Information processing device, information processing method, and program

Abstract

An information processing device according to the present disclosure comprises: an acquiring unit for acquiring a plurality of items of data each classified in advance into any one of a plurality of classes; a calculating unit for calculating distribution data of a first Mahalanobis distance of the plurality of items of data; and a normalizing unit for normalizing a second Mahalanobis distance between input target data and the plurality of items of data, on the basis of the distribution data.

Description

Information processing device, information processing method, and storage medium

[0001] The present disclosure relates to an information processing device, an information processing method, and a storage medium.

[0002] In processes such as machine learning that handle high-dimensional data, dimension reduction may be performed. In such applications, it is desirable that the data be appropriately separated according to classes after dimension reduction. Patent Literature 1 discloses an example of a method for generating a projection matrix used for dimension reduction.

[0003] JP 2010-39778 A

[0004] This disclosure aims to improve upon the techniques described in the prior art documents cited above.

[0005] According to one aspect of this disclosure, there is provided an information processing device comprising: an acquisition unit that acquires a plurality of data, each of which is pre-classified into one of a plurality of classes; a calculation unit that calculates distribution data of first Mahalanobis distances in the plurality of data; and a normalization unit that normalizes second Mahalanobis distances between input target data and the plurality of data based on the distribution data.

[0006] According to another aspect of this disclosure, there is provided an information processing method comprising the steps of acquiring a plurality of data, each of which has been pre-classified into one of a plurality of classes; calculating distribution data of first Mahalanobis distances for the plurality of data; and normalizing second Mahalanobis distances between input target data and the plurality of data based on the distribution data.

[0007] According to another aspect of the present disclosure, there is provided a storage medium having stored thereon a program for causing a computer to execute the steps of acquiring a plurality of data, each of which has been pre-classified into one of a plurality of classes, calculating distribution data of first Mahalanobis distances for the plurality of data, and normalizing second Mahalanobis distances between input target data and the plurality of data based on the distribution data.

[0008] 3A is a block diagram showing the hardware configuration of an information processing device according to a first embodiment; FIG. 3B is a functional block diagram showing the relationship between probability distribution data in known classes and thresholds used for class classification; FIG. 3C is a diagram showing the relationship between probability distribution data in known classes and thresholds used for class classification; FIG. 3D is a diagram showing the state in which the probability distribution data shown in FIG. 3A has been normalized; FIG. 3E is a diagram showing the state in which the probability distribution data shown in FIG. 3B has been normalized; FIG. 3F is a flowchart showing an outline of processing performed in an information processing device according to a first embodiment; FIG. 3G is a functional block diagram showing the outline of processing performed in an information processing device according to a second embodiment; FIG. 3H is a functional block diagram showing the outline of processing performed in an information processing device according to a third embodiment; FIG. 3I is a schematic diagram showing the overall configuration of an information processing system according to a fourth embodiment; FIG. 3I is a block diagram showing an example of the hardware configuration of an earphone control device according to a fourth embodiment; FIG. 3I is a functional block diagram showing the earphone and information processing device according to the fourth embodiment; FIG. 3I is a flowchart showing an outline of biometric matching processing performed by the information processing device according to the fourth embodiment; FIG. 3I is a functional block diagram showing the

[0009] Hereinafter, exemplary embodiments of the present disclosure will be described with reference to the drawings. In the drawings, similar or corresponding elements are designated by the same reference numerals, and descriptions thereof may be omitted or simplified.

[0010] [First Embodiment] An information processing device of this embodiment is a device that determines a class to which input unknown data belongs. This data may be, for example, feature data extracted from biometric information. The information processing device of this embodiment is a biometric matching device that performs identity verification of a person based on biometric information, but is not limited to this.

[0011] 1 is a block diagram showing an example of the hardware configuration of an information processing device 1 according to this embodiment. The information processing device 1 may be, for example, a computer such as a PC (Personal Computer), a processing server, a smartphone, or a microcomputer. The information processing device 1 includes a processor 101, a memory 102, a communication I / F (Interface) 103, an input device 104, and an output device 105. Note that the components of the information processing device 1 are connected to each other via buses, wiring, drive devices, etc. (not shown).

[0012] The processor 101 is a processing device that includes one or more arithmetic processing circuits, such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field-Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), a TPU (Tensor Processing Unit), etc. The processor 101 performs predetermined calculations according to programs stored in the memory 102, etc., and also has the function of controlling each part of the information processing device 1.

[0013] The memory 102 may include a volatile storage medium that provides a temporary memory area required for the operation of the processor 101, and a non-volatile storage medium that non-temporarily stores information such as data to be processed and the operating program of the information processing device 1. Examples of the volatile storage medium include RAM (Random Access Memory). Examples of the non-volatile storage medium include ROM (Read Only Memory), HDD (Hard Disk Drive), SSD (Solid State Drive), flash memory, etc.

[0014] The communication I / F 103 is a communication interface based on standards such as Ethernet (registered trademark), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc. The communication I / F 103 is a module for communicating with other devices such as a data server and a sensor device.

[0015] The input device 104 is a keyboard, a pointing device, a button, etc., and is used by the user to operate the information processing device 1. Examples of pointing devices include a mouse, a trackball, a touch panel, a pen tablet, etc. The input device 104 may include a sensor device such as a camera or a microphone. These sensor devices can be used to acquire biometric information.

[0016] The output device 105 is a device that presents information to a user, such as a display device, a speaker, etc. The input device 104 and the output device 105 may be integrally formed as a touch panel.

[0017] In FIG. 1 , the information processing device 1 is configured by one device, but the configuration of the information processing device 1 is not limited to this. For example, the information processing device 1 may be a system configured by multiple devices. Furthermore, other devices may be added to the information processing device 1, or some devices may not be provided. Furthermore, some devices may be replaced with other devices having similar functions. Furthermore, some functions of this embodiment may be provided by other devices via a network, or the functions of this embodiment may be distributed and realized across multiple devices. For example, the memory 102 may include cloud storage, which is a storage device provided in another device. In this way, the hardware configuration of the information processing device 1 can be changed as appropriate.

[0018] 2 is a functional block diagram of the information processing device 1 according to this embodiment. The information processing device 1 includes a first data storage unit 110, a statistics calculation unit 111, a second data storage unit 112, a minimum value calculation unit 113, a target data storage unit 114, a distance calculation unit 115, a normalization unit 116, and a determination unit 117.

[0019] The processor 101 performs predetermined arithmetic processing by executing a program stored in the memory 102. Based on the program, the processor 101 also controls the memory 102, the communication I / F 103, the input device 104, and the output device 105. Through these, the processor 101 realizes the functions of a statistics calculation unit 111, a minimum value calculation unit 113, a distance calculation unit 115, a normalization unit 116, and a determination unit 117. The memory 102 also realizes the functions of a first data storage unit 110, a second data storage unit 112, and a target data storage unit 114.

[0020] Note that some of the functional blocks shown in FIG. 2 may be provided in a device external to the information processing device 1, or may be realized by cooperation of a plurality of devices.

[0021] The first data storage unit 110 stores a dataset (first dataset) of feature data belonging to a known first class. In this embodiment, the first class is a class to which the feature data of a first person belongs. The feature data of the first person is also referred to as "personal data."

[0022] The statistics calculation unit 111 calculates, as statistics, the intra-class variance in the first class from the first data set acquired from the first data storage unit 110. Specifically, the statistics calculation unit 111 compares the personal data of the first person with each of the multiple personal data belonging to the first class, and calculates the distribution of Mahalanobis distances between the personal data.

[0023] The second data storage unit 112 stores a dataset (second dataset) of feature data belonging to a known second class different from the first class. In this embodiment, the second class is a class to which feature data of a second person different from the first person belongs. The feature data of the second person is also referred to as "other person data." The second data storage unit 112 stores a second class for each of N (N is a natural number equal to or greater than 2) second persons other than the first person.

[0024] The minimum value calculation unit 113 calculates the inter-class variance in the second data set acquired from the second data storage unit 112 based on the statistic (intra-class variance) calculated by the statistic calculation unit 111. The minimum value calculation unit 113 calculates the minimum value of the Mahalanobis distance in the inter-class variance. Specifically, the minimum value calculation unit 113 compares the first person's own data with each of multiple other person's data belonging to the second class, and calculates distribution data of the Mahalanobis distance between the first person's own data and the other person's data.

[0025] The target data storage unit 114 stores, as target data, unknown feature data of a subject for a determination process such as class classification.

[0026] When the distance calculation unit 115 acquires the target data from the target data storage unit 114, it calculates the Mahalanobis distance of the target data based on the statistic (intra-class variance) calculated by the statistic calculation unit 111. Specifically, the distance calculation unit 115 compares the input target data with the first class of personal data, and calculates distribution data of the Mahalanobis distance between the target data and the personal data.

[0027] The normalization unit 116 normalizes the Mahalanobis distance of the target data based on the minimum value of the Mahalanobis distance in the inter-class variance calculated by the minimum value calculation unit 113. A specific example of the normalization method will be described later.

[0028] The determination unit 117 compares the Mahalanobis distance of the normalized target data with a predetermined threshold and performs a predetermined determination on the target data. For example, if the determination by the determination unit 117 is class classification, this determination is a process of determining the class to which the input target data belongs. Also, for example, if the determination by the determination unit 117 is person identification in biometric matching, this determination is a process of determining whether the person who acquired the target data is the same person as the registered person. Note that the threshold is set to the same value across multiple classes.

[0029] 3A and 3B are diagrams illustrating the relationship between probability distribution data for known classes and thresholds used for class classification. FIG. 3C is a diagram illustrating the state in which the probability distribution data shown in FIG. 3A has been normalized. FIG. 3D is a diagram illustrating the state in which the probability distribution data shown in FIG. 3B has been normalized. In the diagrams, the distribution data indicated by solid lines A1 and A2 is the probability distribution data of intra-class variance. The distribution data indicated by dashed-dotted lines B1 and B2 is the probability distribution data of inter-class variance. In each diagram, the vertical axis represents probability, and the horizontal axis represents Mahalanobis distance.

[0030] 3A, a threshold value TH1 is set near the intersection of probability distribution data A1 of intra-class variance and probability distribution data B1 of inter-class variance in a known class CL1. This allows the Mahalanobis distance calculated for the target data of the person to be authenticated to be compared with the threshold value TH1, making it possible to determine whether the target data belongs to class CL1.

[0031] 3B, a threshold value TH2 is set near the intersection of the probability distribution data A2 of the intra-class variance and the probability distribution data B2 of the inter-class variance in the known class CL2. This allows the Mahalanobis distance calculated for the target data of the person to be authenticated to be compared with the threshold value TH2, thereby determining whether the target data belongs to class CL2. However, if a common threshold value TH1 is used as the threshold value for determination in classes CL1 and CL2, it becomes impossible to perform determination in class CL2 with high accuracy.

[0032] Therefore, the information processing device 1 (normalization unit 116) according to this embodiment normalizes the probability distribution data, thereby making it possible to determine the target data with high accuracy using a threshold value TH that is common to all of the multiple classes.

[0033] 3C shows that the probability distribution data A1 of the intra-class variance and the probability distribution data B1 of the inter-class variance in the class CL1 are normalized, and the threshold TH is set for the normalized data. The threshold TH can be set corresponding to the threshold TH1 in FIG. 3A.

[0034] Similarly, FIG. 3D shows that the probability distribution data A2 of the intra-class variance and the probability distribution data B2 of the inter-class variance in class CL2 are each normalized, and a common threshold TH is set for the normalized data.

[0035] 4 is a flowchart showing an outline of the processing performed in the information processing device according to the first embodiment. The operation of the information processing device 1 will be described with reference to FIG.

[0036] In step S101 , the statistics calculation unit 111 acquires a first data set from the first data storage unit 110 .

[0037] In step S102, the statistics calculation unit 111 calculates statistics from the first data set. Specifically, the statistics calculation unit 111 calculates the within-class variance in the first data set as the statistics.

[0038] In step S103 , the minimum value calculation unit 113 acquires the second data set from the second data storage unit 112 .

[0039] In step S104, the minimum value calculation unit 113 calculates the minimum value of the Mahalanobis distance in the inter-class variance based on the second data set acquired in step S103 and the statistics calculated by the statistics calculation unit 111.

[0040] In step S105 , the distance calculation unit 115 acquires the target data from the target data storage unit 114 .

[0041] In step S106 , the distance calculation unit 115 calculates the Mahalanobis distance of the target data based on the statistic (intra-class variance) calculated by the statistic calculation unit 111 .

[0042] In step S107 , the normalization unit 116 normalizes the Mahalanobis distance of the target data based on the minimum value calculated by the minimum value calculation unit 113 .

[0043] The normalization method in the normalization unit 116 of this embodiment will be described. Here, the Mahalanobis distance of the target data before normalization is D, the Mahalanobis distance of the target data after normalization is normD, and the minimum value of the Mahalanobis distance in the inter-class variance of the known other data set (second class) is difMinD. In this case, the normalization unit 116 executes the following process: normD = 101 - 100^(D / difMinD) if(normD < 0) {normD = 0}

[0044] For example, when D=300 and difMinD=150, normD is calculated as follows: normD=101−100 （３００／１５０） = 101 - 100 ２ = -9899 normD < 0, so normD is 0. In this embodiment, the Mahalanobis distance after normalization can take a value from 0 to 100.

[0045] In step S108, the determination unit 117 performs a determination on the target data based on the normalized Mahalanobis distance.

[0046] In step S109, the determination unit 117 outputs the determination result, which may be output to the memory 102 in the information processing device 1 or to another device.

[0047] The Mahalanobis distance between the personal data of a person to be authenticated and the distribution of multiple data included in a known class varies depending on whether the person to be authenticated is the person. Specifically, the Mahalanobis distance is short when the person to be authenticated is the person, and long when the person to be authenticated is a different person. However, for example, if the distribution of the personal data is very small, personal data that deviates slightly when viewed using Euclidean distance may be determined to be the person, but the distance may be large when viewed using Mahalanobis distance, and the person may be erroneously determined to be the person. However, in authentication systems, the same threshold is set for multiple classes to determine whether the target data belongs to a known class, i.e., to authenticate whether the person to be authenticated is the person. A threshold set to the same value for multiple classes may not be appropriate for a specific class, which could result in a decrease in authentication accuracy.

[0048] In contrast, in this embodiment, the minimum value of inter-class variance among known classes is calculated, and the Mahalanobis distance of the target data is normalized based on this minimum value, so that the target data can be determined using a threshold value common to multiple classes. This provides an information processing device 1 that can improve the authentication accuracy of data in multiple classes.

[0049] Furthermore, in normalization, by using the minimum value of the inter-class variance in the known class to which the other person's data belongs, it is also possible to minimize the other person acceptance rate when the target data is the person's own data.

[0050] Second Embodiment A second embodiment will now be described. Since this embodiment is a modification of the first embodiment, the description of elements similar to those in the first embodiment may be omitted or simplified.

[0051] 5 is a functional block diagram of an information processing device 1 according to this embodiment. As shown in FIG. 5, the information processing device 1 according to this embodiment includes a first data storage unit 110, a statistics calculation unit 111, a maximum value calculation unit 118, a target data storage unit 114, a distance calculation unit 115, a normalization unit 116, and a determination unit 117. Unlike the first embodiment, the information processing device 1 according to this embodiment includes a maximum value calculation unit 118 instead of the second data storage unit 112 and the minimum value calculation unit 113.

[0052] The maximum value calculation unit 118 calculates the maximum value of the Mahalanobis distance in the statistics (intra-class variance) calculated by the statistics calculation unit 111. Specifically, the maximum value calculation unit 118 compares the personal data of the first person belonging to the first class with the personal data of other people belonging to the first class, and calculates distribution data of the Mahalanobis distance between the personal data.

[0053] 6 is a flowchart showing an outline of the processing performed by the information processing device 1 according to this embodiment. The operation of the information processing device 1 will be described with reference to FIG.

[0054] In step S201 , the statistics calculation unit 111 acquires the first data set from the first data storage unit 110 .

[0055] In step S202, the statistics calculation unit 111 calculates statistics from the first data set. Specifically, the statistics calculation unit 111 calculates the within-class variance in the first data set as the statistics.

[0056] In step S203, the maximum value calculation unit 118 calculates the maximum value of the Mahalanobis distance in the within-class variance of the first data set based on the statistics calculated by the statistics calculation unit 111.

[0057] In step S204 , the distance calculation unit 115 acquires the target data from the target data storage unit 114 .

[0058] In step S205 , the distance calculation unit 115 calculates the Mahalanobis distance of the target data based on the statistic (intra-class variance) calculated by the statistic calculation unit 111 .

[0059] In step S206, the normalization unit 116 normalizes the Mahalanobis distance of the target data based on the maximum value calculated by the maximum value calculation unit 118.

[0060] The normalization method in the normalization unit 116 of this embodiment will be described. Here, the Mahalanobis distance of the target data before normalization is D, the Mahalanobis distance of the target data after normalization is normD, and the maximum value of the Mahalanobis distance in the intra-class variance of the known personal data set (first class) is selfMaxD. In this case, the normalization unit 116 executes the following process: normD = 101 - 100^(D / selfMaxD) if (normD < 0) {normD = 0}

[0061] For example, when D=150 and selfMaxD=200, normD is calculated as follows: normD=101−100 （１５０／２００） = 101 - 100 ０．７５ ≒ 101 - 31.6 = 69.4

[0062] In step S207, the determination unit 117 performs a determination on the target data based on the normalized Mahalanobis distance.

[0063] In step S208, the determination unit 117 outputs the determination result, which may be output to the memory 102 in the information processing device 1 or to another device.

[0064] As described above, in this embodiment, the maximum value of the intra-class variance among known classes is calculated, and the Mahalanobis distance of the target data is normalized based on this maximum value, so that the target data can be determined using a threshold value common to multiple classes. This provides an information processing device 1 that can improve the authentication accuracy of data in multiple classes.

[0065] Furthermore, by using the maximum value of the intra-class variance in the known class to which the person's data belongs in normalization, it is also possible to minimize the false rejection rate when the target data is person's data.

[0066] [Third Embodiment] Hereinafter, a third embodiment will be described. Since this embodiment is a modification of the first or second embodiment, the description of elements similar to those of the first or second embodiment may be omitted or simplified.

[0067] 7 is a functional block diagram of an information processing device 1 according to this embodiment. The information processing device 1 includes a first data storage unit 110, a statistics calculation unit 111, a second data storage unit 112, a minimum value calculation unit 113, a maximum value calculation unit 118, a target data storage unit 114, a distance calculation unit 115, a normalization unit 116, and a determination unit 117. The information processing device 1 according to this embodiment differs from the first embodiment in that it further includes a maximum value calculation unit 118.

[0068] 8 is a flowchart showing an outline of the processing performed by the information processing device 1 according to this embodiment. The operation of the information processing device 1 will be described with reference to FIG.

[0069] In step S301 , the statistics calculation unit 111 acquires the first data set from the first data storage unit 110 .

[0070] In step S302, the statistics calculation unit 111 calculates statistics from the first data set. Specifically, the statistics calculation unit 111 calculates the within-class variance in the first data set as the statistics.

[0071] In step S303, the maximum value calculation unit 118 calculates the maximum value of the Mahalanobis distance in the within-class variance of the first data set based on the statistics calculated by the statistics calculation unit 111.

[0072] In step S304 , the minimum value calculation unit 113 acquires the second data set from the second data storage unit 112 .

[0073] In step S305 , the minimum value calculation unit 113 calculates the minimum value of the Mahalanobis distance in the inter-class variance based on the acquired second data set and the statistics calculated by the statistics calculation unit 111 .

[0074] In step S306 , the distance calculation unit 115 acquires the target data from the target data storage unit 114 .

[0075] In step S307 , the distance calculation unit 115 calculates the Mahalanobis distance of the target data based on the statistic (intra-class variance) calculated by the statistic calculation unit 111 .

[0076] In step S308, the normalization unit 116 acquires parameters set in advance by the administrator or manufacturer of the information processing device 1 from a storage device such as the memory 102.

[0077] In step S309, the normalization unit 116 calculates a reference value for the normalization process based on the acquired parameters, the minimum value calculated by the minimum value calculation unit 113, and the maximum value calculated by the maximum value calculation unit 118.

[0078] The normalization method in the normalization unit 116 of this embodiment will be described. Here, the Mahalanobis distance of the target data before normalization is D, the Mahalanobis distance of the target data after normalization is normD, the minimum value of the Mahalanobis distance in the inter-class variance of the known other person's data set (second class) is difMinD, the maximum value of the Mahalanobis distance in the intra-class variance of the known person's own data set (first class) is selfMaxD, the reference value is SetD, and X is a parameter value. Note that X is an arbitrary value between 0 and 1.0. In this case, the normalization unit 116 executes the following process. SetD = X * selfMaxD + (1 - X) * difMinD normD = 101 - 100^(D / SetD) if( normD < 0 ) {normD = 0}

[0079] For example, when X=1, SetD is calculated as follows: SetD=1*selfMaxD+(1-1)*difMinD=selfMaxD Also, when D=150 and selfMaxD=200, normD is calculated as follows: normD=101-100 （１５０／２００） = 101 - 100 ０．７５≒101 - 31.6 = 69.4

[0080] Furthermore, when X=0, SetD is calculated as follows: SetD=0*selfMaxD+(1-0)*difMinD=difMinD

[0081] Furthermore, when D=300 and difMinD=150, normD is calculated as follows: normD = 101 - 100^(D / SetD) = 101 - 100^(D / difMinD) = 101 - 100 （３００／１５０） = 101 - 100 ２ = -9899 normD < 0, so normD is 0.

[0082] Furthermore, when X=0.5, SetD is calculated as follows: SetD = 0.5 * selfMaxD + (1-0.5) * difMinD = 0.5 * selfMaxD + 0.5 * difMinD For example, when D=300, selfMaxD=200, and difMinD=150, SetD and normD are calculated as follows: SetD = 0.5 * 200 + 0.5 * 150 = 100 + 75 = 175 normD = 101 - 100^(D / SetD) = 101 - 100^(300 / 175) ≈ 101 - 100 １．７１ ≒ 101 - 2630 = -2529 normD < 0, so normD is 0.

[0083] In step S311, the determination unit 117 performs a determination on the target data based on the normalized Mahalanobis distance.

[0084] In step S312, the determination unit 117 outputs the determination result, which may be output to the memory 102 in the information processing device 1 or to another device.

[0085] As described above, in this embodiment, the maximum value of the intra-class variance in a known class and the minimum value of the inter-class variance in other known classes are calculated, and the Mahalanobis distance of the target data is normalized based on the minimum and maximum values. This makes it possible to determine the target data using a common threshold value across multiple classes. An information processing device 1 is provided that can improve the authentication accuracy of data across multiple classes.

[0086] Furthermore, the weighting of the maximum value of the intra-class variance and the minimum value of the inter-class variance can be changed by parameter values, which allows the false rejection rate and false acceptance rate in the information processing device 1 to be flexibly adjusted.

[0087] [Fourth Embodiment] A fourth embodiment will be described below. In the fourth embodiment, an information processing system that performs ear acoustic matching based on acoustic characteristics acquired by earphones will be illustrated as an application example of the information processing device 1 of the first to third embodiments. Ear acoustic matching is a technology for determining whether a person is the same or different by matching the acoustic characteristics of the person's head, including the ear canal. Because the acoustic characteristics of the ear canal differ from person to person, ear acoustic matching is suitable for biometric information used for personal matching. Therefore, ear acoustic matching may be used to identify users of hearable devices such as earphones. Note that ear acoustic matching may be used not only to determine whether a person is the same or different, but also to determine the wearing state of the hearable device.

[0088] 9 is a schematic diagram showing the overall configuration of an information processing system according to this embodiment. The information processing system includes an information processing device 1 and earphones 2 that can be connected to each other via wireless communication.

[0089] The earphones 2 include an earphone control device 20, a speaker 26, and a microphone 27. The earphones 2 are acoustic devices that can be worn on the head, particularly in the ears, of a user 3, and are typically wireless earphones, wireless headsets, or the like. The speaker 26 functions as a sound wave generator that emits sound waves toward the ear canal of the user 3 when worn, and is arranged on the wearing surface side of the earphones 2. The microphone 27 is arranged on the wearing surface side of the earphones 2 so that it can receive sound waves reverberating in the ear canal, etc., of the user 3 when worn. The earphone control device 20 controls the speaker 26 and the microphone 27 and communicates with the information processing device 1.

[0090] In this specification, "sound" such as sound waves and voice includes inaudible sounds whose frequencies or sound pressure levels are outside the audible range.

[0091] The information processing device 1 is the same device as those described in the first to third embodiments. The information processing device 1 is, for example, a computer communicatively connected to the earphones 2, and performs biometric matching based on acoustic information. The information processing device 1 also controls the operation of the earphones 2, transmits audio data for generating sound waves emitted from the earphones 2, and receives audio data obtained from sound waves received by the earphones 2. As a specific example, when a user 3 listens to music using the earphones 2, the information processing device 1 transmits compressed music data to the earphones 2. Furthermore, when the earphones 2 are telephone devices used for issuing work instructions at an event venue, hospital, or the like, the information processing device 1 transmits audio data of work instructions to the earphones 2. In this case, audio data of the user 3's speech may also be transmitted from the earphones 2 to the information processing device 1.

[0092] Note that this overall configuration is an example, and for example, the information processing device 1 and the earphones 2 may be connected by wire. Also, the information processing device 1 and the earphones 2 may be configured as an integrated device, or another device may be included in the information processing system.

[0093] 10 is a block diagram showing an example of the hardware configuration of earphone control device 20. Earphone control device 20 includes processor 201, memory 202, speaker I / F 203, microphone I / F 204, communication I / F 205, and battery 206. Note that the components of earphone control device 20 are interconnected via buses, wiring, drivers, and the like (not shown).

[0094] The processor 201, the memory 202, and the communication I / F 205 will be omitted from the description as they overlap with those in the first embodiment.

[0095] The speaker I / F 203 is an interface for driving the speaker 26. The speaker I / F 203 includes a digital-to-analog conversion circuit, an amplifier, etc. The speaker I / F 203 converts audio data into an analog signal and supplies it to the speaker 26. This causes the speaker 26 to emit sound waves based on the audio data.

[0096] The microphone I / F 204 is an interface for acquiring signals from the microphone 27. The microphone I / F 204 includes an analog-to-digital conversion circuit, an amplifier, etc. The microphone I / F 204 converts analog signals generated by sound waves received by the microphone 27 into digital signals. As a result, the earphone control device 20 acquires audio data based on the received sound waves.

[0097] The battery 206 is, for example, a secondary battery, and supplies the power necessary for the operation of the earphone 2. This allows the earphone 2 to operate wirelessly without being connected to an external power source via a wire. If the earphone 2 is connected via a wire, the battery 208 may not be provided.

[0098] Note that the hardware configuration shown in FIG. 10 is an example, and other devices may be added, or some devices may not be provided. Furthermore, some devices may be replaced with other devices having similar functions. For example, the earphones 2 may further include an input device such as a button to accept operations by the user 3, and may further include a display device such as a display or indicator light to provide information to the user 3. In this way, the hardware configuration shown in FIG. 10 can be modified as appropriate.

[0099] 11 is a functional block diagram of the earphones 2 and information processing device 1 according to this embodiment. The information processing device 1 includes a target data storage unit 114, a distance calculation unit 115, a normalization unit 116, a determination unit 117, a distance information storage unit 119, and an acoustic characteristic acquisition unit 120. The configuration of the block diagram of the earphones 2 is the same as that of FIG. 10 , and therefore description thereof will be omitted. Of the functional blocks of the information processing device 1, the functions of the target data storage unit 114, the distance calculation unit 115, the normalization unit 116, and the determination unit 117 are the same as those described in the first embodiment.

[0100] The distance information storage unit 119 stores distance information such as the intra-class variance, the inter-class variance, the maximum value of the Mahalanobis distance in the intra-class variance, and the minimum value of the Mahalanobis distance in the inter-class variance, calculated from a known data set. For this reason, in Fig. 11, a block related to a function for normalizing the probability distribution for each Mahalanobis distance in a data set of known classes between classes is not shown.

[0101] The acoustic characteristic acquisition unit 120 acquires acoustic characteristics in the frequency domain based on sound waves propagating through the head of the user 3. The acoustic characteristics may be, for example, a frequency spectrum obtained by converting a time-domain acoustic signal into a frequency domain using an algorithm such as a fast Fourier transform.

[0102] 11 , some or all of the functions of the functional blocks described within the information processing device 1 may be provided in the earphone control device 20 rather than the information processing device 1. That is, the functions described above may be realized by the information processing device 1, by the earphone control device 20, or through cooperation between the information processing device 1 and the earphone control device 20. In the following description, unless otherwise specified, it is assumed that the functional blocks related to the acquisition and determination of acoustic information are provided within the information processing device 1, as shown in FIG.

[0103] 12 is a flowchart showing an outline of the biometric matching process performed by the information processing device 1 according to this embodiment. The operation of the information processing device 1 will be described with reference to FIG.

[0104] 12 is executed, for example, when the user 3 starts using the earphones 2 by operating the earphones 2. Alternatively, the biometric matching process in Fig. 12 may be executed every time a predetermined time elapses while the earphones 2 are powered on.

[0105] In step S401, the acoustic characteristic acquisition unit 120 instructs the earphone control device 20 to emit a test sound. The earphone control device 20 transmits a test signal to the speaker 26, and the speaker 26 generates the test sound based on the test signal and emits it into the ear canal of the user 3.

[0106] The test signal may be a signal containing frequency components within a predetermined range, such as a chirp signal, an M-sequence (Maximum Length Sequence) signal, white noise, or an impulse signal. This makes it possible to acquire an acoustic signal containing information on frequencies within a predetermined range. The test sound may be an audible sound whose frequency and sound pressure level are within the audible range. In this case, by making the user 3 perceive sound waves during verification, the user 3 can be notified that verification is being performed. The test sound may also be an inaudible sound whose frequency or sound pressure level is outside the audible range. In this case, the sound waves can be made less perceptible to the user 3, improving comfort during use.

[0107] In step S402, the microphone 27 receives reverberation (ear acoustics) from the ear canal and converts it into an electrical signal in the time domain. This electrical signal is sometimes called an acoustic signal. The microphone 27 transmits the acoustic signal to the earphone control device 20, and the earphone control device 20 transmits the acoustic signal to the information processing device 1.

[0108] In step S403, the acoustic characteristic acquisition unit 120 acquires acoustic characteristics in the frequency domain based on sound waves propagating through the head of the user 3. The acoustic characteristics may be, for example, a frequency spectrum obtained by converting an acoustic signal in the time domain into the frequency domain using an algorithm such as a fast Fourier transform.

[0109] In step S404, the target data storage unit 114 stores the acoustic characteristics acquired from the earphone control device 20 as target data for feature extraction.

[0110] In step S405, the distance calculation unit 115 acquires target data from the target data storage unit 114. This target data is unknown data that is to be subjected to judgment in this judgment process.

[0111] In step S406, the distance calculation unit 115 calculates the Mahalanobis distance of the target data.

[0112] In step S407, the normalization unit 116 normalizes the Mahalanobis distance of the target data based on the distance information stored in the distance information storage unit 119. The distance information includes the intra-class variance, the inter-class variance, the maximum value of the Mahalanobis distance for the intra-class variance, and the minimum value of the Mahalanobis distance for the inter-class variance, all calculated from a known data set. For example, when the maximum value of the Mahalanobis distance for the intra-class variance is used, normalization can be performed in the same manner as in the first embodiment.

[0113] In step S408, the determination unit 117 performs a determination process on the target data based on the normalized Mahalanobis distance. For example, if the determination by the determination unit 117 is class classification, this determination process is a process of determining a class to which the input target data belongs. Also, for example, if the determination by the determination unit 117 is person identification in biometric matching, this determination process is a process of determining whether the person from whom the target data was obtained is the same person as the registered person.

[0114] In step S409, the determination unit 117 outputs the determination result of step S408. This determination result is used, for example, to control whether or not to permit use of the earphone 2. The output destination may be the memory 102 in the information processing device 1 or another device.

[0115] Although the present embodiment has been described with reference to an example of ear acoustic matching, the present invention is equally applicable to biometric matching using other biometric information, such as face, iris, fingerprint, palm print, veins, voice, auricle, and gait.

[0116] According to this embodiment, since normalization similar to that of the first to third embodiments is performed, target data can be determined using a threshold value common to multiple classes, thereby providing an information processing device 1 that can improve the authentication accuracy of data in multiple classes in biometric matching such as ear acoustic matching.

[0117] 13 is a functional block diagram of an information processing device 4 according to a fifth embodiment. The information processing device 4 includes an acquisition unit 401, a calculation unit 402, and a normalization unit 403. The acquisition unit 401 acquires a plurality of data items, each of which has been pre-classified into one of a plurality of classes. The calculation unit 402 calculates distribution data of the first Mahalanobis distances for the plurality of data items. The normalization unit 403 normalizes the second Mahalanobis distances between input target data and the plurality of data items based on the distribution data.

[0118] According to this embodiment, an information processing device 4 is provided that can improve the authentication accuracy of data in a plurality of classes.

[0119] [Modified Embodiments] This disclosure is not limited to the above-described embodiments and can be modified as appropriate within the scope of the present disclosure. For example, an example in which part of the configuration of one embodiment is added to another embodiment, or an example in which part of the configuration of another embodiment is replaced with another embodiment, is also an embodiment of this disclosure.

[0120] In the above-described embodiment, the intra-class variance or the inter-class variance is illustratively used as an index of the variation in the data, but any statistic other than the variance may be used as long as it can be an index of the variation.

[0121] The scope of each embodiment also includes a processing method in which a program that operates the configuration of the embodiment to realize the functions of the above-described embodiments is recorded on a storage medium, the program recorded on the storage medium is read as code, and the program is executed on a computer. That is, a computer-readable storage medium is also included in the scope of each embodiment. Furthermore, not only the storage medium on which the above-described program is recorded, but also the program itself is included in each embodiment. Furthermore, one or more components included in the above-described embodiments may be circuits such as ASICs or FPGAs configured to realize the functions of each component.

[0122] Examples of the storage medium that can be used include a floppy disk, a hard disk, an optical disk, a magneto-optical disk, a CD (Compact Disk)-ROM, a magnetic tape, a non-volatile memory card, and a ROM. In addition, the scope of each embodiment is not limited to programs that execute processing by themselves recorded on the storage medium, but also includes programs that execute processing by operating on an OS (Operating System) in cooperation with other software and functions of an expansion board.

[0123] The services realized by the functions of the above-described embodiments can also be provided to users in the form of SaaS (Software as a Service).

[0124] It should be noted that the above-described embodiments are merely examples of specific embodiments for carrying out this disclosure, and the technical scope of this disclosure should not be interpreted as being limited by these embodiments. In other words, this disclosure can be carried out in various forms without departing from its technical idea or main features.

[0125] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes.

[0126] (Supplementary Note 1) An information processing device comprising: an acquisition unit that acquires a plurality of data each pre-classified into one of a plurality of classes; a calculation unit that calculates distribution data of first Mahalanobis distances in the plurality of data; and a normalization unit that normalizes second Mahalanobis distances between input target data and the plurality of data based on the distribution data.

[0127] (Supplementary Note 2) The information processing device according to Supplementary Note 1, further comprising: a determination unit that determines a class to which the target data belongs among the plurality of classes by comparing the normalized second Mahalanobis distance with thresholds set for the plurality of classes.

[0128] (Supplementary Note 3) The information processing device according to Supplementary Note 1, wherein the distribution data is an inter-class variance, and the normalization unit uses a minimum value of the first Mahalanobis distance in the inter-class variance for the normalization.

[0129] (Supplementary Note 4) The information processing device according to Supplementary Note 1, wherein the distribution data is an intra-class variance, and the normalization unit uses a maximum value of the first Mahalanobis distance in the intra-class variance for the normalization.

[0130] (Supplementary Note 5) The information processing device according to Supplementary Note 1, wherein the distribution data is an intra-class variance and an inter-class variance, and the normalization unit uses a maximum value of the first Mahalanobis distance in the intra-class variance and a minimum value of the first Mahalanobis distance in the inter-class variance for the normalization.

[0131] (Supplementary Note 6) The information processing device according to Supplementary Note 5, wherein the normalization unit changes weightings for the maximum value and the minimum value in the normalization.

[0132] (Supplementary Note 7) The information processing device according to any one of Supplementary Notes 1 to 6, wherein the plurality of data are biometric information of a person.

[0133] (Supplementary Note 8) The information processing device according to Supplementary Note 7, wherein the biometric information indicates acoustic characteristics of an ear canal of a person.

[0134] (Supplementary Note 9) An information processing method comprising the steps of: acquiring a plurality of data, each of which is pre-classified into one of a plurality of classes; calculating distribution data of first Mahalanobis distances for the plurality of data; and normalizing second Mahalanobis distances between input target data and the plurality of data based on the distribution data.

[0135] (Supplementary Note 10) A storage medium storing a program for causing a computer to execute the steps of: acquiring a plurality of data, each of which has been pre-classified into one of a plurality of classes; calculating distribution data of first Mahalanobis distances for the plurality of data; and normalizing second Mahalanobis distances between input target data and the plurality of data based on the distribution data.

[0136] This application claims priority based on Japanese Patent Application No. 2023-7782, filed on January 23, 2023, the disclosure of which is incorporated herein in its entirety by reference.

[0137] 1, 4 Information processing device 2 Earphone 3 User 20 Earphone control device 26 Speaker 27 Microphone 101, 201 Processor 102, 202 Memory 103, 205 Communication I / F 104 Input device 105 Output device 110 First data storage unit 111 Statistics calculation unit 112 Second data storage unit 113 Minimum value calculation unit 114 Target data storage unit 115 Distance calculation unit 116 Normalization unit 117 Determination unit 118 Maximum value calculation unit 119 Distance information storage unit 120 Acoustic characteristic acquisition unit 203 Speaker I / F 204 Microphone I / F 206 Battery

Claims

1. an acquisition unit that acquires a plurality of data items each of which has been pre-classified into one of a plurality of classes; a calculation unit that calculates distribution data of first Mahalanobis distances in the plurality of data; a normalization unit that normalizes the second Mahalanobis distance between the input target data and the plurality of data based on the distribution data; An information processing device comprising:

2. a determination unit that determines a class to which the target data belongs among the plurality of classes by comparing the normalized second Mahalanobis distance with thresholds set for the plurality of classes; The information processing device according to claim 1 , further comprising:

3. the distribution data is between-class variance; the normalization unit uses a minimum value of the first Mahalanobis distance in the inter-class variance for the normalization. The information processing device according to claim 1 .

4. the distribution data is within-class variance; the normalization unit uses a maximum value of the first Mahalanobis distance in the intra-class variance for the normalization. The information processing device according to claim 1 .

5. the distribution data is within-class variance and between-class variance; the normalization unit uses a maximum value of the first Mahalanobis distance in the intra-class variance and a minimum value of the first Mahalanobis distance in the inter-class variance for the normalization. The information processing device according to claim 1 .

6. the normalization unit changes weightings for the maximum value and the minimum value in the normalization. The information processing device according to claim 5 .

7. The plurality of data is biometric information of a person. The information processing device according to claim 1 .

8. The biometric information indicates acoustic characteristics of the person's ear canal. The information processing device according to claim 7 .

9. acquiring a plurality of data, each of which has been pre-classified into one of a plurality of classes; calculating distribution data of first Mahalanobis distances in the plurality of data; normalizing a second Mahalanobis distance between the input target data and the plurality of data based on the distribution data; An information processing method comprising:

10. On the computer, acquiring a plurality of data, each of which has been pre-classified into one of a plurality of classes; calculating distribution data of first Mahalanobis distances in the plurality of data; normalizing a second Mahalanobis distance between the input target data and the plurality of data based on the distribution data; A program to execute.