentication engines 30A, 30B, 30C (STEP 51). The processors 32A, 32B, 32C of the authentication engines 30A, 30B, 30C transmit the user's facial image data captured by the imaging units 38A, 38B, 38C to the processor 12 of the facial authentication system 10 via the communication units 42A, 42B, 42C (STEP 52). When the processor 12 of the facial authentication system 10 receives the user's facial image data from the authentication engines 30A, 30B, and 30C, it receives only the user's facial image data transmitted from the authentication engines 30A, 30B, and 30C of the service provider selected by the user, which is stored in the memory 16. In the facial authentication system 10, the processor 12 extracts features of the user's facial image as hash values using the feature extraction means 14 based on the facial image data received from the authentication engines 30A, 30B, and 30C (STEP 53). The processor 12 then authenticates the user by comparing the features of the user's facial image extracted by the feature extraction means 14 (specifically, the hash values) with the features of the user's facial image stored in the memory 16 (specifically, the hash values) using the authentication means 15 (STEP 54). More specifically, if the match rate between the features of the user's facial image extracted by the feature extraction means 14 and the features of the user's facial image stored in memory 16 exceeds a predetermined threshold (e.g., 80%), the authentication means 15 authenticates the user. As described above, memory 16 stores pre-registered user identification information and identification information for authentication engines 30A, 30B, and 30C in association with the features of the user's facial image.

When the authentication means 15 authenticates the user ("YES" in STEP 55), information related to the authentication result is transmitted from the processor 12 of the facial authentication system 10 to the authentication engines 30A, 30B, and 30C via the communication unit 18 (STEP 56). The processors 32A, 32B, and 32C of the authentication engines 30A, 30B, and 30C, which have received the information related to the authentication result, enable the respective processing units 40A, 40B, and 40C to implement the service corresponding to the authentication engine 30A, 30B, and 30C (STEP 57). The processors 32A, 32B, and 32C of the authentication engines 30A, 30B, and 30C then transmit information related to the service usage status to the facial authentication system 10. As a result, information related to the service usage status at each service provider is stored in the memory 16 for each user in the facial authentication system 10.

On the other hand, if the features of the user's facial image received from authentication engines 30A, 30B, and 30C do not substantially match the features of the user's facial image stored in memory 16 and the authentication means 15 is unable to authenticate the user ("NO" in STEP 55), information relating to the authentication result is sent from processor 12 of face authentication system 10 to authentication engines 30A, 30B, and 30C via communication unit 18 (STEP 58). Then, processors 32A, 32B, and 32C of authentication engines 30A, 30B, and 30C that have received the information relating to the authentication result disable the service corresponding to authentication engine 30A, 30B, and 30C via their respective processing units 40A, 40B, and 40C (STEP 59). In this case, too, the processors 32A, 32B, and 32C of the authentication engines 30A, 30B, and 30C send information related to the usage status of the service (specifically, information that the user attempted to be authenticated by the authentication engines 30A, 30B, and 30C but was not authenticated and was unable to use the service) to the face authentication system 10.

With this authentication method, even if the features of a user's facial image are registered in one service provider's authentication engine (e.g., authentication engine 30A) but not in another service provider's authentication engine (e.g., authentication engine 30B), by storing the features of the user's facial image in memory 16 of face authentication system 10 in association with the identification information of authentication engines 30A, 30B, and 30C, the user can be authenticated by capturing an image of the user's face with an imaging unit, even at a service provider where the features of the user's facial image are not registered. In this case, the user does not need to register facial image data in all of the multiple authentication engines, thereby saving the user effort.

Next, we will explain the process performed when a user wants to increase the number of service providers to which the above-mentioned facial authentication service is applied in the facial authentication system 10 shown in Figures 1 to 9. After the user completes the user registration described above, when the user presses the "Add Service" button with their finger on the initial screen of the user terminal 20 shown in Figure 10, a list of service providers is displayed as shown in Figure 13. Note that this list of service providers is pre-registered in the facial authentication system 10. On the screen shown in Figure 13, the icons of unregistered services are distinguished from the icons of registered services by displaying them in different colors or by displaying the icons of unregistered services in a dimmed color. When the user presses the icon of an unregistered service with their finger, the terms of the service to be added are displayed. When the user inputs an instruction to agree to the service terms, the unregistered service becomes a registered service. At this time, the facial authentication system 10 associates the service provider associated with this registered service with the user ID (user identification information) and stores it in memory 16. Thereafter, the user terminal 20 displays a facial image capture screen as shown in Figure 12. When the user captures a facial image on such an imaging screen using the user terminal 20, the user's facial image data is transmitted from the user terminal 20 to the facial authentication system 10. In this manner, the processor 12 of the facial authentication system 10 receives the facial image data from the user terminal 20. Then, based on the facial image data received from the user terminal 20, the processor 12 of the facial authentication system 10 extracts, as hash values, facial image features corresponding to the authentication engine of the new service provider using the feature extraction means 14. The processor 12 stores, using the registration means 13, the facial image features corresponding to the new authentication engine extracted by the feature extraction means 14 in the memory 16 of the facial authentication system 10 in association with the user ID (user identification information) and the identification information of the authentication engine of the new service provider. In this manner, registration of the new service provider is completed. As will be described later, if the user's facial image data is stored in memory 16, when the user registers a new service provider using the user terminal 20, the feature extraction means 14 may extract facial image features corresponding to the new service provider's authentication engine as hash values based on the user's facial image data stored in memory 16, without the user terminal 20 capturing the user's facial image. The user may also be able to delete a registered service on a screen such as that shown in FIG. 13. In this case, the registered service becomes an unregistered service. Furthermore, information stored in memory 16 relating to the user's facial image features corresponding to the authentication engine of the service provider related to the deleted registered service is deleted.

Furthermore, after the user has performed the user registration described above, when the user presses the "Authentication History" button on the initial screen of the user terminal 20 as shown in FIG. 10, a list of past authentication history information (in other words, a list of information related to the user's use of the service provider) as shown in FIG. 14 will be displayed on the user terminal 20. More specifically, the memory 16 of the facial authentication system 10 stores the user's past authentication history information in association with the user's identification information. When the user presses the "Authentication History" button on the initial screen of the user terminal 20 as shown in FIG. 10, a signal requesting the user's past authentication history information is transmitted from the user terminal 20 to the processor 12 of the facial authentication system 10. When the processor 12 of the facial authentication system 10 receives a signal requesting the user's past authentication history information from the user terminal 20, it transmits the past authentication history information corresponding to the user's identification information stored in the memory 16 to the user terminal 20 via the communication unit 18. As a result, the user terminal 20 will display a list of the user's past authentication history information. Furthermore, when a user presses a certain authentication history display with their finger in a list of past authentication history information such as that shown in FIG. 14, details of that authentication history will be displayed on the user terminal 20 as shown in FIG. 15.

In addition, in this embodiment, instead of a user using a user terminal 20 to register the user's facial authentication features in the facial authentication system 10, the user may use one of the authentication engines 30A, 30B, and 30C to register the user's facial authentication features in the facial authentication system 10. Specifically, when a user inputs registration information into one of the authentication engines 30A, 30B, and 30C and captures a face image of the user using the imaging units 38A, 38B, and 38C, the input registration information and the user's facial image data are transmitted from the authentication engines 30A, 30B, and 30C to the facial authentication system 10. In this manner, the processor 12 of the facial authentication system 10 receives the facial image data from the authentication engines 30A, 30B, and 30C. The processor 12 also issues a user ID as the user's identification information based on the registration information received from the authentication engines 30A, 30B, and 30C, and stores the issued user ID in memory 16.

Next, the processor 12 of the facial authentication system 10 extracts facial image features corresponding to each authentication engine 30A, 30B, and 30C as hash values using the feature extraction means 14 based on the facial image data received from the authentication engines 30A, 30B, and 30C. At this time, the feature extraction means 14 extracts the user's facial image features for each authentication engine 30A, 30B, and 30C. The feature extraction means 14 also extracts only the user's facial image features corresponding to the authentication engines 30A, 30B, and 30C of the service provider pre-selected by the user. For example, if the user is authorized to use facial image data for the service provider where authentication engine 30A is installed, but is not authorized to use facial image data for the service provider where authentication engine 30B is installed, the feature extraction means 14 extracts only the user's facial image features corresponding to authentication engine 30A. As described above, the memory 16 stores the user's identification information and the service provider selected by the user in association with each other. The processor 12 then causes the registration means 13 to store the facial image features corresponding to each authentication engine 30A, 30B, and 30C extracted by the feature extraction means 14 in the memory 16 of the face authentication system 10 in association with the user ID (user identification information) and the identification information of the authentication engines 30A, 30B, and 30C. In this manner, registration of the user's facial images captured by the imaging units 38A, 38B, and 38C of the authentication engines 30A, 30B, and 30C is completed. In this manner, the user can register the facial authentication features of the user in the face authentication system 10 without using the user terminal 20.

According to the facial authentication method performed by the facial authentication system 10 according to this embodiment and configured as described above, a user's facial image data and user identification information are received, and feature amounts of the user's facial image are extracted for each of the multiple authentication engines 30A, 30B, and 30C based on the received user's facial image data. Information relating to the extracted feature amounts of the user's facial image for each of the multiple authentication engines 30A, 30B, and 30C is then associated with the received user's identification information and stored in memory 16. This facial authentication method makes it possible to easily perform facial authentication using multiple authentication engines 30A, 30B, and 30C.

Specifically, while the use of authentication engines using facial recognition has been widespread in the past, conventional facial recognition systems were unable to perform facial recognition with authentication engines that did not have registered facial data. Therefore, in order to perform authentication with multiple authentication engines, the user had to register their facial data with each of the multiple authentication engines, which was time-consuming and stressful. In contrast, in this embodiment, even if a user's facial image features are registered with one service provider's authentication engine (e.g., authentication engine 30A) but not with another service provider's authentication engine (e.g., authentication engine 30B), the facial image features of the user are stored in memory 16 of facial recognition system 10 for each of authentication engines 30A, 30B, and 30C. By capturing the user's facial image with imaging units 38A, 38B, and 38C, the user can be authenticated even with authentication engines 30A, 30B, and 30C of service providers that do not have registered the user's facial image features. In this case, the user does not need to register facial image data for all of the multiple authentication engines 30A, 30B, and 30C, which saves the user time and effort. This makes it possible to encourage users who find registering facial image data troublesome and have not used various services that use authentication engines that do not have registered facial image data to use these services with ease.

Furthermore, when features of a user's facial image, such as a hash value, are extracted and stored in memory 16, the amount of data stored in memory 16 can be significantly reduced compared to when the user's facial image data itself is stored in memory 16. This is because the amount of data for the features of the user's facial image is smaller than the amount of data for the user's facial image data itself. In addition, in this case, the user's privacy can be protected even more reliably, as the user's facial image data itself is not stored in memory 16. Furthermore, when information related to the features of a user's facial image is sent between face authentication system 10 and each authentication engine 30A, 30B, 30C, the amount of data communication can be significantly reduced compared to when the user's facial image data is sent between face authentication system 10 and each authentication engine 30A, 30B, 30C.

Furthermore, in the face authentication method of this embodiment, as described above, when extracting features of a user's face image based on the received user's face image data, the features of the user's face image are extracted for each of the multiple authentication engines 30A, 30B, and 30C, and the extracted features of the user's face image for each of the multiple authentication engines 30A, 30B, and 30C are associated with the user's identification information and stored in memory by the registration means 13. This also makes it possible to deal with cases where the features of the user's face image extracted by the feature extraction means 14 differ depending on the type of authentication engine 30A, 30B, and 30C. Note that if the same program is used in the multiple authentication engines 30A, 30B, and 30C and the features of the user's face image extracted by the feature extraction means 14 are common to the authentication engines 30A, 30B, and 30C, it is not necessary to extract the features of the user's face image for each of the multiple authentication engines 30A, 30B, and 30C.

In addition, in the facial authentication method of this embodiment, as described above, information related to the service provider selected by the user is stored in memory 16 in association with the user's identification information. In the step of extracting features of the user's facial image for each of multiple authentication engines 30A, 30B, and 30C based on the received user's facial image data by feature extraction means 14, feature extraction means 14 extracts features of the user's facial image stored in memory 16 that correspond only to the authentication engines of the service providers selected by the user. In this case, features of the user's facial image corresponding to authentication engines 30A, 30B, and 30C of service providers not selected by the user are not stored in memory 16, thereby improving security and reassuring the user. Furthermore, companies and other entities participating in the group of authentication engines managed collectively by facial authentication system 10 can appeal to customers by promoting the improved customer convenience of being able to be authenticated by multiple authentication engines simply by registering facial image data on user terminal 20, etc.

Furthermore, in the face authentication method of this embodiment, as described above, the feature extraction means 14 extracts a hash value calculated from the received user's face image data using a predetermined hash function as a feature of this user's face image for each of the multiple authentication engines 30A, 30B, and 30C. In this case, the hash value is stored in memory 16 as a feature of the user's face image, so the amount of data stored in memory 16 can be reduced compared to when the face image data itself is stored in memory 16. Furthermore, since it is difficult to restore or infer face image data from the hash value, the face authentication system 10 only stores the hash value, thereby improving user privacy and security.

In this embodiment, the feature extraction means 14 is not limited to extracting the feature amounts of the user's facial image as hash values for each of the multiple authentication engines 30A, 30B, and 30C based on the received user's facial image data. The feature extraction means 14 may also extract the feature amounts of the user's facial image as values of a different type from hash values for each of the multiple authentication engines 30A, 30B, and 30C based on the received user's facial image data. For example, the relative position, size, and shape of each facial feature (eyes, nose, ears, etc.) may be extracted as features of the user's facial image. Even in this case, if the amount of data of values of a different type from hash values is smaller than the amount of data of the facial image itself, the amount of data stored in memory 16 can be reduced.

Furthermore, in the face authentication method of this embodiment, as described above, in the step of extracting feature quantities of a user's facial image for each of the multiple authentication engines 30A, 30B, and 30C by the feature extraction means 14 based on the received user's facial image data, the feature quantities of the user's facial image for each of the multiple authentication engines 30A, 30B, and 30C are extracted by the feature extraction means 14 based on the user's facial image data transmitted from the user terminal 20 carried by the user. Alternatively, in the step of extracting feature quantities of a user's facial image for each of the multiple authentication engines 30A, 30B, and 30C based on the received user's facial image data by the feature extraction means 14, the feature quantities of the user's facial image for each of the multiple authentication engines 30A, 30B, and 30C may be extracted by the feature extraction means 14 based on the user's facial image data transmitted from one of the multiple authentication engines 30A, 30B, and 30C.

In addition, this embodiment uses a program executed by the processor 12 for performing a facial authentication method using the facial authentication system 10, and a recording medium on which this program is recorded. Here, by executing the program, the processor 12 accepts a user's facial image data and the user's identification information, and extracts features of the user's facial image for each of the multiple authentication engines 30A, 30B, and 30C based on the accepted user's facial image data. Then, information related to the extracted features of the user's facial image for each of the multiple authentication engines 30A, 30B, and 30C is stored in memory 16 in association with the accepted user's identification information. Using this program and recording medium, facial authentication can be easily performed using the multiple authentication engines 30A, 30B, and 30C.

Furthermore, this embodiment uses a facial authentication system 10 equipped with a processor 12. In such a facial authentication system 10, the processor 12 executes a program to accept a user's facial image data and the user's identification information, and extracts features of the user's facial image for each of the multiple authentication engines 30A, 30B, and 30C based on the accepted user's facial image data. Then, information related to the extracted features of the user's facial image for each of the multiple authentication engines 30A, 30B, and 30C is stored in memory 16 in association with the accepted user's identification information. Such a facial authentication system 10 makes it possible to easily perform facial authentication using multiple authentication engines 30A, 30B, and 30C.

Note that the face recognition method and face recognition system according to the present invention are not limited to the above-described aspects, and various modifications can be made.

For example, a facial authentication system such as that shown in FIG. 16 may be used. The facial authentication system 50 shown in FIG. 16 includes a processor 52, a first server 56, a second server 58, and a third server 60. Here, each of the servers 56, 58, and 60 corresponds to each of the authentication engines 30A, 30B, and 30C. Specifically, the first server 56 corresponds to the authentication engine 30A, the second server 58 corresponds to the authentication engine 30B, and the third server 60 corresponds to the authentication engine 30C. Although FIG. 16 illustrates three authentication engines 30A, 30B, and 30C, if two or four or more authentication engines are used, a server corresponding to each authentication engine is provided in the facial authentication system 10. The processor 52 also includes a server management means 52a, a feature extraction means 54, a registration means 53, and an authentication means 55. The feature extraction means 54, registration means 53, and authentication means 55 of the processor 52 have substantially the same functions as the feature extraction means 14, registration means 13, and authentication means 15 of the processor 12 of the face authentication system 10 shown in Figures 1, 4, and 7. The server management means 52a manages each of the servers 56, 58, and 60.

Each server 56, 58, 60 stores feature quantities of user facial image data corresponding to each authentication engine 30A, 30B, 30C, associated with the user's identification information. Each server 56, 58, 60 is communicatively connected to its corresponding authentication engine 30A, 30B, 30C via a network such as the Internet. Each server 56, 58, 60 is configured to be centrally managed by the server management means 52a using an API (application programming interface). This makes it easier to configure the systems for each server 56, 58, 60 than if the systems (programs) for each server 56, 58, 60 were configured independently. Furthermore, the server management means 52a and the service agencies where each authentication engine 30A, 30B, 30C is installed are API-linked. For example, the platform of the server management means 52a could be made available to each service agency, and each service agency could use the same platform as the server management means 52a, making it easy to build a system for providing services at each service agency.

A facial authentication system 50 having such a processor 52 and each server 56, 58, 60 can perform the same processing as the facial authentication system 10 having the processor 12. That is, according to the facial authentication method performed by the facial authentication system 50 shown in FIG. 16, the processor 52 extracts features of the user's facial image for each authentication engine 30A, 30B, 30C based on the received user's facial image data using the feature extraction means 54, and associates the extracted features of the user's facial image with the user's identification information and the authentication engines 30A, 30B, 30C using the registration means 53, and stores them in each server 56, 58, 60.

In addition, information related to the features of the user's facial image stored in each server 56, 58, 60 is transmitted from each server 56, 58, 60 to the corresponding authentication engine 30A, 30B, 30C. As a result, when authenticating a user in each authentication engine 30A, 30B, 30C, the user's facial image data is acquired by capturing an image of the user using the imaging unit 38A, 38B, 38C, and the feature extraction means 34A, 34B, 34C extracts features of the user's facial image based on the acquired facial image data, thereby enabling each authentication engine 30A, 30B, 30C to authenticate the user. Thereafter, the processors 32A, 32B, 32C of the authentication engines 30A, 30B, 30C transmit information related to the service usage status to the facial authentication system 10. As a result, information related to the service usage status at each service provider in the facial authentication system 50 is stored for each user in each server 56, 58, 60.

As another method for authenticating a user, when authenticating a user in each authentication engine 30A, 30B, 30C, the user's facial image data is acquired by capturing an image of the user using the imaging units 38A, 38B, 38C, and the feature extraction means 34A, 34B, 34C extracts features of the user's facial image based on the captured facial image data. Information related to the features of the user's facial image is then sent from each authentication engine 30A, 30B, 30C to the facial authentication system 50. This allows the user to be authenticated by the authentication means 55. The user authentication result is then sent from the facial authentication system 50 to the original authentication engine 30A, 30B, 30C.

As another method for authenticating a user, when authenticating a user in each authentication engine 30A, 30B, 30C, the user's facial image data is obtained by capturing an image of the user using the imaging units 38A, 38B, 38C. The user's facial image data is then transmitted from each authentication engine 30A, 30B, 30C to the facial authentication system 50. The processor 52 then extracts features of the user's facial image based on the user's facial image data transmitted to each server 56, 58, 60 using the feature extraction means 54, and compares the extracted features of the user's facial image with the features of the user's facial image stored in each server 56, 58, 60 using the authentication means 55. This enables the authentication means 55 to authenticate the user. The user authentication result is then transmitted from the facial authentication system 50 to the original authentication engine 30A, 30B, 30C.

These facial recognition methods make it easy to perform facial recognition using multiple authentication engines 30A, 30B, and 30C.

Furthermore, in a facial authentication system 10 such as that shown in Figures 1, 4, 7, etc., the processor 12 may store the user's facial image data itself transmitted from the user terminal 20 or each authentication engine 30A, 30B, 30C in the memory 16.

In addition, while the above example shows a configuration in which the facial authentication system 10, 50 is installed separately from the authentication engines 30A, 30B, 30C installed at each service facility, one of the authentication engines 30A, 30B, 30C installed at each service facility may also perform the functions of the facial authentication system 10, 50. In other words, the processor of one of the authentication engines 30A, 30B, 30C installed at each service facility may have feature extraction means, registration means, and authentication means that have functions equivalent to the feature extraction means 14, registration means 13, and authentication means 15 in the processor 12 of the facial authentication system 10 shown in Figures 1, 4, 7, etc.

10 Face authentication system 12 Processor 13 Registration means 14 Feature extraction means 15 Authentication means 16 Memory 18 Communication unit 20 User terminal 30A, 30B, 30C Authentication engine 32A, 32B, 32C Processor 34A, 34B, 34C Feature extraction means 35A, 35B, 35C Authentication means 36A, 36B, 36C Memory 38A, 38B, 38C Imaging unit 40A, 40B, 40C Processing unit 42A, 42B, 42C Communication unit 50 Face authentication system 52 Processor 52a Server management means 53 Registration means 54 Feature extraction means 55 Authentication means 56 First server 58 Second server 60 Third server

Claims (12)

a first image capturing means for capturing facial image data of a user for extracting features to be used as a comparison standard;
a plurality of face authentication devices that compare the user's face with the comparison criteria and determine whether or not to provide the service requested by the user;
a distribution server that receives the face image data acquired by the first photographing means and transmits and receives data to and from each of the face authentication devices;
the first photographing means is provided using a user terminal that is an information terminal carried by a user,
Each of the face authentication devices has a feature extraction means for extracting features from face image data of a user,
the feature amount used as the comparison standard in each of the face authentication devices is generated based on the face image data acquired by the first photographing means and is registered in a storage device provided in each of the face authentication devices ;
The face recognition devices each operate differently when the face recognition of the user is successful, and the details of the processing are different depending on the device.
Authentication system. Each of the face recognition devices is installed in a service facility that is a facility where services are provided using these face recognition devices.
The authentication system of claim 1 . The distribution server and each of the face recognition devices are separate computer systems connected via the Internet.
The authentication system of claim 1 . Each of the face authentication devices independently determines whether or not to provide the service requested by the user.
The authentication system of claim 1 . The distribution server itself does not perform face authentication processing.
The authentication system of claim 1 . The facial recognition devices have different extraction specifications for feature amounts from facial image data.
The authentication system of claim 1 . The authentication means of each face authentication device is aggregated, and a server device that performs centralized user identity verification is not provided.
The authentication system according to claim 1 or 6 . At least one of the face authentication devices can generate and register features to be used as the comparison standard even from a face image acquired by a photographing means provided in the face authentication device.
The authentication system of claim 1 . The system further comprises a service registration means for registering a service to be used by a user from among the individual services provided using each of the face authentication devices,
the service registration means is provided using a user terminal, which is an information terminal possessed by a user;
The authentication system of claim 1 . At least one of the facial authentication devices authenticates a user to perform a payment transaction, and the facial authentication device or the payment transaction requires the user to authenticate by another method in addition to authenticating the user's face.
The authentication system of claim 1 . At least one of the face recognition devices is
a second photographing means which is a photographing means provided in the face authentication device;
an authentication server connected to the second photographing means via the Internet;
the authentication server has means for extracting features from face image data and means for authenticating a user;
the second photographing means transmits the acquired face image data of the user to the authentication server;
The authentication system of claim 1 . Each of the face authentication devices has a second photographing means for photographing a face of a user.
The authentication system of claim 1 .