Information processing device, information processing method, and computer program

Abstract

An information processing device 1 comprising: an acquisition unit 11 that performs an acquisition operation to acquire a surface image including a fingerprint of a subject; a first estimation unit 12 that performs a first estimation operation to estimate, from the acquired surface image, a pattern that the fingerprint has; and an estimation control unit 13 that controls the acquisition unit 11 and the first estimation unit 12 so as to repeat the acquisition operation and the first estimation operation until a prescribed number of surface images that have been estimated by the first estimation unit 12 to have a first pattern are acquired.

Description

Technical Field

[0001] This disclosure relates to the technical field of information processing apparatuses, information processing methods, and recording media.

Background Art

[0002] Patent Document 1 describes an authentication apparatus including a feature extraction unit that extracts feature information from biometric information of a collator acquired by a biometric sensor, a feature information storage unit that stores feature information of biometric information of one or more users and a plurality of non-users, a first collation score calculation unit that calculates a first collation score by comparing collator feature information of the collator's biometric information extracted by the feature extraction unit with collator target feature information of the biometric information of a target collation person who is one of the users stored in the feature information storage unit and non-user feature information of the biometric information of a plurality of non-users, a collation score correction unit that corrects the first collation score with the collator target feature information based on the first collation scores with the plurality of non-user feature information, and an authentication unit that authenticates the collator as the target collation person when the corrected first collation score is equal to or greater than a preset discrimination threshold. Patent Document 2 describes a technique in which a mobile device captures a high-resolution image representing a plurality of fingers of a target, identifies respective fingertip segments for each of the plurality of fingers from the high-resolution image according to a segmentation algorithm, extracts distinguishable features from the respective fingertip segments for each finger, generates a biometric identifier including the extracted distinguishable features, and stores the generated biometric identifier in a memory. Patent Document 3 describes a technique for capturing a user's biometric features using a mobile device such as a smartphone and generating an identifier that characterizes the user's biometric features. The biometric identifier is generated using images of multiple fingers of the user for the purpose of authenticating / identifying the user according to the captured biometrics and determining the user's existence. Patent Document 3 also describes additional techniques to prevent false authentication due to impersonation. Patent Document 3 describes a technique in which an anti-impersonation method may include capturing one or more images of the user's fingers and analyzing the captured images for signs of existence. [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] International Publication No. 2019 / 207649 [Patent Document 2] Japanese Patent Publication No. 2020-074174 [Patent Document 3] Japanese Patent Publication No. 2020-501264 [Overview of the Initiative] [Problems that the invention aims to solve]

[0004] This disclosure aims to provide an information processing device, an information processing method, and a recording medium that improve upon the technologies described in prior art documents. [Means for solving the problem]

[0005] One aspect of an information processing device includes: an acquisition means that performs an acquisition operation to acquire a surface image including a subject's fingerprint; a first estimation means that performs a first estimation operation to estimate the pattern of the fingerprint from the acquired surface image; and an estimation control means that controls the acquisition means and the first estimation means to repeat the acquisition operation and the first estimation operation until a predetermined number of surface images that the first estimation means has estimated to have a first pattern have been acquired.

[0006] One aspect of the information processing method involves performing an acquisition operation to acquire a surface image containing the subject's fingerprints, performing a first estimation operation to estimate the pattern of the fingerprints from the acquired surface image, and controlling the system to repeat the acquisition operation and the first estimation operation until a predetermined number of surface images that are estimated to have a first pattern by the first estimation operation have been acquired.

[0007] One embodiment of a recording medium contains a computer program that causes a computer to execute an information processing method which involves performing an acquisition operation to acquire a surface image containing a subject's fingerprint, performing a first estimation operation to estimate the pattern of the fingerprint from the acquired surface image, and repeating the acquisition operation and the first estimation operation until a predetermined number of surface images that are estimated to have a first pattern by the first estimation operation have been acquired. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 is a block diagram showing the configuration of the information processing device in the first embodiment. [Figure 2] Figure 2 is a block diagram showing the configuration of the information processing device in the second embodiment. [Figure 3] Figure 3 is a flowchart showing the flow of information processing operations performed by the information processing device in the second embodiment. [Figure 4] Figure 4 is a block diagram showing the configuration of the information processing device in the third embodiment. [Figure 5] Figure 5 is a flowchart showing the flow of information processing operations performed by the information processing device in the third embodiment. [Figure 6] Figure 6 shows an example of the display screen by the information processing device in the third embodiment. [Figure 7] Figure 7 is a block diagram showing the configuration of the information processing device in the fourth embodiment. [Figure 8] Figure 8 is a flowchart showing the flow of information processing operations performed by the information processing device in the fourth embodiment. [Figure 9] Figure 9 is a flowchart showing the flow of information processing operations performed by the information processing device in the fourth embodiment. [Figure 10] Figure 10 is a block diagram showing the configuration of the information processing device in the fifth embodiment. [Figure 11] Figure 11 shows an example of the display screen by the information processing device in the fifth embodiment. [Figure 12] Figure 12 is a block diagram showing the configuration of the information processing device in the sixth embodiment. [Figure 13] Figure 13 is a flowchart showing the flow of information processing operations performed by the information processing device in the sixth embodiment. [Figure 14] Figure 14 shows an example of the display screen by the information processing device in the sixth embodiment. [Modes for carrying out the invention]

[0009] The following describes embodiments of the information processing device, information processing method, and recording medium with reference to the drawings. [1: First Embodiment]

[0010] A first embodiment of the information processing device, information processing method, and recording medium will be described below. The first embodiment of the information processing device, information processing method, and recording medium will be described using an information processing device 1 to which the first embodiment of the information processing device, information processing method, and recording medium is applied. [1-1: Configuration of Information Processing Device 1]

[0011] Referring to FIG. 1, the configuration of the information processing apparatus 1 in the first embodiment will be described. FIG. 1 is a block diagram showing the configuration of the information processing apparatus 1 in the first embodiment.

[0012] As shown in FIG. 1, the information processing apparatus 1 includes an acquisition unit 11, a first estimation unit 12, and an estimation control unit 13. The acquisition unit 11 performs an acquisition operation of acquiring a surface image including the fingerprint of the target person. The first estimation unit 12 performs a first estimation operation of estimating the pattern of the fingerprint from the acquired surface image. The estimation control unit 13 controls the acquisition unit 11 and the first estimation unit 12 so as to repeat the acquisition operation and the first estimation operation until a predetermined number of surface images estimated to have the first pattern are acquired. [1-2: Technical Effects of the Information Processing Apparatus 1]

[0013] Since the information processing apparatus 1 in the first embodiment repeats the acquisition operation and the first estimation operation until a predetermined number of surface images estimated to have the first pattern are acquired, the pattern of the fingerprint can be accurately estimated. [2: Second Embodiment]

[0014] The second embodiment of the information processing apparatus, the information processing method, and the recording medium will be described. Hereinafter, the second embodiment of the information processing apparatus, the information processing method, and the recording medium will be described using the information processing apparatus 2 to which the second embodiment of the information processing apparatus, the information processing method, and the recording medium is applied. [2-1: Configuration of the Information Processing Apparatus 2]

[0015] Referring to FIG. 2, the configuration of the information processing apparatus 2 in the second embodiment will be described. FIG. 2 is a block diagram showing the configuration of the information processing apparatus 2 in the second embodiment.

[0016] As shown in Figure 2, the information processing device 2 comprises an arithmetic unit 21 and a storage device 22. Furthermore, the information processing device 2 may also include a communication device 23, an input device 24, and an output device 25. However, the information processing device 2 does not have to include at least one of the communication device 23, the input device 24, and the output device 25. The arithmetic unit 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.

[0017] The arithmetic unit 21 includes, for example, at least one of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), and an FPGA (Field Programmable Gate Array). The arithmetic unit 21 reads a computer program. For example, the arithmetic unit 21 may read a computer program stored in the storage device 22. For example, the arithmetic unit 21 may read a computer program stored in a computer-readable and non-temporary recording medium using a recording medium reading device (not shown) provided by the information processing device 2 (for example, an input device 24 described later). The arithmetic unit 21 may obtain a computer program from a device (not shown) located outside the information processing device 2 via a communication device 23 (or other communication device) (i.e., it may download or read the program). The arithmetic unit 21 executes the read computer program. As a result, logical functional blocks for performing the operations that the information processing device 2 should perform are realized within the arithmetic unit 21. In other words, the arithmetic unit 21 can function as a controller for realizing logical functional blocks necessary for the information processing device 2 to perform its operations (in other words, processing).

[0018] Figure 2 shows an example of a logical functional block implemented within the arithmetic unit 21 to perform information processing operations. As shown in Figure 2, the arithmetic unit 21 implements an acquisition unit 211, which is a specific example of the "acquisition means" described in the appendix below; a first estimation unit 212, which is a specific example of the "first estimation means" described in the appendix below; an estimation control unit 213, which is a specific example of the "estimation control means" described in the appendix below; and a second estimation unit 214, which is a specific example of the "second estimation means" described in the appendix below. However, the arithmetic unit 21 does not necessarily have to include the second estimation unit 214. The operations of the acquisition unit 211, the first estimation unit 212, the estimation control unit 213, and the second estimation unit 214 will be described later with reference to Figure 3.

[0019] In this specification, "acquisition" may also refer to an active acquisition in which the device retrieves data stored in another device, storage medium, etc., based on user input or program instructions. Active acquisition may include, for example, requesting or querying another device to receive data, or accessing and reading data from another device, storage medium, etc. In addition, in this specification, "acquisition" may also refer to a passive acquisition in which the device inputs data output from another device to its own device based on user input or program instructions. Passive acquisition may include, for example, receiving data that is distributed (or transmitted, push notification, etc.), or selecting and acquiring data or information from the received data or information. In addition, in this specification, "acquisition" may also refer to generating new data by editing data (converting to text, rearranging data, extracting some data, changing file format, etc.) and acquiring that new data.

[0020] The storage device 22 is capable of storing desired data. For example, the storage device 22 may temporarily store computer programs executed by the arithmetic unit 21. The storage device 22 may temporarily store data that the arithmetic unit 21 uses temporarily when it is executing a computer program. The storage device 22 may store data that the information processing device 2 stores long-term. The storage device 22 may include at least one of the following: RAM (Random Access Memory), ROM (Read Only Memory), hard disk drive, magneto-optical disk drive, SSD (Solid State Drive), and disk array drive. In other words, the storage device 22 may include non-temporary recording media.

[0021] The communication device 23 can communicate with devices outside the information processing device 2 via a communication network (not shown). The communication device 23 may have a communication interface based on standards such as Ethernet (registered trademark), Wi-Fi (registered trademark), Bluetooth (registered trademark), or USB (Universal Serial Bus).

[0022] The input device 24 is a device that receives information input to the information processing device 2 from outside the information processing device 2. For example, the input device 24 may include an operating device that can be operated by an operator of the information processing device 2 (for example, at least one of a keyboard, mouse trackball, touch panel, pointing device such as a pen tablet, buttons, etc.). For example, the input device 24 may include a reading device that can read information recorded as data on a recording medium that can be attached externally to the information processing device 2.

[0023] The output device 25 is a device that outputs information to the outside of the information processing device 2. For example, the output device 25 may output information as an image. That is, the output device 25 may include a display device (so-called display) capable of displaying an image representing the information to be output. Examples of display devices include liquid crystal displays and OLED (Organic Light Emitting Diode) displays. For example, the output device 25 may output information as sound. That is, the output device 25 may include an audio device (so-called speaker) capable of outputting sound. For example, the output device 25 may output information onto paper. That is, the output device 25 may include a printing device (so-called printer) capable of printing desired information onto paper. Furthermore, the input device 24 and the output device 25 may be integrally formed as a touch panel.

[0024] Note that the hardware configuration shown in Figure 2 is just an example, and additional devices other than those shown in Figure 2 may be included, or some devices may be omitted. Also, some devices may be replaced with other devices having similar functions. Furthermore, some functions of the second embodiment may be provided by other devices via a network. The functions of the second embodiment may be implemented by distributing them across multiple devices. Thus, the hardware configuration shown in Figure 2 can be modified as appropriate. [2-2: Fingerprint Patterns]

[0025] Fingerprints of each human finger, including those of newborns, can be classified into five types of fingerprint patterns: whorl (W), double loop (D), left loop (L), right loop (R), and arch (A). The term "fingerprint pattern" may also refer to the overall pattern of the fingerprint. The term "fingerprint pattern" may also be used.

[0026] A whorl pattern (W) is a fingerprint pattern with a ring-shaped or spiral-shaped ridge with deltas on either side. A non-flowing circular pattern exists in the center of the pattern, with deltas on both sides of the center. Depending on the fingerprint acquisition conditions, a delta may be present on only one side. The deltas may also be referred to as "deltas." Separation pattern (D) is a fingerprint pattern with deltas on either side of a double hoof-shaped or similar ridge. A circular pattern containing a flow exists in a tomoe-like pattern in the center of the pattern, with deltas on both sides of the center of the pattern. Depending on the circumstances of fingerprint acquisition, deltas may be present on only one side. The left-hand loop print (L) is a fingerprint pattern that includes loop lines and has a delta to the right of the direction of flow. A pattern exists that flows from the left towards the center of the pattern, with a delta to the right of the direction of flow. Note that depending on the circumstances of fingerprint acquisition, a delta may not be present. In this embodiment, the same terminology is used for both the right-hand and left-hand patterns. The right-hand loop print (R) is a fingerprint pattern that includes loop lines and has a delta to the left of the direction of flow. A pattern exists that flows from the right towards the center of the pattern, with a delta to the left of the direction of flow. Note that depending on the circumstances of fingerprint acquisition, a delta may not be present. In this embodiment, the same terminology is used for both the right-hand and left-hand patterns. The arch-shaped pattern (A) is a fingerprint pattern formed by arch-shaped glands. A delta pattern may appear in the center of the pattern, but more often than not, the pattern does not contain a delta.

[0027] Alternatively, the first estimation unit 212 may determine which of the six types of fingerprint patterns each of the multiple fingerprint images possesses is one of the five types of fingerprint patterns plus "Unknown (UK)". If the first estimation unit 212 cannot determine that the pattern of a fingerprint image is one of the five types of fingerprint patterns, it may determine that the pattern of the fingerprint image is "UK". Note that the five types of fingerprint patterns described above are just examples, and other classifications may be adopted. For example, fingerprints may be classified into eight types of fingerprint patterns: Plain Arch (PA), Tented Arch (TA), Ulnar Loop (UL), Radial Loop (RL), Double Loop (DL), Plain Whorl (PW), Central Pocket Loop Whorl (CW), and Accidental Whorl (AW). [2-3: Information processing operations performed by the information processing device 2]

[0028] Referring to Figure 3, the flow of information processing operations performed by the information processing device 2 in the second embodiment will be explained. Figure 3 is a flowchart showing the flow of information processing operations performed by the information processing device 2 in the second embodiment. In the second embodiment, when the information processing device 2 acquires a predetermined number of surface images that are estimated to have a first pattern, it may estimate that the first pattern is the pattern of the subject's fingerprint. In the second embodiment, the predetermined number may be four. That is, in the second embodiment, when four surface images that are estimated to have the same fingerprint pattern are acquired, the same fingerprint pattern may be estimated to be the pattern of the fingerprint. Note that the predetermined number of surface images to acquire may be any number. The larger the predetermined number, the better the accuracy of estimating the pattern of the fingerprint.

[0029] As shown in Figure 3, n is set to zero when the information processing operation starts. n is a variable that counts the acquired surface images.

[0030] The acquisition unit 211 performs an acquisition operation to acquire a surface image including the subject's fingerprints (step S20). The acquisition operation may be an operation to acquire a surface image of the fingerprints of a predetermined finger of the subject. The subject may be a newborn. In this embodiment, a newborn may refer to an infant in the very early stages, within a few hours of birth. For example, in this embodiment, a newborn may refer to an infant within half a day of birth. In this embodiment, a newborn may refer to an infant in the period before a situation arises where it is necessary to identify the person. A situation where it is necessary to identify the person may be, for example, a situation where the person is moved from the place of birth (e.g., a hospital) to another place (e.g., home). The subject may be a newborn up to four weeks old, an infant, a toddler, or an adult.

[0031] Fingerprint images taken from the surface of a finger can be used as stable biometric information obtained from newborns. Stable biometric information may refer to biometric information that does not change much with growth, etc., and can be used for individual identification. The pitch of a newborn's fingerprint is much finer than that of an adult. For this reason, the acquisition unit 211 may acquire a high-resolution fingerprint image.

[0032] The first estimation unit 212 performs a first estimation operation to estimate the pattern of a fingerprint from the acquired surface image (step S21). The first estimation operation may be an operation to estimate which of a predetermined set of patterns the pattern of the fingerprint from the acquired surface image is. For example, the predetermined set of patterns may be five types of fingerprint patterns: "W", "D", "L", "R", and "A". In this case, the first estimation operation may be an operation to estimate which of the fingerprint patterns "W", "D", "L", "R", and "A" the pattern of the fingerprint contained in the surface image is.

[0033] The first estimation unit 212 may use an algorithm to estimate which of the five (or six, or any) fingerprint patterns it is. The first estimation unit 212 may use a determination model constructed by machine learning (for example, a determination model using a neural network) to determine which of the five (or six, or any) fingerprint patterns it is. The first estimation unit 212 may use a determination model constructed by deep learning, which is an example of machine learning, to determine which of the five (or six, or any) fingerprint patterns it is.

[0034] The estimation control unit 213 determines whether n is less than 4, which is a predetermined number (step S22). If n is less than 4 (step S22: Yes), the estimation control unit 213 adds 1 to n (step S23). The estimation control unit 213 determines whether n is 4, which is a predetermined number (step S24). If n is less than 4 (step S24: No), the process returns to step S20. The estimation control unit 213 controls the process to repeat steps S20 to S24 a predetermined number of times until n changes from 0 to a predetermined number.

[0035] If n is 4, a predetermined number (step S24: Yes), the estimation control unit 213 determines the number of surface images to acquire for the first pattern (steps S25 to S27). In the second embodiment, the first pattern may be the fingerprint pattern with the largest number of surface images estimated to have the same fingerprint pattern. For example, suppose the number of surface images acquired is 4, the number of surface images estimated to be fingerprint pattern W is 1, the number of surface images estimated to be fingerprint pattern D is 1, the number of surface images estimated to be fingerprint pattern L is 1, and the number of surface images estimated to be fingerprint pattern R is 1. In this case, the number of surface images acquired for the first pattern is 0, and the estimation control unit 213 determines No in steps S25, S26, and S27, and proceeds to step S28. The estimation control unit 213 substitutes 4 for Dn (step S28) and returns to step S20. Dn may be a variable indicating the number of surface images to be acquired. In other words, if the number of surface images obtained for the same fingerprint pattern is zero, four more surface images may be obtained and the pattern estimated again.

[0036] After the determination in step S24 is Yes, the determination in step S22 is No. Therefore, after steps S20, S21, and S22, the process proceeds to step S29. The estimation control unit 213 subtracts 1 from Dn (step S29) and determines whether Dn is 0 or not (step S30). The estimation control unit 213 repeats the operations of steps S20, S21, S22, S29, and S30 until Dn becomes 0.

[0037] If step S28 is completed, four new surface images are acquired, so in the second step S25, eight surface images are acquired. For example, suppose the number of surface images estimated to be fingerprint pattern W is 3, the number of surface images estimated to be fingerprint pattern D is 2, the number of surface images estimated to be fingerprint pattern L is 2, and the number of surface images estimated to be fingerprint pattern R is 1. In this case, the first pattern is fingerprint pattern W, so the number of surface images acquired for the first pattern is 3. The estimation control unit 213 determines No in step S25, Yes in step S26, and proceeds to step S32. The estimation control unit 213 assigns 1 to Dn (step S32) and returns to step S20. The estimation control unit 213 performs the operations of steps S20, S21, S22, S29, and S30 once, and proceeds to step S25.

[0038] If step S32 is performed after step S28, one new surface image is acquired, so in the third step S25, nine surface images have been acquired. For example, suppose the number of surface images estimated to be fingerprint pattern W is 4, the number of surface images estimated to be fingerprint pattern D is 2, the number of surface images estimated to be fingerprint pattern L is 2, and the number of surface images estimated to be fingerprint pattern R is 1. In this case, the first pattern is fingerprint pattern W, so the number of surface images acquired for the first pattern is 4. The estimation control unit 213 determines Yes in step S25 and proceeds to step S33. That is, the information processing device 2 acquires surface images of the subject's fingers and estimates the fingerprint pattern from the acquired surface images, repeating this process until a predetermined number of surface images estimated to be the first pattern among the estimated fingerprint patterns are reached.

[0039] The second estimation unit 214 performs a second estimation operation (step S33) in which, when it has acquired a predetermined number of surface images that the first estimation unit 212 has estimated to have a first pattern, it estimates that the first pattern is the pattern of the subject's fingerprint. In the second embodiment, the second estimation unit 214 estimates that the first pattern that first reaches a predetermined number is the pattern of the subject's fingerprint.

[0040] In the determinations made in steps S25 to S27, if the number of surface images of the first pattern obtained is 2 (step S25: No, step S26: No, and step S27: Yes), the process proceeds to step S31, where the estimation control unit 213 substitutes 2 for Dn (step S31) and returns to step S20. In this case as well, the estimation control unit 213 repeats the operations of steps S20, S21, S22, S29, and S30 until Dn becomes 0.

[0041] In other words, the estimation control unit 213 controls the acquisition unit 211 and the first estimation unit 212 to repeat the acquisition operation (step S20) and the first estimation operation (step S21) until a predetermined number of surface images that the first estimation unit 212 has estimated to have a first pattern are acquired.

[0042] The five fingerprint patterns described above are merely examples. Fingerprints may be classified into more than five types, for example, 20 or more fingerprint patterns. Alternatively, fingerprints may be classified into three types, for example, a first fingerprint pattern that does not include deltas, a second fingerprint pattern that includes one delta, and a third fingerprint pattern that includes two deltas. Alternatively, fingerprints may be classified into two types, for example, a delta-free fingerprint pattern that does not include deltas, and a delta-present fingerprint pattern that includes deltas. Reducing the number of classifications can reduce errors in pattern estimation.

[0043] For example, the user may specify the number of fingerprint classifications according to the requirements for using information about the newborn. In this case, the first estimation unit 212 may estimate which of the number of fingerprint patterns specified by the user is the fingerprint pattern.

[0044] Furthermore, the "acquisition means" described in the appendix below may be an imaging unit (or imaging means). That is, the information processing device 2 may be an image imaging device, and it may repeatedly alternate between a first process of capturing a surface image including the subject's fingerprint and a second process of estimating the pattern of the fingerprint from the captured surface image, and may terminate the repetition when a predetermined number of surface images estimated to contain the first pattern have been captured from among the multiple estimated patterns. In this case, the image imaging device as an information processing device may have multiple imaging units (or imaging means) as "acquisition means". Each acquisition means may acquire a surface image of a different finger. The surface image may be a fingerprint image. This makes it possible to speed up processing when acquiring multiple surface images of multiple fingers. [2-4: Variations]

[0045] As a variation of this embodiment, the estimation control unit 213 may repeatedly process data until the difference between the number of acquired fingerprint patterns and the second most acquired fingerprint patterns reaches a predetermined number, even if the acquisition number condition is met, and then determine the first pattern. In this case, if the difference between the number of acquired fingerprint patterns and the second most acquired fingerprint patterns is large and represents a significant difference, the fingerprint pattern with the highest acquisition number can be considered more likely to be the subject's fingerprint pattern, enabling highly accurate estimation. [2-5: Technical effects of the information processing device 2]

[0046] The skin surface of newborns shortly after birth is often covered with sebum, amniotic fluid, etc., making it difficult to accurately estimate the fingerprint pattern of a newborn. This is especially true when postpartum care is inadequate or when medical facilities are insufficient. Alternatively, if sebum, amniotic fluid, etc. are not removed to protect the newborn's health, it is often difficult to accurately estimate the fingerprint pattern of a newborn.

[0047] In contrast, the information processing device 2 in the second embodiment performs a second estimation operation in which, when a predetermined number of surface images estimated to have the first pattern are acquired, the first pattern is estimated to be the pattern of the subject's fingerprint, thereby enabling highly accurate estimation. The predetermined number may be a number that can be determined to be likely to be estimated. Therefore, when a predetermined number of surface images estimated to have the first pattern are acquired, it means that a number of surface images that can be determined to be likely to be estimated are acquired, so the information processing device 2 can perform highly accurate estimation. [3: Third Embodiment]

[0048] A third embodiment of the information processing device, information processing method, and recording medium will be described below. In the following, the third embodiment of the information processing device, information processing method, and recording medium will be described using an information processing device 3 to which the third embodiment of the information processing device, information processing method, and recording medium is applied. [3-1: Configuration of Information Processing Device 3]

[0049] The configuration of the information processing device 3 in the third embodiment will be described with reference to Figure 4. Figure 4 is a block diagram showing the configuration of the information processing device 3 in the third embodiment.

[0050] As shown in Figure 4, the information processing device 3 in the third embodiment includes a calculation unit 21 and a storage device 22, similar to the information processing device 2 in the second embodiment. Furthermore, the information processing device 3 may also include a communication device 23, an input device 24, and an output device 25, similar to the information processing device 2 in the second embodiment. However, the information processing device 3 does not have to include at least one of the communication device 23, the input device 24, and the output device 25. The information processing device 3 in the third embodiment differs from the information processing device 2 in that the calculation unit 21 further includes a display control unit 315. In the third embodiment, the output device 25 includes a display device (so-called display) capable of displaying an image showing the information to be output. The display control unit 315 causes the display device to display a display screen D containing information about the control operation of the estimation control unit 213. The control operation of the estimation control unit 213 is an operation that repeats the acquisition operation and the first estimation operation until a predetermined number of surface images estimated to have a first pattern are acquired. The information about the control operation of the estimation control unit 213 includes information about the number of surface images estimated to have the same pattern. The information processing device 3 may provide the administrator of the information processing device 3 with information regarding the control operation of the estimation control unit 213 as information to notify the administrator of the information processing device 3 of the progress of the information processing operation of the information processing device 3.

[0051] Other features of the information processing device 3 may be the same as other features of the information processing device 2 in the second embodiment. For this reason, the following will describe in detail the parts that differ from each embodiment already described, and will omit explanations of other overlapping parts as appropriate. [3-2: Information processing operations performed by the information processing device 3]

[0052] The information processing operations performed by the information processing device 3 in the third embodiment will be described with reference to Figures 5 and 6. Figure 5 is a flowchart showing the flow of information processing operations performed by the information processing device 3 in the third embodiment. Figure 6 is a diagram showing an example of the display screen D.

[0053] As shown in Figure 5, the information processing device 3 in the third embodiment differs from the information processing device 2 in the second embodiment in that it performs a display update operation after steps S23, S28, S31, S32, S33, and S29.

[0054] Figure 6(a) shows an example of display screen D when the information processing operation shown in Figure 5 is started. In the third embodiment, the predetermined number may be 4, and the display control unit 315 may display display screen D including 4 boxes as the predetermined number. The display control unit 315 may represent the number of acquired surface images by the number of check marks. In other words, the display control unit 315 may represent the number of surface images to be acquired by the number of boxes without check marks. That is, the display control unit 315 may prompt the administrator of the information processing device 3 to take a surface image including the subject's fingerprint by displaying display screen D including boxes without check marks. The administrator of the information processing device 3 may be the person who takes the surface image including the subject's fingerprint and inputs it into the information processing device 3. In this case, the acquisition unit 211 acquires the input surface image.

[0055] Following the first acquisition operation, the display control unit 315 may update the display screen D from the example shown in Figure 6(a) to the example shown in Figure 6(b) by the operation in step S34. Following the second acquisition operation, the display control unit 315 may update the display screen D from the example shown in Figure 6(b) to the example shown in Figure 6(c). Following the third acquisition operation, the display control unit 315 may update the display screen D from the example shown in Figure 6(c) to the example shown in Figure 6(d). Following the fourth acquisition operation, the display control unit 315 may update the display screen D from the example shown in Figure 6(d) to the example shown in Figure 6(e).

[0056] When the acquisition of four surface images, which is a predetermined number, is complete (Step S24: Yes), the display control unit 315 updates the display screen D according to the determination result of the number of acquired first patterns.

[0057] If the number of surface images having the first pattern acquired is less than two (step S25: No, step S26: No, step S27: No), the display control unit 315 may update the display screen D exemplified in Figure 6(e) to the display screen D exemplified in Figure 6(a) (step S35). That is, the display control unit 315 may display a display screen D that includes information to make the administrator of the information processing device 3 understand that it is necessary to acquire four surface images. In this case, in the subsequent step S39, the display control unit 315 may sequentially update from the display screen D exemplified in Figure 6(a) to the display screen D exemplified in Figure 6(b), from the display screen D exemplified in Figure 6(b) to the display screen D exemplified in Figure 6(c), from the display screen D exemplified in Figure 6(c) to the display screen D exemplified in Figure 6(d), and from the display screen D exemplified in Figure 6(d) to the display screen D exemplified in Figure 6(e).

[0058] If two surface images having the first pattern have been acquired (step S25: No, step S26: No, step S27: Yes), the display control unit 315 may update the display screen D exemplified in Figure 6(e) to the display screen D exemplified in Figure 6(f) (step S36). The display control unit 315 may also represent the number of valid surface images by shading a box. That is, the display control unit 315 may display a display screen D that includes information informing the administrator that two surface images of the first pattern have been acquired and that two more surface images of the first pattern are needed. In this case, in the subsequent step S39, the display control unit 315 may sequentially update from the display screen D exemplified in Figure 6(f) to the display screen D exemplified in Figure 6(g), and from the display screen D exemplified in Figure 6(g) to the display screen D exemplified in Figure 6(h).

[0059] If three surface images having the first pattern have been acquired (step S25: No, step S26: Yes), the display control unit 315 may update the display screen D exemplified in Figure 6(e) to the display screen D exemplified in Figure 6(i) (step S37). The display control unit 315 may also display a display screen D that includes information informing the administrator that three surface images of the first pattern have been acquired and that one more surface image of the first pattern is needed. In this case, in the subsequent step S39, the display control unit 315 may update the display screen D exemplified in Figure 6(i) to the display screen D exemplified in Figure 6(j).

[0060] If four first patterns have been acquired (Step S25: Yes), the display control unit 315 may update the display screen D shown in Figure 6(e) to the display screen D shown in Figure 6(k) (Step S38). This display screen D may be a screen that informs the administrator that four surface images of the first patterns have been acquired and that all the necessary surface images are available. [3-3: Technical Effects of Information Processing Device 3]

[0061] In the third embodiment, the information processing device 3 displays a display screen containing information about control operations on a display device, so, for example, the administrator of the information processing device 3 can visually understand the status of information processing by the information processing device 3. Furthermore, since the information about control operations includes information about the number of surface images that are estimated to have the same pattern, the administrator of the information processing device 3 can know the progress of the information processing operations by the information processing device 3. [4: Fourth Embodiment]

[0062] A fourth embodiment of the information processing device, information processing method, and recording medium will be described below. The fourth embodiment of the information processing device, information processing method, and recording medium will be described using an information processing device 4 to which the fourth embodiment of the information processing device, information processing method, and recording medium is applied. [4-1: Configuration of Information Processing Device 4]

[0063] The configuration of the information processing device 4 in the fourth embodiment will be described with reference to Figure 7. Figure 7 is a block diagram showing the configuration of the information processing device 4 in the fourth embodiment.

[0064] As shown in Figure 7, the information processing device 4 in the fourth embodiment includes an arithmetic unit 21 and a storage device 22, similar to the information processing device 2 in the second embodiment and the information processing device 3 in the third embodiment. Furthermore, the information processing device 4 may also include a communication device 23, an input device 24, and an output device 25, similar to the information processing device 2 in the second embodiment and the information processing device 3 in the third embodiment. However, the information processing device 4 does not have to include at least one of the communication device 23, the input device 24, and the output device 25. The information processing device 4 in the fourth embodiment differs from the information processing device 2 in the second embodiment and the information processing device 3 in the third embodiment in that the arithmetic unit 21 further includes a registration control unit 416, the first estimation unit 212 includes a calculation unit 417, and the storage device 22 includes a pattern database DB. The pattern database DB may be a database that stores information indicating the pattern of the subject's fingerprint and finger information that associates the surface image of the pattern of the subject's fingerprint. However, the pattern database DB may be implemented in a storage mechanism other than the storage device 22. For example, the information processing device 4 may be an edge server provided for each hospital. In this case, the pattern database DB may be implemented in the storage device provided by the cloud server. In this case, multiple edge servers may perform registration control for the pattern database DB. Other features of the information processing device 3 may be the same as other features of the information processing device 2 in the second embodiment. For this reason, the following will describe in detail the parts that differ from each embodiment already described, and will omit explanations of other overlapping parts as appropriate. [4-2: Information processing operations performed by the information processing device 4]

[0065] The information processing operations performed by the information processing device 4 in the fourth embodiment will be described with reference to Figures 8 and 9. Figures 8 and 9 are flowcharts showing the flow of information processing operations performed by the information processing device 4 in the fourth embodiment.

[0066] As shown in Figure 8, in the fourth embodiment, after the acquisition operation in step S20, the calculation unit 417 performs a calculation operation to calculate a score indicating the probability that the pattern in the surface image is one of a predetermined set of multiple types of fingerprint patterns (step S40). In other words, the calculation unit 417 calculates the likelihood that the pattern in the surface image is at least one of the predetermined set of multiple types of fingerprint patterns.

[0067] For example, the calculation unit 417 may calculate the probability that the pattern in the surface image is one of several types of fingerprint patterns as a score that falls within the range of 0 or more and 1 or less. In this case, the calculation unit 417 may be considered to be calculating a score that indicates the probability that the pattern in the surface image is one type of fingerprint pattern as a probability between 0% and 100%.

[0068] In the fourth embodiment, the first estimation unit 212 estimates which of several types of fingerprint patterns the pattern of the surface image is based on the score calculated by the calculation unit 417 (step S21). The first estimation unit 212 may estimate the fingerprint pattern with the highest score as the most likely pattern of the surface image. Alternatively, the first estimation unit 212 may set the highest score as the score (S) of the corresponding surface image.

[0069] The calculation unit 417 determines whether the score (S) of the surface image exceeds a predetermined score threshold (step S41). If the score (S) of the surface image exceeds the predetermined score threshold, the first estimation unit 212 performs the operations of steps S22 to S24, step S29, and step S30 in the same manner as in the second embodiment. That is, in the fourth embodiment, if the score (S) of the surface image exceeds the score threshold, the first estimation unit 212 may use the acquired surface image as the target for subsequent processing.

[0070] The predetermined score threshold may be 0.51. In this case, the first estimation unit 212 may determine whether the score (S) of the surface image exceeds 0.51. If the score (S) of the surface image exceeds 0.51, the first estimation unit 212 may select the acquired surface image for subsequent processing. In other words, the first estimation unit 212 may select the acquired surface image for subsequent processing if there is a greater than 51% probability that the pattern of the surface image is the most likely fingerprint pattern. When the predetermined score is set to 0.51, surface images with accurately estimated patterns can be selected for subsequent processing.

[0071] If the score (S) of the surface image is less than 0.51, the process returns to step S20. In this case, the first estimation unit 212 may discard the acquired surface image.

[0072] As shown in Figure 9, the first estimation unit 212 calculates the number of surface images (IN) estimated to have a fingerprint pattern for each of the predetermined multiple types of fingerprint patterns, and also calculates the sum of the scores (SS) of the surface images estimated to have a fingerprint pattern (step S42).

[0073] The second estimation unit 214 determines the fingerprint pattern (P1) with the largest sum of scores (SS) of each surface image estimated to have the same fingerprint pattern (step S43). In the third embodiment, the fingerprint pattern (P1) with the largest sum of scores (SS) is also referred to as the first pattern.

[0074] The second estimation unit 214 determines whether the number of surface images (IN) corresponding to the first pattern is 4, which is a predetermined number (step S25).

[0075] If the number of surface images (IN) corresponding to the first pattern is 4 (Step S25: Yes), the second estimation unit 214 estimates that the reliability of the first pattern is high (Step S44). The second estimation unit 214 estimates that the first pattern is a pattern found in the subject's fingerprint (Step S33).

[0076] The registration control unit 416 registers finger information that associates information indicating a first pattern with a predetermined number of surface images that are estimated to have the first pattern (step S45). The registration control unit 416 deletes surface images other than the predetermined number of surface images estimated to have the first pattern from among the multiple surface images acquired by the acquisition unit 211 until the first estimation unit 212 acquires a predetermined number of surface images that are estimated to have the first pattern. Deleting a surface image may also be an operation to delete a surface image temporarily stored in the storage device 22 from the storage device 22 and make it unusable in subsequent processing. The registration control unit 416 may discard surface images that were not estimated to have the first pattern from among the surface images acquired by the acquisition unit 211 in order to eliminate fluctuations in the estimated value caused by saving surface images that show different patterns and to improve the estimation accuracy. The registration control unit 416 may also register only the predetermined number of surface images that are estimated to have the first pattern, associating them with information indicating the first pattern.

[0077] For example, if a predetermined number of images is defined as four, and three surface images are estimated to have the first pattern and one surface image is determined to have the second pattern, then one additional surface image is acquired. If this additionally acquired surface image is estimated to have the first pattern, then there will be four surface images with the first pattern and one surface image determined to have the second pattern. In this case, since there are now four surface images with the first pattern, the surface image with the second pattern is discarded as an unnecessary surface image, and the four surface images with the first pattern are registered.

[0078] For example, a predetermined number of surface images that are estimated to have the first pattern and are registered by the registration control unit 416 in association with information indicating the first pattern may be used in the machine learning of the judgment model described above. That is, the surface images registered by the registration control unit 416 may be used as samples of surface images of a newborn's finger having the first pattern. For example, suppose a surface image that does not have the first pattern (i.e., a surface image that does not resemble the first pattern, for example, a surface image that has the second pattern) is registered in association with information indicating the first pattern. If a surface image that does not resemble the first pattern and is associated with information indicating the first pattern is used in machine learning, it may be detrimental to improving the accuracy of the judgment model's determination. In this embodiment, after the accuracy satisfies the condition for determining the pattern that the subject's fingerprint has, surface images that have a pattern different from the determined pattern are deleted from the patterns acquired by the acquisition operation and calculation operation, which can contribute to improving the accuracy of the estimation.

[0079] If the number of surface images (IN) corresponding to the first pattern is not 4 (step S25: No), the second estimation unit 214 determines whether the number of surface images (IN) corresponding to the first pattern is 3 or not (step S26).

[0080] If the number of surface images (IN) corresponding to the first pattern is a predetermined number of 3 (Step S26: Yes), the second estimation unit 214 determines whether the difference between the sum of scores corresponding to the first pattern (SS1) and the sum of scores corresponding to the pattern with the second largest sum of scores (SS2) exceeds 1.75 (Step S46).

[0081] If the difference exceeds 1.75 (Step S46: Yes), the second estimation unit 214 estimates the reliability of the first pattern to be high (Step S47). On the other hand, if the difference is 1.75 or less (Step S46: No), the second estimation unit 214 estimates the reliability of the first pattern to be moderate (Step S48). That is, the second estimation unit 214 estimates the reliability of the pattern with the largest total score to be higher than the case where the difference is less than the threshold if the number of surface images (IN) corresponding to the pattern with the largest total score (first pattern) among the surface images estimated to have the same pattern is less than a predetermined number of 4, and the difference between the total score (SS1) corresponding to the pattern with the largest total score and the total score (SS2) corresponding to the pattern with the second largest total score is greater than or equal to the threshold.

[0082] If the number of surface images (IN) corresponding to the first pattern is not 3 (step S26: No), the second estimation unit 214 determines whether the number of surface images (IN) corresponding to the first pattern is 2 or not (step S27).

[0083] If the number of surface images (IN) corresponding to the first pattern is a predetermined number of 2 (Step S27: Yes), the second estimation unit 214 determines whether the difference between the sum of scores corresponding to the first pattern (SS1) and the sum of scores corresponding to the pattern with the second largest sum of scores (SS2) exceeds 1.0 (Step S49).

[0084] If the difference exceeds 1.0 (Step S49: Yes), the second estimation unit 214 estimates the confidence level of the first pattern to be moderate (Step S50). On the other hand, if the difference is 1.0 or less (Step S49: No), the second estimation unit 214 estimates the confidence level of the first pattern to be low (Step S51).

[0085] The estimation control unit 213 controls the calculation unit 417 to repeat the acquisition and calculation operations until the probability satisfies the conditions for determining the pattern of the subject's fingerprint. The conditions for determining the pattern of the subject's fingerprint may include at least one of the following: the number of surface images of the first pattern reaches a predetermined number, and the difference in the sum of scores exceeds a threshold. For example, the estimation control unit 213 may perform the operation of step S33 after the operation of step S47. That is, even if the number of surface images of the first pattern is less than a predetermined number, a form may be adopted in which the pattern of the subject's fingerprint is determined. In other words, the information processing device 4 may acquire a surface image of the subject's finger, calculate the probability from the captured surface image that the fingerprint is at least one of a plurality of patterns, and repeat the process of determining whether the probability satisfies the conditions for determining the pattern, as long as the conditions are not met.

[0086] Furthermore, the fingerprint information registered in the pattern database DB may, in the future, be integrated into, for example, a national information DB that stores information identifying all citizens managed by the government. [4-3: Technical effects of the information processing device 4]

[0087] In the fourth embodiment, the information processing device 4 performs confidence estimation and estimates the pattern based on the confidence level, thereby enabling more accurate pattern estimation. Furthermore, since the information processing device 4 registers the surface image having the estimated pattern, the accuracy of the first estimation operation can be improved. [5: Fifth Embodiment]

[0088] A fifth embodiment of the information processing device, information processing method, and recording medium will be described below. The fifth embodiment of the information processing device, information processing method, and recording medium will be described using an information processing device 5 to which the fifth embodiment of the information processing device, information processing method, and recording medium is applied. [5-1: Configuration of Information Processing Device 5]

[0089] The configuration of the information processing device 5 in the fifth embodiment will be described with reference to Figure 10. Figure 10 is a block diagram showing the configuration of the information processing device 5 in the fifth embodiment.

[0090] As shown in Figure 10, the information processing device 5 in the fifth embodiment includes a arithmetic unit 21 and a storage device 22, similar to the information processing devices 2 in the second embodiment to the information processing device 4 in the fourth embodiment. Furthermore, the information processing device 5 may also include a communication device 23, an input device 24, and an output device 25, similar to the information processing device 2 in the second embodiment to the information processing device 4 in the fourth embodiment. However, the information processing device 5 does not have to include at least one of the communication device 23, the input device 24, and the output device 25. The information processing device 5 in the fifth embodiment differs from the information processing device 2 in the second embodiment and the information processing device 3 in the third embodiment in that the arithmetic unit 21 further includes a registration control unit 416, the first estimation unit 212 includes a calculation unit 417, and the storage device 22 includes a pattern database DB. Also, the information processing device 5 in the fifth embodiment differs from the information processing device 2 in the second embodiment and the information processing device 4 in the fourth embodiment in that the arithmetic unit 21 further includes a display control unit 315. In other words, the information processing device 5 in the fifth embodiment can display the confidence level of the estimated pattern on the display screen D. Other features of the information processing device 5 may be the same as at least one other feature of the information processing device 2 in the second embodiment to the information processing device 4 in the fourth embodiment. For this reason, the following will describe in detail the parts that differ from each embodiment already described, and will omit explanations of other overlapping parts as appropriate. [5-2: Information processing operations performed by the information processing device 5]

[0091] The information processing operations performed by the information processing device 5 in the fifth embodiment will be described with reference to Figure 11. Figure 11 is a diagram showing an example of the display screen D.

[0092] As shown in Figure 11, the information processing device 5 in the fifth embodiment can perform both confidence estimation and confidence display.

[0093] Similar to the fourth embodiment, in the fifth embodiment as well, the calculation unit 417 calculates a score indicating the likelihood that the pattern in the surface image is one of a predetermined number of fingerprint patterns. Based on the calculated score, the first estimation unit 212 estimates which of the multiple types of fingerprint patterns the pattern in the surface image is.

[0094] In step S44 shown in Figure 9, the display control unit 315 may cause the display screen D, illustrated in Figure 11(a), to be displayed on the display device. That is, the display control unit 315 may cause a horizontal line pattern indicating high reliability to be displayed in the box on the left.

[0095] Furthermore, in step S47 (step S46: Yes) shown in Figure 9, the display control unit 315 may display the display screen D illustrated in Figure 11(b) on the display device. That is, the display control unit 315 may display a horizontal line pattern indicating high reliability in the left box. On the other hand, in step S48 (step S46: No) shown in Figure 9, the display control unit 315 may display the display screen D illustrated in Figure 11(c) on the display device. That is, the display control unit 315 may display a vertical line pattern indicating medium reliability in the left box. In other words, the display control unit 315 displays the display screen D on the display device such that the display mode of the display screen D differs when the difference between the sum of scores corresponding to the pattern with the largest sum of scores for each surface image estimated to have the same pattern and the sum of scores corresponding to the pattern with the second largest sum of scores is greater than or equal to a threshold, and when the difference is less than a threshold.

[0096] Furthermore, in step S50 (step S49: Yes) shown in Figure 9, the display control unit 315 may display the display screen D illustrated in Figure 11(d) on the display device. That is, the display control unit 315 may display a vertical line pattern indicating medium reliability in the left box. On the other hand, in step S51 (step S49: No) shown in Figure 9, the display control unit 315 may display the display screen D illustrated in Figure 11(e) on the display device. That is, the display control unit 315 may leave all boxes blank and display a display screen D that indicates that a reliable surface image has not been obtained. [5-3: Technical Effects of Information Processing Device 5]

[0097] In the fifth embodiment, the information processing device 5 can inform the administrator of the reliability of the estimated pattern. [6: Sixth Embodiment]

[0098] A sixth embodiment of the information processing device, information processing method, and recording medium will be described below. In the following, the sixth embodiment of the information processing device, information processing method, and recording medium will be described using an information processing device 6 to which the sixth embodiment of the information processing device, information processing method, and recording medium is applied. [6-1: Configuration of Information Processing Device 6]

[0099] The configuration of the information processing device 6 in the sixth embodiment will be described with reference to Figure 12. Figure 12 is a block diagram showing the configuration of the information processing device 6 in the sixth embodiment.

[0100] As shown in Figure 12, the information processing device 6 in the sixth embodiment includes a arithmetic unit 21 and a storage device 22, similar to the information processing devices 2 in the second embodiment to 5 in the fifth embodiment. Furthermore, the information processing device 6 may also include a communication device 23, an input device 24, and an output device 25, similar to the information processing devices 2 in the second embodiment to 5 in the fifth embodiment. However, the information processing device 6 does not have to include at least one of the communication device 23, input device 24, and output device 25. The information processing device 6 in the sixth embodiment differs from the information processing device 2 in the second embodiment to 5 in the information processing device 5 in the second embodiment in that the arithmetic unit 21 further includes a matching unit 618. Other features of the information processing device 6 may be the same as at least one other feature of the information processing device 2 in the second embodiment to 5 in the information processing device 5 in the fifth embodiment. For this reason, the following will describe in detail the parts that differ from each embodiment already described, and will omit explanations of other overlapping parts as appropriate. [6-2: Information processing operations performed by the information processing device 6]

[0101] The information processing operations performed by the information processing device 6 in the sixth embodiment will be described with reference to Figures 13 and 14. Figure 13(a) is a flowchart showing the flow of the pattern registration operation performed by the information processing device 6 in the sixth embodiment, and Figure 13(b) is a flowchart showing the flow of the matching operation performed by the information processing device 6 in the sixth embodiment. Figure 14 is a diagram showing an example of the display screen D. [Registration operation]

[0102] As shown in Figure 13(a), the second estimation unit 214 estimates the pattern of the subject's fingerprint (step S100). The second estimation unit 214 may estimate the pattern of the fingerprint by the same operation as at least one of the information processing devices 2 in the second embodiment to the information processing device 5 in the fifth embodiment. The information showing the pattern estimation result by the second estimation unit 214 may be called elemental information.

[0103] The second estimation unit 214 may estimate which of the five (or six, or any) fingerprint patterns the fingerprints of each of the four fingers, including the first and second fingers of both hands, are.

[0104] If the four fingers of a newborn are the subject of the second estimation action, the second estimation unit 214 may estimate which of the five types of fingerprint patterns each of the four fingerprints possesses (for example, which of the five types described above: whorl pattern (W), separation pattern (D), left loop pattern (L), right loop pattern (R), and arcuate pattern (A)).

[0105] The second estimation unit 214 determines whether it has estimated all the patterns of the fingerprints that are the target of the second estimation operation (step S101). If there are targets of the second estimation operation for which the patterns of the fingerprints have not been estimated (step S101: No), the process returns to step S100.

[0106] Figure 14 illustrates display screen D during the estimation of fingerprint patterns for each of the four fingers, specifically the first and second fingers of both hands. Figure 14 shows that the pattern estimation for the first finger of the right hand is complete. Figure 14 also shows that a high-confidence estimation has been made for the second finger of the right hand, but one more surface image of the first pattern is needed. Furthermore, Figure 14 shows that a moderate-confidence estimation has been made for the first finger of the left hand, and one more surface image of the first pattern is needed. Furthermore, Figure 14 shows that a moderate-confidence estimation has been made for the second finger of the left hand, and two more surface images of the first pattern are needed. In other words, Figure 14 illustrates a case where there are targets for the second estimation operation in which the estimation of the fingerprint pattern is not yet complete.

[0107] If all patterns of the fingerprints targeted by the second estimation operation have been estimated (step S101: Yes), the registration control unit 416 generates registration pattern information by combining each of the patterns of each of the multiple fingers estimated by the second estimation unit 214 (step S102).

[0108] The registration control unit 416 registers the registration pattern information by associating each of the multiple fingers with the corresponding finger information (step S103). The registration control unit 416 may also store the registration pattern information, which is a combination of each of the patterns that each of the multiple fingers estimated by the second estimation unit 214, in the pattern database DB in association with the finger information that each of the multiple fingers corresponds to. The registration pattern information may also be information that shows an arrangement of element information (hereinafter sometimes referred to as "sequence data").

[0109] In the sixth embodiment, the registration control unit 416 may store registration pattern information, which is a combination of the element information corresponding to each of the multiple fingers determined by the second estimation unit 214, in association with the finger information in the pattern database DB. The registration control unit 416 may store sequence data, which is a combination of the element information corresponding to each of the four fingers, in association with the finger information in the pattern database DB. When the second estimation unit 214 determines the fingerprint pattern of each of the four fingers, the sequence data may be represented, for example, as (left index finger - left thumb - right thumb - right index finger: whorl pattern (W) - whorl pattern (W) - whorl pattern (W) - whorl pattern (W).

[0110] For example, the occurrence rate of whorl patterns (W) in Japanese fingerprints is said to be 50%, making it the most frequent pattern. Therefore, if the fingerprint patterns of all four fingers are whorls (W) (left index finger - left thumb - right thumb - right index finger: WWWW), the occurrence rate of this sequence data is 6.25% (0.5 to the power of 4). Furthermore, if the fingerprint patterns of all fingers on both hands (10 fingers) are whorls (W) (WWWWWWWWWW), the occurrence rate of this sequence data is 0.097% (0.5 to the power of 10), which is lower than the occurrence rate for four fingers.

[0111] When the registered pattern information is sequence data, the information processing device 6 can identify newborns with greater accuracy. The information processing device 6 can also identify newborns with greater accuracy even when it is more difficult to obtain biological information of a certain quality or higher, such as in cases of premature birth. For example, even if it is not possible to obtain a fingerprint image of a certain quality level required for adult fingerprint authentication, it can still accurately identify newborns.

[0112] The information processing device 6 may determine the number of fingers from which to acquire fingerprint images, depending on the accuracy required for the registered pattern information and the burden on the newborn. Since newborns often register fingerprints of all their fingers after they grow up, it is preferable to be able to acquire fingerprints of all fingers from newborns. Furthermore, increasing the number of correctly estimated fingerprints (number of fingers) and making the combinations more complex can improve the accuracy of individual identification. However, increasing the number of fingers from which to acquire fingerprints places a significant burden on the newborn.

[0113] For example, if the number of expected births is large, the information processing device 6 may decide to lower the accuracy required for the registered pattern information. In this case, for example, the information processing device 6 may decide to estimate the fingerprint patterns of four fingers. Conversely, if the number of expected births is small, the information processing device 6 may decide to increase the accuracy required for the registered pattern information. In this case, for example, the information processing device 6 may decide to acquire fingerprint images from all ten fingers.

[0114] Furthermore, for example, if there are two types of predetermined fingerprint patterns, such as the presence or absence of a delta, the information processing device 6 may estimate the patterns of the fingerprints of all ten fingers and generate registered pattern information. By increasing the number of fingers to be estimated, the information processing device 6 can ensure accuracy even when there are only a few predetermined types, such as two. [Matching operation]

[0115] The matching operation by the information processing device 6 may be performed before the time when the newborn moves from a place other than home, such as a hospital, to their home. "Before the time of movement" may refer to the time of movement or before the movement. The information processing operation by the information processing device 6 may also be performed before the time when the newborn is discharged from the hospital.

[0116] The information processing device 6 performs the verification operation shown in Figure 13(b) after the registration operation of the registration pattern information by the registration control unit 416 shown in Figure 13(a).

[0117] The second estimation unit 214 estimates the patterns of the subject's fingerprints (step S200). The second estimation unit 214 determines whether it has estimated all the patterns of the fingerprints of the target of the second estimation operation (step S201). If there are targets of the second estimation operation whose fingerprint patterns have not been estimated (step S201: No), the process returns to step S200.

[0118] The matching unit 618 generates matching pattern information by combining each of the patterns of the fingerprints of each of the multiple fingers estimated by the second estimation unit 214 (step S202). Step S200 may be the same operation as step S100 described above, step S201 may be the same operation as step S101 described above, and step S202 may be the same operation as step S102 described above.

[0119] The matching unit 618 compares the matching pattern information with the registered pattern information (step S203). The matching pattern information may be information indicating an arrangement of element information (hereinafter sometimes referred to as "sequence data"). The matching unit 618 may also perform matching of sequence data. [6-3: Technical Effects of Information Processing Device 6]

[0120] In the sixth embodiment, the information processing device 6 uses information that combines the patterns of each of the estimated fingers, so even when the person to be identified is a newborn, it can accurately identify the individual using biological information. [7: Addendum]

[0121] The following additional information is disclosed regarding the embodiments described above. [Note 1] An acquisition means that performs an acquisition operation to acquire a surface image including the subject's fingerprints, A first estimation means performs a first estimation operation to estimate the pattern of a fingerprint from the acquired surface image, An estimation control means controls the acquisition means and the first estimation means so as to repeat the acquisition operation and the first estimation operation until a predetermined number of surface images that have been estimated by the first estimation means to have a first pattern are acquired. An information processing device equipped with the following features. [Note 2] When a predetermined number of surface images that have been estimated to have a first pattern by the first estimation means have been acquired, the second estimation means performs a second estimation operation in which it is estimated that the first pattern is the pattern of the subject's fingerprint. An information processing device as described in Appendix 1, further comprising the following: [Note 3] Registration control means for registering finger information that associates information showing the first pattern with a predetermined number of surface images that are estimated to have the first pattern. An information processing device as described in Appendix 2, further comprising the above. [Note 4] The registration control means deletes surface images other than the predetermined number of surface images estimated to have the first pattern from among the multiple surface images acquired by the acquisition means until a predetermined number of surface images estimated to have the first pattern have been acquired by the first estimation means. The information processing device described in Appendix 3. [Note 5] The first estimation means calculates a score indicating the probability that the pattern in the surface image is one of a predetermined set of patterns, and estimates which of the set of patterns the pattern in the surface image is based on the calculated score. The second estimation means estimates the confidence level of the pattern with the largest total score to be higher than the case where the difference is less than the threshold if the number of surface images corresponding to the pattern with the largest total score among the surface images estimated to have the same pattern is less than the predetermined number, and the difference between the total score of the pattern with the largest total score and the total score of the pattern with the second largest total score is greater than or equal to a threshold. The information processing device described in Appendix 2. [Note 6] Display control means for displaying a display screen containing information regarding the control operation of the estimation control means on a display device. An information processing device as described in Appendix 1, further comprising the following: [Note 7] The information includes information regarding the number of surface images that are estimated to have the same pattern. The information processing device described in Appendix 6. [Note 8] The first estimation means calculates a score indicating the probability that the pattern in the surface image is one of a predetermined set of patterns, and estimates which of the set of patterns the pattern in the surface image is based on the calculated score. The display control means causes the display screen to be displayed on the display device such that the display mode of the display screen differs when the difference between the sum of scores corresponding to the pattern with the largest sum of scores for each of the surface images estimated to have the same pattern and the sum of scores corresponding to the pattern with the second largest sum is greater than or equal to the threshold, and when the difference is less than the threshold. The information processing device described in Appendix 6. [Note 9] The second estimation means estimates each of the patterns of the fingerprints of each of the subject's multiple fingers, The registration control means registers registration pattern information, which is a combination of each of the patterns that each of the plurality of fingers estimated by the second estimation means, by associating each of the plurality of fingers with the finger information corresponding to it. The information processing device described in Appendix 2. [Note 10] The acquisition process is performed to obtain a surface image including the subject's fingerprints. A first estimation operation is performed to estimate the pattern of the fingerprint from the acquired surface image. The system is controlled to repeat the acquisition operation and the first estimation operation until a predetermined number of surface images that are estimated to have a first pattern by the first estimation operation are acquired. Information processing methods. [Note 11] On the computer, The acquisition process is performed to obtain a surface image including the subject's fingerprints. A first estimation operation is performed to estimate the pattern of the fingerprint from the acquired surface image. The system is controlled to repeat the acquisition operation and the first estimation operation until a predetermined number of surface images that are estimated to have a first pattern by the first estimation operation are acquired. A recording medium on which computer programs for executing information processing methods are stored. [Note 12] After the registration of the registered pattern information by the registration control means, the matching means compares the matching pattern information, which is a combination of the patterns of each of the fingerprints of the plurality of fingers estimated by the second estimation means, with the registered pattern information. An information processing device as described in Appendix 8, further comprising the following: [Note 13] An acquisition means that performs an acquisition operation to acquire a surface image including the subject's fingerprints, A calculation means that performs a calculation operation to calculate the probability that the pattern of the fingerprint obtained from the surface image is at least one of a predetermined set of patterns, An estimation control means controls the acquisition means and the calculation means to repeat the acquisition operation and the calculation operation until the probability satisfies the condition for determining the pattern of the subject's fingerprint. An information processing device equipped with the following features. [Note 14] The process alternately repeats a first process of capturing a surface image including the subject's fingerprints, and a second process of estimating the pattern of the fingerprints from the captured surface image. An image acquisition device that terminates the iteration when a predetermined number of surface images have been captured in which, among the multiple estimated patterns, the first pattern is estimated to be included. [Note 15] An image acquisition device that captures surface images of a subject's fingers and estimates the fingerprint pattern from the captured surface images, repeating this process until a predetermined number of surface images match a first pattern among the estimated patterns. [Note 16] An image acquisition device that captures a surface image of a subject's finger, calculates the likelihood that the captured surface image is at least one of a plurality of patterns, and determines whether the likelihood satisfies the conditions for determining a fingerprint, repeating this process as long as the conditions are not met.

[0122] At least some of the constituent elements of each embodiment described above can be appropriately combined with at least some other constituent elements of each embodiment described above. Some of the constituent elements of each embodiment described above may not be used.

[0123] This disclosure is not limited to the embodiments described above. This disclosure may be modified as appropriate, insofar as it does not contradict the technical idea that can be inferred from the claims and the entire specification. Information processing devices, information processing methods, and recording media that result from such modifications are also included in the technical idea of ​​this disclosure. Furthermore, to the extent permitted by law, all published papers and articles described in this specification are incorporated herein by reference.

[0124] To the extent permitted by law, this application claims priority based on Japanese Patent Application No. 2022-128256, filed on 10 August 2022, and incorporates all of its disclosures herein. [Explanation of Symbols]

[0125] 1,2,3,4,5,6 Information Processing Device 11,211 Acquisition Department 12,212 1st estimation part 13,213 Estimated Control Unit 214 Second estimation part 315 Display Control Unit 416 Registration Control Unit 417 Calculation Unit 618 Verification Unit DB Pattern Database D Display screen

Claims

1. An acquisition means that performs an acquisition operation to acquire a surface image including the subject's fingerprints, A first estimation means performs a first estimation operation to estimate the pattern of a fingerprint from the acquired surface image, An estimation control means controls the acquisition means and the first estimation means to repeat the acquisition operation and the first estimation operation until a predetermined number of surface images that have been estimated by the first estimation means to have a first pattern are acquired. When a predetermined number of surface images that have been estimated to have a first pattern by the first estimation means have been acquired, a second estimation means performs a second estimation operation to estimate that the first pattern is the pattern of the subject's fingerprint. Equipped with, The first estimation means calculates a score indicating the probability that the pattern in the surface image is one of a predetermined set of patterns, and based on the calculated score, estimates which of the set of patterns the pattern in the surface image is. The second estimation means is an information processing device that estimates the reliability of the pattern with the largest total score to be higher than the case where the difference is less than the threshold, if the number of surface images corresponding to the pattern with the largest total score among the surface images estimated to have the same pattern is less than the predetermined number, and the difference between the total score corresponding to the pattern with the largest total score and the total score corresponding to the pattern with the second largest total score is greater than or equal to a threshold.

2. Acquisition means that performs an acquisition operation to acquire a surface image including the fingerprints of a subject, A first estimation means performs a first estimation operation to estimate the pattern of a fingerprint from the acquired surface image, An estimation control means controls the acquisition means and the first estimation means to repeat the acquisition operation and the first estimation operation until a predetermined number of surface images that have been estimated by the first estimation means to have a first pattern are acquired. A display control means that causes a display screen containing information regarding the control operation of the estimation control means to be displayed on a display device. Equipped with, The first estimation means calculates a score indicating the probability that the pattern in the surface image is one of a predetermined set of patterns, and based on the calculated score, estimates which of the set of patterns the pattern in the surface image is. The display control means causes the display screen to be displayed on the display device such that the display mode of the display screen differs when the difference between the sum of scores corresponding to the pattern with the largest sum of scores for each of the surface images estimated to have the same pattern and the sum of scores corresponding to the pattern with the second largest sum is greater than or equal to a threshold, and when the difference is less than the threshold.

3. When a predetermined number of surface images that have been estimated to have a first pattern by the first estimation means have been acquired, the second estimation means performs a second estimation operation in which it is estimated that the first pattern is the pattern of the subject's fingerprint. The information processing apparatus according to claim 2, further comprising:

4. Registration control means for registering finger information that associates information showing the first pattern with a predetermined number of surface images that are estimated to have the first pattern. The information processing apparatus according to claim 1 or 3, further comprising:

5. The registration control means deletes surface images other than the predetermined number of surface images estimated to have the first pattern from among the plurality of surface images acquired by the acquisition means until a predetermined number of surface images estimated to have the first pattern have been acquired by the first estimation means. The information processing apparatus according to claim 4.

6. The information includes information regarding the number of surface images that are estimated to have the same pattern. The information processing apparatus according to claim 2.

7. The process involves acquiring a surface image containing the subject's fingerprints, A first estimation operation is performed to estimate the pattern of the fingerprint from the acquired surface image, The system is controlled to repeat the acquisition operation and the first estimation operation until a predetermined number of surface images that are estimated to have a first pattern by the first estimation operation are acquired. When a predetermined number of surface images are obtained that are estimated to have a first pattern by the first estimation operation, a second estimation operation is performed to estimate that the first pattern is the pattern of the subject's fingerprint. Includes, The first estimation operation includes calculating a score indicating the probability that the pattern in the surface image is one of a predetermined set of patterns, and estimating, based on the calculated score, which of the set of patterns the pattern in the surface image is. The second estimation operation includes estimating the confidence level of the pattern with the largest total score to be higher than the case where the difference is less than the threshold, if the number of surface images corresponding to the pattern with the largest total score among the surface images estimated to have the same pattern is less than the predetermined number, and the difference between the total score of the pattern with the largest total score and the total score of the pattern with the second largest total score is greater than or equal to a threshold. The information processing method performed by computers.

8. Performing an acquisition operation to acquire a surface image including the subject's fingerprints, A first estimation operation is performed to estimate the pattern of the fingerprint from the acquired surface image, A control operation is performed to control the acquisition operation and the first estimation operation to be repeated until a predetermined number of surface images that are estimated to have a first pattern by the first estimation operation are acquired. To display a display screen containing information regarding the aforementioned control operation on a display device. Includes, The first estimation operation includes calculating a score indicating the probability that the pattern in the surface image is one of a predetermined set of patterns, and estimating, based on the calculated score, which of the set of patterns the pattern in the surface image is. The display of the aforementioned means includes displaying the display screen on the display device such that the display mode of the display screen differs when the difference between the sum of scores corresponding to the pattern with the largest sum of scores for each of the surface images estimated to have the same pattern and the sum of scores corresponding to the pattern with the second largest sum of scores is greater than or equal to a threshold, and when the display mode of the display screen differs when the difference is less than the threshold. The information processing method performed by computers.

9. On the computer, The process involves acquiring a surface image containing the subject's fingerprints, A first estimation operation is performed to estimate the pattern of the fingerprint from the acquired surface image, The system is controlled to repeat the acquisition operation and the first estimation operation until a predetermined number of surface images that are estimated to have a first pattern by the first estimation operation are acquired. When a predetermined number of surface images are obtained that are estimated to have a first pattern by the first estimation operation, a second estimation operation is performed to estimate that the first pattern is the pattern of the subject's fingerprint. Includes, The first estimation operation includes calculating a score indicating the probability that the pattern in the surface image is one of a predetermined set of patterns, and estimating, based on the calculated score, which of the set of patterns the pattern in the surface image is. The second estimation operation includes estimating the confidence level of the pattern with the largest total score to be higher than the case where the difference is less than the threshold, if the number of surface images corresponding to the pattern with the largest total score among the surface images estimated to have the same pattern is less than the predetermined number, and the difference between the total score of the pattern with the largest total score and the total score of the pattern with the second largest total score is greater than or equal to a threshold. A computer program that executes an information processing method.

10. A computer, The process involves acquiring a surface image containing the subject's fingerprints, A first estimation operation is performed to estimate the pattern of the fingerprint from the acquired surface image, A control operation is performed to control the acquisition operation and the first estimation operation to be repeated until a predetermined number of surface images that are estimated to have a first pattern by the first estimation operation are acquired. To display a display screen containing information regarding the aforementioned control operation on a display device. Includes, The first estimation operation includes calculating a score indicating the probability that the pattern in the surface image is one of a predetermined set of patterns, and estimating, based on the calculated score, which of the set of patterns the pattern in the surface image is. The display of the aforementioned means includes displaying the display screen on the display device such that the display mode of the display screen differs when the difference between the sum of scores corresponding to the pattern with the largest sum of scores for each of the surface images estimated to have the same pattern and the sum of scores corresponding to the pattern with the second largest sum of scores is greater than or equal to a threshold, and when the display mode of the display screen differs when the difference is less than the threshold. A computer program that executes an information processing method.

Images