Processing apparatus

Abstract

This processing apparatus comprises a storage unit that stores, in a memory device, a false authentication score that is a score calculated when it is determined that a false authentication has occurred during facial authentication, and an adjustment unit that adjusts a value to be used when the facial authentication is performed on the basis of the false authentication score.

Description

Processing equipment

[0001] The present invention relates to a processing device, a processing method, and a recording medium.

[0002] It is known that biometric information such as facial features is utilized to achieve various purposes such as face recognition.

[0003] For example, Patent Document 1 describes a face recognition device that includes a face image acquisition unit that acquires a face image of an object to be authenticated, a matching unit that performs face recognition on the face image of the object to be authenticated based on a threshold, a time measurement unit that measures the elapsed time since the start of operation of the face recognition device, and a threshold change unit that restricts the threshold from being changed to a value greater than a value determined depending on the measured elapsed time.

[0004] Japanese Patent Application Laid-Open No. 2019-125003

[0005] Depending on the environment in which a camera capturing a facial image is installed, the appropriate threshold value used when performing facial recognition may vary. To address such variations, simply adjusting the threshold value over time as described in Patent Document 1 has not always been appropriate. Thus, there has been a problem in that it may be difficult to appropriately adjust the value used when performing facial recognition.

[0006] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide a processing device, a processing method, and a recording medium that aim to solve the above-mentioned problems.

[0007] In order to achieve this object, a processing device that is one form of the present disclosure has a configuration including: a storage unit that stores an erroneous authentication score, which is a score calculated when it is determined that an erroneous authentication has occurred in face authentication, in a storage device; and an adjustment unit that adjusts a value used when performing face authentication based on the erroneous authentication score.

[0008] Furthermore, a processing method according to another aspect of the present disclosure is configured to store an erroneous authentication score, which is a score calculated when it is determined that an erroneous authentication has occurred in face authentication, in a storage device, and adjust a value used when performing face authentication based on the erroneous authentication score.

[0009] Furthermore, a recording medium that is another form of the present disclosure is a computer-readable recording medium that stores in a storage device an erroneous authentication score, which is a score calculated when it is determined that an erroneous authentication has occurred in face authentication, and records a program for implementing a process of adjusting a value used when performing face authentication based on the erroneous authentication score.

[0010] According to the above-mentioned configurations, the above-mentioned problems can be solved.

[0011] FIG. 1 is a diagram illustrating a configuration example of an authentication system according to a first embodiment of the present disclosure. FIG. 2 is a block diagram illustrating a configuration example of an authentication device. FIG. 3 is a diagram illustrating an example of authentication processing. FIG. 4 is a diagram illustrating an example of authentication processing. FIG. 5 is a diagram illustrating an example of threshold adjustment. FIG. 6 is a diagram illustrating an example of threshold adjustment. FIG. 7 is a diagram illustrating an example of threshold adjustment. FIG. 8 is a flowchart illustrating an example of operation when storing a score. FIG. 9 is a flowchart illustrating an example of operation when adjusting a threshold. FIG. 10 is a flowchart illustrating an example of operation when determining to omit confirmation. FIG. 11 is a block diagram illustrating a configuration example of a processing device according to a second embodiment of the present disclosure. FIG. 12 is a block diagram illustrating an example of the configuration of a processing device.

[0012] [First Embodiment] A first embodiment of the present disclosure will be described with reference to Figs. 1 to 11. Fig. 1 is a diagram illustrating a configuration example of an authentication system 100. Fig. 2 is a block diagram illustrating a configuration example of an authentication device 300. Figs. 3 and 4 are diagrams illustrating an example of authentication processing. Figs. 5 to 8 are diagrams for explaining an example of threshold adjustment. Figs. 9 to 11 are flowcharts illustrating an operation example of the authentication device 300.

[0013] In a first embodiment of the present disclosure, an authentication system 100 will be described that performs face authentication based on a facial image of a person to be authenticated, who is a user of the authentication system 100, and that can adjust a value used during face authentication by analyzing the authentication result. As will be described later, the authentication system 100 described in this embodiment collects an error authentication score, which is a score at the time of the error authentication, when it is determined that an error authentication has occurred. Then, the authentication system 100 adjusts a threshold value, which is a value used during authentication, based on the collected error authentication score.

[0014] In this embodiment, the false authentication score includes a score obtained when a false authentication is performed based on a facial image of another person, a score obtained when authentication of a person to be authenticated fails, and the like. For example, the false authentication score includes a false acceptance score, which is a score calculated based on a facial image of another person that the authentication system 100 erroneously determines to be the person to be authenticated when a false authentication is performed based on a facial image of another person pre-stored in the authentication system 100. The false authentication score also includes a false rejection score, which is a score that is assumed to be the person to be authenticated, such as the highest score calculated by the authentication system 100 when authentication of a person to be authenticated whose facial image is supposed to be stored in the authentication system 100 fails. For example, the authentication system 100 can identify the above-mentioned false authentication by confirming the authentication result or performing multi-step authentication, as described below. Note that when an individual person to be authenticated can be identified by multi-step authentication or the like, the false rejection score may be a score calculated by the authentication system 100 based on a stored facial image corresponding to the identified person to be authenticated, among the scores calculated by the authentication system 100.

[0015] In the present embodiment, the score refers to a value calculated by the authentication system 100 during face authentication. For example, the score may be the degree of similarity between a feature extracted from a face image of a user using the authentication system 100 and a feature extracted from a face image pre-stored in the authentication system 100. The feature may be extracted using a known method, such as calculation based on the detection results of face feature points within the detected face area. The similarity may also be a value calculated using a known method, such as cosine similarity.

[0016] Fig. 1 shows an example of the configuration of an authentication system 100. Referring to Fig. 1, the authentication system 100 includes, for example, an image capture device 200 such as a camera, and an authentication device 300 that performs face authentication. As shown in Fig. 1, the image capture device 200 and the authentication device 300 are connected via a network or the like so that they can communicate with each other. Note that the authentication system 100 may have a configuration other than that shown in Fig. 1, such as including a plurality of image capture devices 200.

[0017] The imaging device 200 acquires a facial image of a user of the authentication system 100, a person to be authenticated, or the like. For example, the imaging device 200 may be a general device such as a camera. The imaging device 200 can transmit the acquired facial image to the authentication device 300. The imaging device 200 may transmit the acquired facial image to the authentication device 300 together with identification information predetermined for each imaging device 200, information indicating the time the facial image was acquired, and the like.

[0018] The authentication device 300 is an information processing device that performs face authentication based on a facial image of the person to be authenticated acquired by the imaging device 200. When it is determined that an authentication error has occurred based on the result of having the person to be authenticated confirm the authentication result or the result of multi-step authentication, the authentication device 300 collects an authentication error score according to the type of authentication error. Then, the authentication device 300 adjusts the value used during authentication based on the collected authentication error score, etc.

[0019] Fig. 2 shows an example of the main configuration of the authentication device 300. Referring to Fig. 2, the authentication device 300 has, as main components, for example, an operation input unit 310, a screen display unit 320, a communication I / F unit 330, a storage unit 340, and an arithmetic processing unit 350.

[0020] 2 illustrates an example in which the functions of the authentication device 300 are realized using one information processing device. However, the authentication device 300 may be realized using multiple information processing devices, for example, on the cloud. For example, the authentication device 300 may be configured with an authentication device having a face image acquisition unit 351, a face authentication unit 352, a result confirmation unit 353, a multi-step authentication unit 354, and a score storage unit 355, among the functions illustrated in FIG. 2, and an analysis device having a threshold adjustment unit 356 and a determination unit 357. Furthermore, the authentication device 300 may not have some of the components illustrated above, such as not having the operation input unit 310, or may have components other than those illustrated above.

[0021] The operation input unit 310 is made up of operation input devices such as a keyboard, a mouse, etc. It detects the operation of the person operating the authentication device 300 and outputs the detected operation to the calculation processing unit 350.

[0022] The screen display unit 320 is composed of a screen display device such as an LCD (Liquid Crystal Display), a display device with a touch panel, etc. In response to instructions from the calculation processing unit 350, the screen display unit 320 can display on the screen various information stored in the storage unit 340, information when the result confirmation unit 353 (described later) performs predetermined result confirmation, and the like.

[0023] The communication I / F unit 330 is made up of a data communication circuit and performs data communication with the image capture device 200 and other external devices connected via a communication line.

[0024] The storage unit 340 is a storage device such as a hard disk or memory. The storage unit 340 stores processing information and a program 345 required for various processes in the arithmetic processing unit 350. The program 345 is read into the arithmetic processing unit 350 and executed to realize various processing units. The program 345 is read in advance from an external device or recording medium via a data input / output function such as the communication I / F unit 330, and is stored in the storage unit 340. Main information stored in the storage unit 340 includes, for example, facial feature amount information 341, multi-step authentication information 342, score information 343, threshold information 344, etc.

[0025] The facial feature amount information 341 includes information about facial images used in facial authentication or features extracted from facial images. For example, the facial feature amount information 341 associates facial images (stored facial images) of users of the authentication system 100 with information about each user, such as their name and affiliation. The facial feature amount information 341 may include information indicating facial features extracted from the facial images instead of or in addition to the facial images. As an example, the facial feature amount information 341 is acquired in advance by acquiring a facial image from an external device, the imaging device 200, or the like via the communication I / F unit 330, and stored in the storage unit 340. The facial feature amount information 341 may be updated as needed by acquiring a facial image from an external device, the imaging device 200, or the like via the communication I / F unit 330.

[0026] The multi-step authentication information 342 includes information used during multi-step authentication. For example, the multi-step authentication information 342 includes encryption information used during multi-step authentication. Here, the encryption information may be predetermined confirmation information for performing multi-step authentication, such as a value corresponding to the telephone number of the company to which the user of the authentication system 100 belongs, information corresponding to the name or employee number of the user, or any other arbitrary PIN number. For example, the multi-step authentication information 342 includes encryption information for each user who uses the authentication system 100. The multi-step authentication information 342 may also include encryption information common to each user. For example, the multi-step authentication information 342 is acquired in advance from an external device via the communication I / F unit 330, input using the operation input unit 310, or the like, and stored in the storage unit 340. The multi-step authentication information 342 may be updated as needed, for example, by acquiring it from an external device via the communication I / F unit 330.

[0027] The score information 343 includes information about the score calculated by the authentication device 300 during face authentication. For example, the score information 343 includes not only the true person score, which is the score obtained when face authentication is successful, but also false authentication scores such as the above-mentioned false person acceptance score and false person rejection score. In addition to the scores exemplified above, the score information 343 may also include a false person score, which is a score other than the true person score and false authentication score calculated during face authentication. Note that the false person score corresponds to a score that does not correspond to the false person rejection score among the scores at which the authentication device 300 determines that the person is a false person during face authentication. For example, the score information 343 includes information such as the true person score and false authentication score for each face authentication. The score information 343 may also include information such as the true person score and false authentication score for each user who uses the authentication system 100. The score information 343 may also include various scores for each image capture device 200, time period, season, etc. As an example, the score information 343 is updated when the score storage unit 355 stores the true person score, false authentication score, etc. in the memory unit 340.

[0028] The threshold information 344 includes information about a threshold used during facial authentication. For example, the threshold information 344 may include information about a threshold for each user who uses the authentication system 100. The threshold information 344 may also include information indicating a threshold for each image capture device 200 or for each time period during which facial authentication is performed. For example, the threshold information 344 is acquired in advance from an external device via the communication I / F unit 330, or by input using the operation input unit 310, and is stored in the storage unit 340. The threshold information 344 is updated by a threshold adjustment unit 356 (described later) based on the false authentication score included in the score information 343.

[0029] The arithmetic processing unit 350 has an arithmetic device such as a CPU (Central Processing Unit) and its peripheral circuits. The arithmetic processing unit 350 reads and executes a program 345 from the storage unit 340, thereby causing the hardware and the program 345 to work together to realize various processing units. Major processing units realized by the arithmetic processing unit 350 include, for example, a face image acquisition unit 351, a face authentication unit 352, a result confirmation unit 353, a multi-step authentication unit 354, a score storage unit 355, a threshold adjustment unit 356, and a determination unit 357.

[0030] In addition, instead of the above-mentioned CPU, the arithmetic processing unit 350 may have a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), an MPU (Micro Processing Unit), an FPU (Floating point number Processing Unit), a PPU (Physics Processing Unit), a TPU (Tensor Processing Unit), a quantum processor, a microcontroller, or a combination of these.

[0031] The face image acquisition unit 351 acquires a face image of the person to be authenticated who is the target of face authentication. For example, the face image acquisition unit 351 acquires the face image of the person to be authenticated from the imaging device 200 via the communication I / F unit 330.

[0032] The face authentication unit 352 performs face authentication processing based on the face feature amount information 341 and threshold information 344 to confirm whether a face image of a person matching the person in the face image acquired by the imaging device 200 is stored in the memory unit 340.

[0033] For example, the face authentication unit 352 calculates a score, such as a similarity score, between each stored face image included in the face feature amount information 341 and the face image of the person to be authenticated acquired by the face image acquisition unit 351, and identifies the combination of the face image and the stored face image that results in the highest score. The face authentication unit 352 may identify multiple combinations that result in a score equal to or greater than a predetermined value. Furthermore, the face authentication unit 352 references the threshold information 344 to identify a threshold value for the user corresponding to the stored face image in the identified combination. The face authentication unit 352 then compares the score calculated for the identified combination with the identified threshold value. For example, if the score is equal to or greater than the threshold value, the face authentication unit 352 generates an authentication result indicating successful face authentication. On the other hand, if the score is less than the threshold value, the face authentication unit 352 generates an authentication result indicating unsuccessful face authentication.

[0034] For example, as described above, the face authentication unit 352 performs authentication processing to check whether a face image of a person matching the person in the face image acquired by the imaging device 200 is stored in the storage unit 340. Note that if the authentication device 300 can identify the person to be authenticated in advance by reading the employee ID card of the person to be authenticated, the face authentication unit 352 may identify a threshold value corresponding to the user identified by the above means from the threshold information 344. In this case, the face authentication unit 352 may determine whether face authentication is successful based on the result of comparing the threshold value identified by the above means with the highest score.

[0035] The result confirmation unit 353 confirms with the person to be authenticated whether or not there is an error in the authentication by the face authentication unit 352, for example, by displaying the authentication result by the face authentication unit 352 on the screen display unit 320. In other words, the result confirmation unit 353 functions as a confirmation unit that confirms whether or not an authentication error has occurred by having the person to be authenticated confirm the authentication result, which is a process different from face authentication.

[0036] For example, when the face authentication unit 352 generates an authentication result indicating successful face authentication, the result confirmation unit 353 confirms the authentication result. Specifically, for example, the result confirmation unit 353 confirms with the person to be authenticated whether or not the person to be authenticated, whose face image was acquired by the imaging device 200, is definitely the same person as the user corresponding to the stored face image used to calculate the score indicating successful authentication. As an example, the result confirmation unit 353 can confirm whether or not the person to be authenticated is the identified user by displaying on the screen display unit 320 a name or the like associated with the stored face image, such as "Is this Mr. / Ms. XX?"

[0037] If the result confirmation unit 353 confirms that there is no problem, the result confirmation unit 353 can determine to omit multi-step authentication. In this case, the authentication device 300 may terminate the authentication process and start a predetermined process, such as opening a related door. On the other hand, if the result confirmation unit 353 confirms that the person to be authenticated is different from the identified user, the result confirmation unit 353 determines that erroneous authentication based on a facial image of another person has occurred. Furthermore, the result confirmation unit 353 determines to perform multi-step authentication. Note that if it is confirmed that the person to be authenticated is different from the identified user, the result confirmation unit 353 may be configured to accept input of information indicating the identity of the person to be authenticated from the person to be authenticated.

[0038] The result confirmation unit 353 may be configured to perform confirmation even when the face authentication unit 352 generates an authentication result indicating face authentication failure. Furthermore, as will be described later, when the determination unit 357 determines that a predetermined condition is satisfied, confirmation by the result confirmation unit 353 can be omitted.

[0039] The multi-step authentication unit 354 performs multi-step authentication by accepting input of encryption information such as a PIN from the person to be authenticated using the operation input unit 310. For example, the multi-step authentication unit 354 performs multi-step authentication when the result confirmation unit 353 determines that erroneous authentication has been performed based on the facial image of another person or when the face authentication unit 352 generates an authentication result indicating face authentication failure.

[0040] For example, the multi-step authentication unit 354 displays a message on the screen display unit 320 or the like indicating that it accepts input of encryption information, and accepts input of encryption information from the person to be authenticated using the operation input unit 310 or the like. Furthermore, upon accepting input of encryption information, the multi-step authentication unit 354 references the multi-step authentication information 342 to confirm whether the accepted encryption information is stored in the multi-step authentication information 342. If the accepted encryption information is stored in the multi-step authentication information 342, the multi-step authentication unit 354 generates an authentication result indicating successful multi-step authentication. If encryption information for each user is stored in the multi-step authentication information 342, the multi-step authentication unit 354 may generate an authentication result indicating successful multi-step authentication and identify the person to be authenticated who performed the multi-step authentication. On the other hand, if the accepted encryption information is not stored in the multi-step authentication information 342, the multi-step authentication unit 354 generates an authentication result indicating unsuccessful multi-step authentication. If the received encryption information is not stored in the multi-step authentication information 342, the multi-step authentication unit 354 may accept re-entry of encryption information up to a predetermined number of times.

[0041] Furthermore, when multi-step authentication is performed because the facial authentication unit 352 generates an authentication result indicating a facial authentication failure, if the received encryption information is stored in the multi-step authentication information 342, it is highly likely that the person to be authenticated is the user and facial authentication has failed. Therefore, in the above case, the multi-step authentication unit 354 can determine that an erroneous authentication has occurred, in which authentication of the person to be authenticated, whose facial image should have been stored in the authentication system 100, has failed. In this way, the multi-step authentication unit 354 can also be said to check whether an erroneous authentication has occurred by performing multi-step authentication, which is a process different from facial authentication, on the person to be authenticated.

[0042] The score storage unit 355 stores the score calculated by the face authentication unit 352 in the memory unit 340. The score storage unit 355 can store in the memory unit 340 types of scores according to the processing results of each processing unit of the face authentication unit 352, the result confirmation unit 353, and the multi-step authentication unit 354, such as a true person score, false authentication scores such as a false person acceptance score and a false person rejection score, and a false person score.

[0043] For example, when the face authentication unit 352 generates an authentication result indicating successful face authentication and the result confirmation unit 353 confirms that there is no problem, the score storage unit 355 can store a true person score or a false person score, which are scores equal to or greater than a threshold, in the memory unit 340. Furthermore, when the face authentication unit 352 generates an authentication result indicating successful face authentication and the result confirmation unit 353 confirms that the person is different, the score storage unit 355 can store a false person acceptance score or a false person score, which are incorrectly recognized scores, instead of the true person score. When the face authentication unit 352 generates an authentication result indicating successful face authentication and the result confirmation unit 353 confirms that the person is different, the score storage unit 355 may store a false person acceptance score or a false person score, provided that the multi-step authentication by the multi-step authentication unit 354 is successful. Furthermore, when the face authentication unit 352 generates an authentication result indicating unsuccessful face authentication and the multi-step authentication unit 354 generates an authentication result indicating successful multi-step authentication, the score storage unit 355 can store a true person rejection score or a false person score. If the face authentication unit 352 generates an authentication result indicating that face authentication has failed and the multi-step authentication unit 354 generates an authentication result indicating that multi-step authentication has failed, the score storage unit 355 may store the score in the memory unit 340 as a score for someone who is not a user of the authentication system 100, or may not store the score.

[0044] The score storage unit 355 may store an identity score, an erroneous authentication score, etc. for each user. The user can be identified, for example, by the face authentication unit 352 generating an authentication result indicating successful face authentication and the result confirmation unit 353 confirming that there are no problems, the result confirmation unit 353 accepting input of information for identifying the user, or by identifying the user through multi-step authentication. The authentication device 300 may also identify the user at a timing other than the above example, such as by reading an employee ID card at any timing. The score storage unit 355 may also store various scores for each imaging device 200.

[0045] To summarize the above, authentication processing and score storage processing are performed as shown in Figures 3 and 4. For example, as shown in Figure 3, when the face authentication unit 352 generates an authentication result indicating successful face authentication, confirmation is performed by the result confirmation unit 353. If the result of confirmation by the result confirmation unit 353 shows that there is no particular problem, an identity score, etc. are stored. On the other hand, when the result of confirmation by the result confirmation unit 353 shows that the authentication is incorrect, an identity tolerance score, etc. are stored. The identity tolerance score may be stored according to the result of multi-step authentication. Also, with reference to Figure 4, when the face authentication unit 352 generates an authentication result indicating unsuccessful face authentication, multi-step authentication is performed. If multi-step authentication is successful, an identity rejection score, etc. are stored. If multi-step authentication fails, it is not necessary to store the score, etc.

[0046] The threshold adjustment unit 356 adjusts the threshold, which is a value used when the face authentication unit 352 performs face authentication, based on the results stored in the score storage unit 355. In other words, the threshold adjustment unit 356 adjusts the threshold included in the threshold information 344 based on the distribution of false authentication scores included in the score information 343. For example, the threshold adjustment unit 356 can adjust the threshold for each user based on the distribution of scores for each user. The threshold adjustment unit 356 may also adjust the threshold in units stored in the score information 343. For example, the threshold adjustment unit 356 can determine whether to adjust the threshold by checking, at predetermined intervals, whether there are any false authentication scores stored since the adjustment. As an example, the threshold adjustment unit 356 may determine to adjust the threshold if there are any false authentication scores stored since the previous adjustment. The threshold adjustment unit 356 may also determine whether to adjust the threshold by checking whether a condition other than the above examples is met, such as whether the number of false authentication scores exceeds a predetermined number.

[0047] For example, the threshold adjustment unit 356 adjusts the threshold based on the distribution of the false authentication score, the true person score, etc., so that the false person tolerance score is as close to the threshold as possible. FIGS. 5 and 6 show an example of adjustment by the threshold adjustment unit 356. For example, in FIGS. 5 and 6, white circles indicate true person scores, black circles indicate false person tolerance scores, and check marks indicate false person scores. In the example shown in FIG. 5, false person tolerance scores having values ​​equal to or greater than the threshold exist before the threshold adjustment. Therefore, as shown in FIG. 6, the threshold adjustment unit 356 adjusts the threshold to increase the value so that the false person tolerance score is as close to the threshold as possible. In this case, as shown in FIG. 6, it is desirable that the threshold adjustment unit 356 adjusts the threshold so that the false person score remains above the threshold.

[0048] Furthermore, for example, the threshold adjustment unit 356 adjusts the threshold based on the distribution of the false authentication score, the true score, etc., so that the value of the false rejection score is as close to or greater than the threshold as possible. For example, in Figures 7 and 8, white circles indicate true scores, arc circles indicate false acceptance scores, and crosses indicate false scores. In the example shown in Figure 7, false rejection scores having values ​​below the threshold exist before the threshold adjustment. Therefore, as shown in Figure 8, the threshold adjustment unit 356 adjusts the threshold to lower it so that the value of the false rejection score is as close to or greater than the threshold as possible. In this case, as shown in Figure 8, it is desirable that the threshold adjustment unit 356 adjusts the threshold so that the value of the false rejection score does not exceed the threshold as much as possible.

[0049] For example, as described above, the threshold adjustment unit 356 adjusts the threshold based on the distribution of false authentication scores, such as the false acceptance score and the false rejection score, so as to reduce false authentications as much as possible. Note that during actual operation, the false rejection score and the false rejection score may both be included, or the false authentication score and each false authentication score may be mixed. The threshold adjustment unit 356 may adjust the threshold using any method, for example, by calculating the ratio of each score, so as to minimize false acceptance while minimizing false rejection. Furthermore, the threshold adjustment unit 356 may be preset with information, such as whether the false acceptance score or the false rejection score should be given more importance in the adjustment. In this case, the threshold adjustment unit 356 may perform the adjustment according to the set information.

[0050] The determination unit 357 determines, based on the adjustment status, whether or not to confirm the result by the result confirmation unit 353. For example, the determination unit 357 can make the above determination by checking whether or not a period during which the threshold adjustment unit 356 has not performed threshold adjustment satisfies a predetermined condition.

[0051] For example, if a predetermined condition is met, such as a period of time during which the threshold adjustment unit 356 has not adjusted the threshold being equal to or longer than a predetermined period, the determination unit 357 determines to omit the result confirmation by the result confirmation unit 353. On the other hand, if the condition is not met, the determination unit 357 determines to omit the result confirmation by the result confirmation unit 353. In this case, the result confirmation by the result confirmation unit 353 is performed.

[0052] The conditions used by the determination unit 357 when making a determination may be set arbitrarily. For example, the conditions may be that the threshold has not been adjusted for a predetermined period, that the number of adjustments within the predetermined period is equal to or less than a certain value, etc. The period during which no adjustments have been made and the number of adjustments may be set arbitrarily.

[0053] The above is an example of the configuration of authentication device 300. Note that authentication device 300 may have a configuration other than that illustrated in Fig. 2. For example, authentication device 300 may have an output unit that outputs information stored in storage unit 340, such as score information as illustrated in Figs. 5 to 8, to an external device or the like.

[0054] Next, an example of the operation of the authentication device 300 will be described with reference to Fig. 9 to Fig. 11. Fig. 9 is a flowchart showing an example of the operation when storing a score. Referring to Fig. 9, the face authentication unit 352 performs face authentication processing to check whether a face image of a person matching the person in the face image acquired by the imaging device 200 is stored in the storage unit 340, based on the face feature amount information 341 and the threshold information 344 (step S101).

[0055] If the facial authentication unit 352 generates an authentication result indicating successful facial authentication (Yes in step S102), the result confirmation unit 353 asks the person to be authenticated whether there is an error in the authentication by the facial authentication unit 352 (step S103). If the result confirmation unit 353 confirms that there is no problem (Yes in step S104), the result confirmation unit 353 can determine whether to omit multi-step authentication. In this case, the score storage unit 355 stores the person's score, etc. in the memory unit 340 (step S105). On the other hand, if the result confirmation unit 353 confirms that the person to be authenticated is different from the identified user (No in step S104), the result confirmation unit 353 determines that erroneous authentication has occurred based on a facial image of another person. In this case, the score storage unit 355 stores the other person tolerance score, etc. (step S106). Furthermore, the multi-step authentication unit 354 performs multi-step authentication (step S107). The stranger tolerance score may be stored according to the result of multi-step authentication by the multi-step authentication unit 354 .

[0056] Furthermore, if the face authentication unit 352 generates an authentication result indicating face authentication failure (step S102, No), the multi-step authentication unit 354 performs multi-step authentication (step S108). If the multi-step authentication unit 354 generates an authentication result indicating multi-step authentication success (step S109, Yes), it is highly likely that the person to be authenticated is the user and face authentication has failed. Therefore, the multi-step authentication unit 354 determines that an erroneous authentication has occurred, in which authentication of a user whose face image should be stored in the authentication system 100 has failed. In this case, the score storage unit 355 stores the false rejection score, etc., in the memory unit 340 (step S110). On the other hand, if the multi-step authentication unit 354 generates an authentication result indicating multi-step authentication failure (step S109, No), for example, the authentication device 300 terminates processing.

[0057] The above is an example of the operation when storing the score. Next, an example of the operation when adjusting the threshold value will be described with reference to FIG.

[0058] Fig. 10 shows an example of the operation of the authentication device 300 when adjusting the threshold value. Note that the operation shown in Fig. 10 may be performed periodically at predetermined intervals, or may be performed when a predetermined condition is met, such as when the number of newly stored erroneous authentication scores exceeds a predetermined value.

[0059] Referring to FIG. 10, the threshold adjustment unit 356 checks the score information 343 and determines whether or not to adjust the threshold (step S201).

[0060] When adjusting the threshold, the threshold adjustment unit 356 adjusts the threshold, which is a value used when the face authentication unit 352 performs face authentication, based on the result stored in the score storage unit 355 (step S202). For example, the threshold adjustment unit 356 adjusts the threshold based on an erroneous authentication score such as a false acceptance score or a false rejection score so as to reduce false authentication as much as possible. In other words, the threshold adjustment unit 356 adjusts the threshold so as to minimize false rejection while maximizing false acceptance.

[0061] The above is an example of the operation when adjusting the threshold value. Next, an example of the operation when the result confirmation unit 353 determines whether or not to confirm the result will be described with reference to FIG.

[0062] 11 is a flowchart showing an example of an operation performed when determining whether or not to confirm the result by the result confirmation unit 353. Referring to Fig. 11, the determination unit 357 checks whether or not a period during which the threshold adjustment unit 356 has not performed threshold adjustment satisfies a predetermined condition (step S301).

[0063] If a predetermined condition is satisfied, such as the period during which the threshold adjustment unit 356 has not adjusted the threshold being equal to or longer than a predetermined period (Yes in step S301), the determination unit 357 determines to omit the result confirmation by the result confirmation unit 353 (step S302). On the other hand, if the condition is not satisfied (No in step S301), the determination unit 357 determines to omit the result confirmation by the result confirmation unit 353. In this case, the result confirmation by the result confirmation unit 353 is performed.

[0064] The above is an example of the operation when the result confirmation unit 353 determines whether or not to confirm the result.

[0065] As described above, the authentication device 300 includes the score storage unit 355 and the threshold adjustment unit 356. With this configuration, the threshold adjustment unit 356 can adjust the threshold based on the erroneous authentication score stored in the score storage unit 355. As a result, the threshold can be appropriately adjusted to reduce the possibility of erroneous authentication as much as possible. Furthermore, the score storage unit 355 is configured to store each score for each user. This allows the threshold adjustment unit 356 to adjust the threshold for each user. As a result, the threshold can be adjusted more appropriately.

[0066] Furthermore, the authentication device 300 has a result confirmation unit 353 and a multi-step authentication unit 354. With this configuration, the score storage unit 355 can store an erroneous authentication score in the memory unit 340 when it is determined that there is a possibility of an erroneous authentication as a result of processing by the result confirmation unit 353 or the multi-step authentication unit 354. As a result, the threshold adjustment unit 356 can more appropriately adjust the threshold based on the erroneous authentication score stored in the score storage unit 355, etc.

[0067] The authentication device 300 also includes a determination unit 357. With this configuration, the determination unit 357 can determine whether to omit confirmation by the result confirmation unit 353 when a predetermined condition is satisfied. As a result, it becomes possible to omit confirmation of the result when it can be determined that the threshold has been adjusted to an appropriate value.

[0068] Note that the configurations of the imaging device 200 and the authentication device 300 may be other than those exemplified in this embodiment. For example, the imaging device 200 may have at least a part of the configuration of the authentication device 300 exemplified in this embodiment. Similarly, the authentication device 300 may have the functions of the imaging device 200.

[0069] Second Embodiment Next, a second embodiment of the present disclosure will be described with reference to Fig. 12 and Fig. 13. In the second embodiment of the present disclosure, an overview of the configuration of a processing device 400 that is an information processing device will be described.

[0070] Fig. 12 shows an example of the hardware configuration of the processing device 400. Referring to Fig. 12, the processing device 400 has the following hardware configuration, as an example: CPU (Central Processing Unit) 401 (arithmetic device); ROM (Read Only Memory) 402 (storage device); RAM (Random Access Memory) 403 (storage device); programs 404 loaded into RAM 403; a storage device 405 that stores the programs 404; a drive device 406 that reads and writes from a storage medium 410 outside the information processing device; a communication interface 407 that connects to a communication network 411 outside the information processing device; an input / output interface 408 that inputs and outputs data; and a bus 409 that connects the various components.

[0071] 13 by the CPU 401 acquiring and executing the program group 404. The program group 404 is stored in advance in the storage device 405 or the ROM 402, for example, and is loaded into the RAM 403 or the like by the CPU 401 for execution as needed. The program group 404 may be supplied to the CPU 401 via the communication network 411, or may be stored in advance in the recording medium 410, and the drive device 406 may read out the program and supply it to the CPU 401.

[0072] 12 shows an example of the hardware configuration of the processing device 400. The hardware configuration of the processing device 400 is not limited to the above-described case. For example, the processing device 400 may be configured with only a part of the above-described configuration, such as excluding the drive device 406.

[0073] The storage unit 421 stores in a storage device an erroneous authentication score, which is a score calculated when it is determined that an erroneous authentication has occurred in face authentication.

[0074] The adjustment unit 422 adjusts the value used when performing face authentication based on the erroneous authentication score.

[0075] As described above, the processing device 400 includes the storage unit 421 and the adjustment unit 422. With this configuration, the adjustment unit 422 can adjust the value used when performing face authentication based on the erroneous authentication score. As a result, appropriate adjustment can be performed.

[0076] Note that an information processing device such as the above-described processing device 400 can be realized by incorporating a predetermined program into the information processing device. Specifically, the program according to another aspect of the present invention is a program for realizing a process in which an information processing device stores, in a storage device, an erroneous authentication score, which is a score calculated when it is determined that an erroneous authentication has occurred in face authentication, and adjusts a value used when performing face authentication based on the erroneous authentication score.

[0077] In addition, the processing method executed by the above-mentioned information processing device is such that the information processing device stores an error authentication score, which is a score calculated when it is determined that an error authentication has occurred in facial authentication, in a storage device, and adjusts a value used when performing facial authentication based on the error authentication score.

[0078] Even if the invention has the above-described configuration, such as a program (or recording medium) or a processing method, it can achieve the above-described object of the present invention because it has the same action and effect as the above-described case.

[0079] <Supplementary Notes> Part or all of the above-described embodiments can be described as follows: The processing apparatus and the like according to the present invention will be outlined below. However, the present invention is not limited to the following configuration.

[0080] (Supplementary Note 1) A processing device comprising: a storage unit that stores an erroneous authentication score, which is a score calculated when it is determined that an erroneous authentication has occurred in face recognition, in a storage device; and an adjustment unit that adjusts a value used when performing face recognition based on the erroneous authentication score. (Supplementary Note 2) The processing device according to Supplementary Note 1, further comprising: a confirmation unit that confirms whether or not an erroneous authentication has occurred by performing a confirmation different from face recognition on a person to be authenticated in face recognition, and the storage unit stores the erroneous authentication score in accordance with a result of the confirmation by the confirmation unit. (Supplementary Note 3) The processing device according to Supplementary Note 2, wherein the confirmation unit confirms whether or not an erroneous authentication has occurred by confirming whether or not a person identified by face recognition is the person to be authenticated, and the storage unit stores the erroneous authentication score in accordance with a result of the confirmation by the confirmation unit. (Supplementary Note 4) The processing device according to Supplementary Note 3, wherein the storage unit stores, as the erroneous authentication score, a stranger tolerance score that is a score calculated when an erroneous authentication has occurred based on a facial image of another person, and the adjustment unit adjusts a threshold value used when performing face recognition based on the stranger tolerance score. (Supplementary Note 5) The processing device according to Supplementary Note 3, wherein the confirmation unit confirms whether or not a person identified by facial authentication is a person to be authenticated when it is determined that authentication is successful in facial authentication. (Supplementary Note 6) The processing device according to Supplementary Note 3, further comprising a determination unit that determines whether or not to perform confirmation by the confirmation unit based on a predetermined condition, and the confirmation unit performs confirmation according to a determination result of the determination unit. (Supplementary Note 7) The processing device according to Supplementary Note 2, wherein the confirmation unit confirms whether or not an erroneous authentication has occurred by accepting input of predetermined encryption information from the person to be authenticated, and the storage unit stores the erroneous authentication score according to a result of the confirmation by the confirmation unit. (Supplementary Note 8) The processing device according to Supplementary Note 7, wherein the storage unit stores, as the erroneous authentication score, a false rejection score that is a score calculated when it is determined that authentication of a person to be authenticated has failed, and the adjustment unit adjusts a threshold used when performing facial authentication based on the false rejection score.(Supplementary Note 9) A processing method in which an information processing device stores in a storage device an error recognition score, which is a score calculated when it is determined that an error recognition has occurred in face recognition, and adjusts a value used when performing face recognition based on the error recognition score. (Supplementary Note 10) A computer-readable recording medium having recorded thereon a program for implementing a process in which an information processing device stores in a storage device an error recognition score, which is a score calculated when it is determined that an error recognition has occurred in face recognition, and adjusts a value used when performing face recognition based on the error recognition score.

[0081] The programs described in the above embodiments and appendices may be stored in a storage device or a computer-readable recording medium, such as a portable medium such as a flexible disk, an optical disk, a magneto-optical disk, or a semiconductor memory.

[0082] Although the present invention has been described above with reference to the above-mentioned embodiments, the present invention is not limited to the above-mentioned embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0083] In addition, the present invention claims the benefit of priority based on the patent application of Japanese Patent Application No. 2022-161038 filed on October 5, 2022 in Japan, and all contents described in the patent application are included in this specification.

[0084] 100 Authentication system 200 Imaging device 300 Authentication device 310 Operation input unit 320 Screen display unit 330 Communication I / F unit 340 Storage unit 341 Facial feature amount information 342 Multi-step authentication information 343 Score information 344 Threshold information 345 Program 350 Arithmetic processing unit 351 Facial image acquisition unit 352 Facial authentication unit 353 Result confirmation unit 354 Multi-step authentication unit 355 Score storage unit 356 Threshold adjustment unit 357 Determination unit 400 Processing device 401 CPU 402 ROM 403 RAM 404 Program group 405 Storage device 406 Drive device 407 Communication interface 408 Input / output interface 409 Bus 410 Recording medium 411 Communication network 421 Storage unit 422 Adjustment part

Claims

1. a storage unit that stores in a storage device an erroneous recognition score, which is a score calculated when it is determined that an erroneous recognition has occurred in face recognition; an adjustment unit that adjusts a value used when performing face authentication based on the false authentication score; have Processing unit.

2. 2. The processing device according to claim 1, A confirmation unit that confirms whether or not an erroneous authentication has occurred by performing a confirmation different from the face authentication on a person to be authenticated by the face authentication, The storage unit stores the false authentication score according to a result of the confirmation by the confirmation unit. Processing unit.

3. 3. The processing device according to claim 2, The confirmation unit confirms whether a person identified by face recognition is a person to be authenticated, thereby confirming whether an erroneous authentication has occurred; The storage unit stores the false authentication score according to a result of the confirmation by the confirmation unit. Processing unit.

4. 4. The processing device according to claim 3, the storage unit stores, as the erroneous authentication score, a stranger tolerance score which is a score calculated when an erroneous authentication based on a facial image of another person is performed; The adjustment unit adjusts a threshold used when performing face authentication based on the other person tolerance score. Processing unit.

5. 4. The processing device according to claim 3, The confirmation unit confirms whether or not a person specified by face authentication is a person to be authenticated when it is determined that authentication is successful in face authentication. Processing unit.

6. 4. The processing device according to claim 3, A determination unit that determines whether or not to perform a check by the check unit based on a predetermined condition, The confirmation unit performs confirmation depending on the determination result of the determination unit. Processing unit.

7. 3. The processing device according to claim 2, the confirmation unit confirms whether or not an authentication error has occurred by receiving an input of predetermined encryption information from a person to be authenticated; The storage unit stores the false authentication score according to a result of the confirmation by the confirmation unit. Processing unit.

8. 8. The processing device according to claim 7, the storage unit stores, as the false authentication score, a false rejection score which is a score calculated when it is determined that authentication of a person to be authenticated has failed; The adjustment unit adjusts a threshold used when performing face authentication based on the false rejection score. Processing unit.

9. An information processing device, storing a misrecognition score, which is a score calculated when it is determined that a misrecognition has occurred in face recognition, in a storage device; Adjusting a value used when performing face recognition based on the false recognition score Processing methods.

10. In the information processing device, storing a misrecognition score, which is a score calculated when it is determined that a misrecognition has occurred in face recognition, in a storage device; Adjusting a value used when performing face recognition based on the false recognition score A program for implementing processing.