Classifications

• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
  • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
  • G06F21/31—User authentication
  • G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints

Definitions

• This disclosure relates to the technical fields of authentication devices, authentication methods, and recording media.
• Patent Document 1 For example, a system has been proposed that generates funds transfer data for a designated account if identity verification, which involves comparing reference facial image feature point data with authentication facial image feature point data, is successful (see Patent Document 1).
• Other prior art documents related to this disclosure include Patent Documents 2 to 5.
• the objective of this disclosure is to provide an authentication device, authentication method, and recording medium that aim to improve upon the technology described in prior art documents.
• One aspect of the authentication device includes a feature calculation unit that calculates a general feature that is a feature related to a general feature of the person to be authenticated and a unique feature that is a feature related to a unique feature of the person to be authenticated; a score calculation unit that calculates a first matching score obtained by matching the general feature of the person to be authenticated with the general feature of a registrant and a second matching score obtained by matching the unique feature of the person to be authenticated with the unique feature of the registrant; and a determination unit that determines whether the person to be authenticated is the registrant based on the first matching score and the second matching score, and the determination unit determines that the person to be authenticated is not the registrant when at least one of a first result indicating whether the person to be authenticated is the registrant based on the first matching score and a second result indicating whether the person to be authenticated is the registrant based on the second matching score indicates that the person to be authenticated is not the registrant.
• Another aspect of the authentication device includes a feature calculation unit that calculates general features, which are features related to the general features of the person to be authenticated, and unique features, which are features related to the unique features of the person to be authenticated; a score calculation unit that calculates an integrated score by integrating a first matching score obtained by matching the general features of the person to be authenticated with the general features of a registrant, and a second matching score obtained by matching the unique features of the person to be authenticated with the unique features of the registrant; and a determination unit that determines whether the person to be authenticated is the registrant by comparing the integrated score with a decision boundary for determining whether the person to be authenticated is the registrant, the decision boundary being set so that the range of the integrated score in which the person to be authenticated is determined to be the registrant is smaller than the range of the integrated score in which the person to be authenticated is determined to be not the registrant.
• One aspect of the authentication method is to calculate general features which are features related to the general features of the person to be authenticated and unique features which are features related to the unique features of the person to be authenticated, calculate a first matching score obtained by matching the general features of the person to be authenticated with the general features of the registrant, and calculate a second matching score obtained by matching the unique features of the person to be authenticated with the unique features of the registrant, determine whether the person to be authenticated is the registrant based on the first matching score and the second matching score, and determine that the person to be authenticated is not the registrant if at least one of the first result indicating whether the person to be authenticated is the registrant based on the first matching score and the second result indicating whether the person to be authenticated is the registrant based on the second matching score indicates that the person to be authenticated is not the registrant.
• Another aspect of the authentication method is an authentication method that calculates general features, which are features related to the general features of the person to be authenticated, and unique features, which are features related to the unique features of the person to be authenticated, calculates an integrated score by combining a first matching score obtained by matching the general features of the person to be authenticated with the general features of the registrant, and a second matching score obtained by matching the unique features of the person to be authenticated with the unique features of the registrant, and compares the integrated score with a decision boundary for determining whether the person to be authenticated is the registrant, and the decision boundary is set so that the range of integrated scores in which the person to be authenticated is determined to be the registrant is smaller than the range of integrated scores in which the person to be authenticated is determined to be not the registrant.
• a computer program is recorded to cause a computer to execute an authentication method that calculates general features that are features related to the general features of the person to be authenticated and unique features that are features related to the unique features of the person to be authenticated, calculates a first matching score obtained by matching the general features of the person to be authenticated with the general features of a registrant and a second matching score obtained by matching the unique features of the person to be authenticated with the unique features of the registrant, determines whether the person to be authenticated is the registrant based on the first matching score and the second matching score, and determines that the person to be authenticated is not the registrant when at least one of a first result indicating whether the person to be authenticated is the registrant based on the first matching score and a second result indicating whether the person to be authenticated is the registrant based on the second matching score indicates that the person to be authenticated is not the registrant.
• Another aspect of the recording medium is an authentication method that determines whether the authenticated person is the registrant by calculating general features, which are features related to the general features of the authenticated person, and unique features, which are features related to the unique features of the authenticated person, calculating an integrated score by integrating a first matching score obtained by matching the general features of the authenticated person with the general features of the registrant, and a second matching score obtained by matching the unique features of the authenticated person with the unique features of the registrant, and comparing the integrated score with a decision boundary for determining whether the authenticated person is the registrant, wherein the decision boundary is set so that the range of the integrated score in which the authenticated person is determined to be the registrant is smaller than the range of the integrated score in which the authenticated person is determined to be not the registrant.
• FIG. 2 is a block diagram showing an example of a configuration of an authentication device.
• FIG. 13 is a block diagram showing another example of the configuration of the authentication device. 2 is a block diagram showing an example of a configuration of an authentication unit;
• FIG. 13 is a diagram showing an example of a screen presented to a user.
• This section describes embodiments of an authentication device, authentication method, and recording medium.
• FIG. 1 A first embodiment of an authentication device, an authentication method, and a recording medium will be described with reference to Fig. 1. In the following, the first embodiment of the authentication device, the authentication method, and a recording medium will be described using an authentication device 1.
• the authentication device 1 includes a feature calculation unit 11, a score calculation unit 12, and a determination unit 13.
• the authentication device 1 determines whether or not the person to be authenticated is a registered person (in other words, whether or not the person is the person in question).
• the feature calculation unit 11 calculates general features, which are features related to the general features of the person to be authenticated.
• General features refer to features common to multiple people to be authenticated.
• face recognition for example, the eyes, nose, mouth, etc. correspond to general features.
• unique features which are features related to the unique features of the person to be authenticated.
• Unique features refer to features unique to a certain person to be authenticated. In face recognition, for example, wrinkles, scars, moles, etc. correspond to unique features.
• the score calculation unit 12 calculates a first matching score obtained by matching the general features of the person to be authenticated with the general features of the registered person.
• the score calculation unit 12 calculates a second matching score obtained by matching the unique features of the person to be authenticated with the unique features of the registered person. Note that various existing methods can be applied to the calculation method of the first matching score and the second matching score, so detailed explanations are omitted.
• the determination unit 13 determines whether the person to be authenticated is a registrant based on the first matching score and the second matching score. Specifically, the determination unit 13 may determine whether the person to be authenticated is a registrant based on the first matching score. The determination unit 13 may determine whether the person to be authenticated is a registrant based on the second matching score. Then, if at least one of the first result indicating whether the person to be authenticated is a registrant based on the first matching score and the second result indicating whether the person to be authenticated is a registrant based on the second matching score indicates that the person to be authenticated is not a registrant, the determination unit 13 determines that the person to be authenticated is not a registrant. In other words, if the first result and the second result indicate that the person to be authenticated is a registrant, the determination unit 13 determines that the person to be authenticated is a registrant.
• the judgment unit 13 judges that the person to be authenticated is not a registrant. In other words, if both the first judgment result and the second judgment result indicate that the person to be authenticated is a registrant (in other words, an acceptance judgment), the judgment unit 13 judges that the person to be authenticated is a registrant. In this way, in this embodiment, by prioritizing rejection judgments over acceptance judgments, it is possible to improve authentication accuracy while compensating for the disadvantage of unique features, which are easily affected by changes over time.
• Such an authentication device 1 may be realized, for example, by a computer reading a computer program recorded on a recording medium.
• the recording medium may be recorded with a computer program for causing a computer to execute an authentication method that calculates general features that are features related to the general features of the person to be authenticated and specific features that are features related to the specific features of the person to be authenticated, calculates a first matching score obtained by matching the general features of the person to be authenticated with the general features of the registrant and a second matching score obtained by matching the specific features of the person to be authenticated with the registrant, determines whether the person to be authenticated is a registrant based on the first matching score and the second matching score, and determines that the person to be authenticated is not a registrant when at least one of the first result indicating whether the person to be authenticated is a registrant based on the first matching score and the second result indicating whether the person to be authenticated is a registrant based on the second matching score indicates that the person to be authentic
• Second Embodiment A second embodiment of the authentication device, authentication method, and recording medium will be described with reference to Fig. 1. In the following, the second embodiment of the authentication device, authentication method, and recording medium will be described using an authentication device 1.
• the authentication device 1 includes a feature calculation unit 11, a score calculation unit 12, and a determination unit 13.
• the authentication device 1 determines whether or not the person to be authenticated is a registered person (in other words, whether or not the person is the person in question).
• the feature calculation unit 11 calculates general features, which are features related to the general features of the person to be authenticated.
• the feature calculation unit 11 calculates unique features, which are features related to the unique features of the person to be authenticated.
• the score calculation unit 12 calculates a first matching score obtained by matching the general features of the person to be authenticated with the general features of the registered person.
• the score calculation unit 12 calculates a second matching score obtained by matching the unique features of the person to be authenticated with the unique features of the registered person. Note that various existing aspects can be applied to the calculation method of the first matching score and the second matching score, so detailed explanations are omitted.
• the score calculation unit 12 calculates an integrated score by combining the first matching score and the second matching score.
• the score calculation unit 12 may, for example, calculate the average value of the first matching score and the second matching score as the integrated score.
• the score calculation unit 12 may, for example, calculate the mean square root of the first matching score and the second matching score as the integrated score. Note that the method of calculating the integrated score is not limited to these. Various existing methods can be applied to the method of calculating the integrated score.
• the determination unit 13 determines whether the person to be authenticated is a registrant by comparing the integrated score with a decision boundary for determining whether the person to be authenticated is a registrant.
• the decision boundary is set so that the range of integrated scores in which the person to be authenticated is determined to be a registrant is smaller than the range of integrated scores in which the person to be authenticated is determined to be not a registrant.
• the decision boundary may be expressed by a function with the first score and the second score as variables.
• one or more coefficients included in the function may be set so that the range of integrated scores in which the person to be authenticated is determined to be a registrant is smaller than the range of integrated scores in which the person to be authenticated is determined to be not a registrant.
• the determination unit 13 determines that the person to be authenticated is not a registrant. In other words, if both the first matching score and the second matching score on which the integrated score is based are relatively high, the determination unit 13 determines that the person to be authenticated is a registrant. According to the second embodiment, as in the first embodiment described above, it is possible to improve authentication accuracy while compensating for the drawback of the inherent characteristic of being susceptible to changes over time.
• Such an authentication device 1 may be realized, for example, by a computer reading a computer program recorded on a recording medium.
• the recording medium may be recorded with a computer program for causing a computer to execute an authentication method that calculates general features, which are features related to the general features of the person to be authenticated, and unique features, which are features related to the unique features of the person to be authenticated, calculates an integrated score by integrating a first matching score obtained by matching the general features of the person to be authenticated with the general features of the registrant, and a second matching score obtained by matching the unique features of the person to be authenticated with the unique features of the registrant, and compares the integrated score with a decision boundary for determining whether the person to be authenticated is a registrant, the decision boundary being set so that the range of the integrated score in which the person to be authenticated is determined to be a registrant is smaller than the range of the integrated score in which the person to be authenticated is determined to be not a registrant.
• a third embodiment of the authentication device, authentication method, and recording medium will be described with reference to Fig. 2 and Fig. 3. In the following, the third embodiment of the authentication device, authentication method, and recording medium will be described using the authentication device 2.
• the authentication device 2 includes a calculation device 21, a storage device 22, and a communication device 23.
• the authentication device 2 may include an input device 24 and an output device 25.
• the authentication device 2 does not have to include at least one of the input device 24 and the output device 25.
• the calculation device 21, the storage device 22, the communication device 23, the input device 24, and the output device 25 may be connected via a data bus 26.
• the computing device 21 may include, for example, at least one of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), a TPU (Tensor Processing Unit), and a quantum processor.
• a CPU Central Processing Unit
• GPU Graphics Processing Unit
• FPGA Field Programmable Gate Array
• TPU Torsor Processing Unit
• quantum processor a quantum processor
• the storage device 22 may include, for example, at least one of a RAM (Random Access Memory), a ROM (Read Only Memory), a hard disk device, an optical magnetic disk device, an SSD (Solid State Drive), and an optical disk array.
• the storage device 22 may include a non-transient recording medium.
• the storage device 22 is capable of storing desired data.
• the storage device 22 may temporarily store a computer program executed by the arithmetic device 21.
• the storage device 22 may temporarily store data that is temporarily used by the arithmetic device 21 when the arithmetic device 21 is executing a computer program.
• the communication device 23 may be capable of communicating with devices external to the authentication device 2 via a network (not shown).
• the communication device 23 may perform wired communication or wireless communication.
• the input device 24 is a device capable of accepting information input to the authentication device 2 from the outside.
• the input device 24 may include an operating device (e.g., a keyboard, a mouse, a touch panel, etc.) that can be operated by an operator of the authentication device 2.
• the input device 24 may include a recording medium reading device that can read information recorded on a recording medium that is detachable from the authentication device 2, such as a USB (Universal Serial Bus) memory.
• the communication device 23 may function as an input device.
• the output device 25 is a device capable of outputting information to the outside of the authentication device 2.
• the output device 25 may output visual information such as characters and images, auditory information such as voice, or tactile information such as vibration as the above information.
• the output device 25 may include at least one of a display, a speaker, a printer, and a vibration motor, for example.
• the output device 25 may be capable of outputting information to a recording medium that is detachable from the authentication device 2, such as a USB memory. Note that when the authentication device 2 outputs information via the communication device 23, the communication device 23 may function as an output device.
• the computing device 21 may have the authentication unit 210 as a logically realized functional block or as a physically realized processing circuit.
• the authentication unit 210 may be realized in a form that combines a logical functional block and a physical processing circuit (i.e., hardware). When at least a part of the authentication unit 210 is a functional block, at least a part of the authentication unit 210 may be realized by the computing device 21 executing a specified computer program.
• the calculation device 21 may obtain (in other words, read) the above-mentioned specific computer program from the storage device 22.
• the calculation device 21 may read the above-mentioned specific computer program stored in a computer-readable and non-transient recording medium using a recording medium reading device (not shown) provided in the authentication device 2.
• the calculation device 21 may obtain (in other words, download or read) the above-mentioned specific computer program from a device (not shown) external to the authentication device 2 via the communication device 23.
• the recording medium for recording the above-mentioned specific computer program executed by the calculation device 21 may be at least one of an optical disk, a magnetic medium, a magneto-optical disk, a semiconductor memory, and any other medium capable of storing a program.
• the authentication unit 210 has a general authentication unit 211, a unique authentication unit 212, a reference threshold determination unit 213, and a judgment unit 214.
• the general authentication unit 211 has a feature calculation unit 2111, a score calculation unit 2112, and a judgment unit 2113.
• the unique authentication unit 212 has a feature calculation unit 2121, a score calculation unit 2122, a judgment unit 2123, an attribute input unit 2124, a threshold estimation unit 2125, and a score memory unit 2126.
• the reference threshold determination unit 213 has a threshold determination information output unit 2131, a reference threshold input unit 2132, an authentication accuracy memory unit 2133, and a reference threshold memory unit 2134.
• the authentication unit 210 performs facial authentication of the person to be authenticated.
• the general authentication unit 211 performs matching based on the positions and sizes of the person to be authenticated, such as the eyes, nose, and mouth, as part of the facial authentication.
• the unique authentication unit 212 performs matching based on the positions and sizes of the person to be authenticated, such as wrinkles, scars, moles, etc., as another part of the facial authentication.
• wrinkles, scars, moles, etc. as another part of the facial authentication.
• the authentication unit 210 may acquire a facial image IM of the person to be authenticated. If the authentication device 2 is equipped with a camera capable of capturing an image of the person to be authenticated, the camera of the authentication device 2 may capture an image of the person to be authenticated, thereby generating a facial image IM of the person to be authenticated.
• the person to be authenticated may be captured by a camera that is a device different from the authentication device 2. In this case, the authentication device 2 may acquire, via the communication device 23 or the input device 24, the facial image IM of the person to be authenticated, which is generated by the camera capturing an image of the person to be authenticated.
• the feature calculation unit 2111 of the general authentication unit 211 calculates general features, which are features of the general features of the person to be authenticated, contained in the face image IM.
• the score calculation unit 2112 compares the general features of the person to be authenticated with the general features of the registrant to calculate a first comparison score.
• the general features of the registrant and the unique features of the registrant may be stored in the storage device 22 of the authentication device 2. Alternatively, the general features and unique features of the registrant may be stored in a device other than the authentication device 2. In this case, the authentication device 2 may acquire the general features and unique features of the registrant from the other device via the communication device 23.
• the determination unit 2113 compares the first matching score with the first threshold. If the first matching score is higher than the first threshold, the determination unit 2113 determines that the person to be authenticated is a registrant. On the other hand, if the first matching score is lower than the first threshold, the determination unit 2113 determines that the person to be authenticated is not a registrant. Note that if the first matching score and the first threshold are equal, it is sufficient to treat either case as including them.
• the determination unit 2113 outputs first determination result information indicating the determination result to the determination unit 214.
• the feature calculation unit 2121 of the unique authentication unit 212 calculates a unique feature, which is a feature of the unique feature of the person to be authenticated, contained in the face image IM.
• the score calculation unit 2122 compares the unique feature of the person to be authenticated with the unique feature of the registrant to calculate a second matching score.
• the determination unit 2123 compares the second matching score with a second threshold. If the second matching score is higher than the second threshold, the determination unit 2123 determines that the person to be authenticated is a registrant. On the other hand, if the second matching score is lower than the second threshold, the determination unit 2123 determines that the person to be authenticated is not a registrant. Note that if the second matching score and the second threshold are equal, it is sufficient to treat them as including either case.
• the determination unit 2123 outputs second determination result information indicating the determination result to the determination unit 214.
• the second threshold is estimated by the threshold estimation unit 2125.
• the threshold estimation unit 2125 estimates the second threshold based on the attribute information input by the attribute input unit 2124, the information stored in the score storage unit 2126, and the reference threshold determined by the reference threshold determination unit 213.
• the score storage unit 2126 stores (or accumulates) the second matching score and attribute information from past face authentication as the above information.
• Attribute information refers to information about factors that affect face recognition (particularly the processing in the unique authentication unit 212). Attribute information may include, for example, information about age, facial direction, whether makeup is worn, whether a mask is worn, whether glasses are worn, whether sunglasses are worn, lighting conditions, image resolution, whether the image is out of focus, whether the image is blurred, etc. Attribute information may also include information about at least one of race, sex, and region. Note that lighting conditions are not limited to conditions related to the light source, such as the wavelength of light and the direction of light irradiation, but may also include conditions related to time.
• the attribute input unit 2124 may acquire at least a part of the attribute information based on the facial image IM. For example, the attribute input unit 2124 may acquire at least a part of the attribute information by performing image processing on the facial image IM. The attribute input unit 2124 may acquire at least a part of the attribute information using a calculation model that outputs attribute information when the facial image IM is input. The attribute input unit 2124 may acquire the attribute information based on information input by a user of the authentication device 2. The attribute input unit 2124 inputs the acquired attribute information to the threshold estimation unit 2125. Note that the above user is an operator or administrator of the authentication device 2, and is a person different from the person to be authenticated.
• the authentication accuracy storage unit 2133 of the reference threshold determination unit 213 stores information related to the authentication accuracy of face authentication.
• the authentication accuracy storage unit 2133 may store a TAR (True Acceptance Rate), a FAR (False Acceptance Rate), and a threshold value in correspondence with each other.
• the TAR is the probability of authenticating a registered person as a registered person.
• the FAR is the probability of authenticating an unregistered person as a registered person. For this reason, the TAR and FAR can be said to be information indicating authentication accuracy or matching accuracy.
• TAR related to general features in other words, a TAR related to the general authentication unit 211
• TAR related to unique features in other words, a TAR related to the unique authentication unit 212
• FAR related to general features in other words, a FAR related to the general authentication unit 211
• FAR related to unique features in other words, a FAR related to the unique authentication unit 212
• the threshold determination information output unit 2131 outputs information for the user of the authentication device 2 to determine a threshold based on information related to the authentication accuracy of face authentication stored in the authentication accuracy storage unit 2133. In this case, the threshold determination information output unit 2131 may control the output device 25 to output information for the user to determine a threshold. As a result, for example, a screen shown in FIG. 4 may be presented to the user. Note that the output device 25 may be referred to as a presentation unit, since it presents the screen shown in FIG. 4 to the user.
• the TAR (overall) when the threshold is "0", the TAR (overall) is "99.9%” and the FAR (overall) is "1%". In this case, it is shown that the probability of authenticating a registrant as a registrant is 99.9%, and the probability of authenticating an unregistered person as a registrant is 1%.
• the threshold increases, both the TAR (overall) and the FAR (overall) decrease.
• a decrease in the TAR (overall) is, for example, synonymous with a decrease in convenience for registrants.
• a decrease in the FAR (overall) is, for example, synonymous with an increase in security.
• the user of the authentication device 2 may determine the threshold by taking into consideration the balance between convenience for registrants and security.
• the user inputs the determined threshold value via the input device 24 of the authentication device 2.
• the reference threshold input unit 2132 inputs (or registers) the threshold value input via the input device 24 as the reference threshold value in the reference threshold storage unit 2134.
• the threshold estimation unit 2125 acquires a TAR (unique feature) associated with a threshold corresponding to the reference threshold from the authentication accuracy storage unit 2133 based on the reference threshold stored in the reference threshold storage unit 2134.
• the threshold estimation unit 2125 estimates the second threshold by solving a cumulative density function for the second threshold based on the TAR (unique feature), the attribute information input by the attribute input unit 2124, and the second matching score and attribute information at the time of past face authentication stored in the score storage unit 2126.
• the cumulative density function may be expressed as, for example, "F(Sth
• a) 1-TAR(unique feature)".
• “Sth" is the second threshold and "a" is the attribute information.
• the second threshold estimated in this way is a threshold that can realize the TAR (unique feature).
• the threshold estimation unit 2125 estimates a threshold that can realize TAR (unique feature) as the second threshold.
• the threshold estimation unit 2125 estimating the second threshold is synonymous with setting the second threshold. For this reason, the threshold estimation unit 2125 may be referred to as a setting unit.
• the determination unit 214 determines whether or not the person to be authenticated is a registrant based on the first determination result information (i.e., information indicating the determination result of the determination unit 2113 of the general authentication unit 211) and the second determination result information (i.e., information indicating the determination result of the determination unit 2123 of the unique authentication unit 212).
• the determination unit 214 determines that the person to be authenticated is a registrant.
• the determination unit 214 determines that the person to be authenticated is not a registrant.
• the unique features of the person to be authenticated are easily affected by changes in attributes and aging. If the unique features are affected by changes in attributes and aging, the possibility that the person to be authenticated will not be authenticated as a registered person increases, even though he or she is a registered person. In other words, the TAR (overall) decreases.
• the threshold estimation unit 2125 estimates (or determines) the second threshold based on attribute information, etc.
• the second threshold estimated by the threshold estimation unit 2125 is a threshold that can realize the TAR (unique feature) associated with the reference threshold determined by the user. In this way, by estimating the second threshold, even if the unique feature is affected by aging or attribute changes, it is possible to suppress a decrease in the TAR (overall). In other words, it is possible to maintain the TAR (overall) associated with the reference threshold determined by the user. Therefore, according to this embodiment, it is possible to improve authentication accuracy while compensating for the disadvantage of unique features, which are easily affected by aging and attribute changes.
• the user determines the reference threshold.
• the authentication device 2 may automatically determine the reference threshold.
• the authentication device 2 may determine the reference threshold so that, for example, "1-TAR+FAR" is minimized.
• the unique feature may be treated as a separate unique feature for each type of feature. For example, wrinkles, scars, and moles may be treated as separate unique features.
• FAR unique feature
• face recognition is given as an example.
• the technical idea according to the embodiment can be applied to recognition other than face recognition.
• the technical idea according to the embodiment may be applied to voice recognition in which a voiceprint is a general feature and a dialect is a unique feature.
• the authentication device 2 may be realized by a terminal device (e.g., at least one of a smartphone, a tablet terminal, and a notebook personal computer) or by a server device (e.g., a cloud server).
• the authentication device 2 may have some of its functions realized by a terminal device and the remaining parts realized by a server device.
• the feature calculation units 2111 and 2121, the attribute input unit 2124, the threshold determination information output unit 2131, and the reference threshold input unit 2132 may be realized by a terminal device, and the remaining parts may be realized by a server device.
• (Appendix 1) a feature amount calculation unit that calculates a general feature amount that is a feature amount related to a general feature of a person to be authenticated and a unique feature amount that is a feature amount related to a unique feature of the person to be authenticated; a score calculation unit that calculates a first matching score obtained by matching the general feature of the person to be authenticated with a general feature of a registrant, and a second matching score obtained by matching the unique feature of the person to be authenticated with a unique feature of the registrant; a determination unit that determines whether the person to be authenticated is the registrant based on the first matching score and the second matching score; Equipped with The determination unit determines that the person to be authenticated is not the registrant when at least one of a first result indicating whether the person to be authenticated is the registrant based on the first matching score and a second result indicating whether the person to be authenticated is the registrant based on the second matching score indicates that the person to be authenticated is not the
• the first result is a determination result of the determination unit based on a comparison result between the first matching score and a first threshold;
• the authentication device according to claim 1, wherein the second result is a determination result of the determination unit based on a comparison result between the second matching score and a second threshold value.
• the determination unit determines that the person to be authenticated is the registrant when the first matching score is greater than the first threshold value, The authentication device according to claim 2, wherein the determination unit determines that the person to be authenticated is the registrant when the second matching score is greater than the second threshold value.
• the authentication device according to claim 2 or 3, further comprising a setting unit that sets the second threshold based on a matching accuracy related to matching between the unique feature of the person to be authenticated and the unique feature of the registered person and a factor that may affect the matching.
• a feature amount calculation unit that calculates a general feature amount that is a feature amount related to a general feature of a person to be authenticated and a unique feature amount that is a feature amount related to a unique feature of the person to be authenticated; a score calculation unit that calculates an integrated score by integrating a first matching score obtained by matching the general feature of the person to be authenticated with a general feature of a registrant and a second matching score obtained by matching the unique feature of the person to be authenticated with a unique feature of the registrant; a determination unit that determines whether the person to be authenticated is the registrant by comparing the integrated score with a decision boundary for determining whether the person to be authenticated is the registrant; Equipped with The authentication device, wherein the decision boundary is set so that a range of integrated scores for which the person to be authenticated is determined to be the registrant is smaller than a range of integrated scores for which the person to be authenticated is determined to be not the registrant.
• Appendix 7 the decision boundary is expressed by a function having the first matching score and the second matching score as variables; The authentication device described in Appendix 6, wherein one or more coefficients included in the function are set so that the range of integrated scores for which the person to be authenticated is determined to be the registrant is smaller than the range of integrated scores for which the person to be authenticated is determined to be not the registrant.
• (Appendix 8) Calculating a general feature amount which is a feature amount related to a general feature of the person to be authenticated and a unique feature amount which is a feature amount related to a unique feature of the person to be authenticated; calculating a first matching score obtained by matching the general feature of the person to be authenticated with a general feature of a registrant, and a second matching score obtained by matching the unique feature of the person to be authenticated with the unique feature of the registrant, determining whether the person to be authenticated is the registrant based on the first matching score and the second matching score; an authentication method for determining that the person to be authenticated is not the registrant when at least one of a first result indicating whether the person to be authenticated is the registrant based on the first matching score and a second result indicating whether the person to be authenticated is the registrant based on the second matching score indicates that the person to be authenticated is not the registrant.

Landscapes

• Engineering & Computer Science (AREA)
• Computer Security & Cryptography (AREA)
• Theoretical Computer Science (AREA)
• Computer Hardware Design (AREA)
• Software Systems (AREA)
• Physics & Mathematics (AREA)
• General Engineering & Computer Science (AREA)
• General Physics & Mathematics (AREA)
• Collating Specific Patterns (AREA)

Priority Applications (2)

Applications Claiming Priority (1)

Publications (1)

Family

ID=92262095

Family Applications (1)

Country Status (2)

Citations (5)

• 2023
  • 2023-02-07 WO PCT/JP2023/004027 patent/WO2024166210A1/ja not_active Ceased
  • 2023-02-07 JP JP2024575914A patent/JPWO2024166210A1/ja active Pending

Patent Citations (5)

Also Published As

Similar Documents

Legal Events