Information processing device, information processing method, and recording medium

Abstract

This information processing device comprises: a first acquisition means that captures an image of a finger of a hand placed on a finger placement table to acquire a first fingerprint image; an estimation means that, on the basis of at least one fingerprint included in the first fingerprint image, estimates the posture of the hand using a learning model trained in advance; an output means that outputs guide information relating to how to place the hand according to the estimated posture of the hand; and a second acquisition means that, after the guide information has been outputted, captures an image of the finger of the hand to acquire a second fingerprint image to be used for fingerprint matching. According to such an information processing device, it is possible to appropriately acquire a fingerprint image to be used for fingerprint matching.

Description

Information processing device, information processing method, and recording medium

[0001] The present disclosure relates to the technical fields of an information processing device, an information processing method, and a recording medium.

[0002] Known examples of this type of device include those that capture fingerprint images including fingerprints. For example, Patent Document 1 discloses a device that calculates hand posture information by detecting the outline of the hand and the positions of the fingertips, and performs biometric authentication when it is determined that the hand posture information is within a certain range.

[0003] Japanese Patent Application Laid-Open No. 2023-011333

[0004] An object of this disclosure is to provide an information processing device, an information processing method, and a recording medium that aim to improve upon the techniques disclosed in prior art documents.

[0005] One aspect of the information processing device disclosed herein includes a first acquisition means that captures an image of the fingers of a hand placed on a finger rest to acquire a first fingerprint image; an estimation means that estimates the posture of the hand using a pre-trained learning model based on at least one fingerprint included in the first fingerprint image; an output means that outputs guide information regarding how to place the hand according to the estimated hand posture; and a second acquisition means that, after the guide information is output, captures an image of the fingers of the hand to acquire a second fingerprint image to be used for fingerprint matching.

[0006] One aspect of the information processing method disclosed herein involves using at least one computer to capture an image of the fingers of a hand placed on a finger rest to obtain a first fingerprint image, estimating the posture of the hand using a pre-trained learning model based on at least one fingerprint included in the first fingerprint image, outputting guide information regarding how to place the hand according to the estimated hand posture, and, after the guide information has been output, capturing an image of the fingers of the hand to obtain a second fingerprint image to be used for fingerprint matching.

[0007] One aspect of the recording medium of this disclosure is a recording medium having recorded thereon a computer program for causing at least one computer to execute an information processing method, which comprises capturing an image of fingers of a hand placed on a finger rest to obtain a first fingerprint image, estimating the posture of the hand using a pre-trained learning model based on at least one fingerprint included in the first fingerprint image, outputting guide information regarding how to place the hand according to the estimated posture of the hand, and, after the guide information has been output, capturing an image of the fingers of the hand to obtain a second fingerprint image to be used for fingerprint matching.

[0008] 1 is a block diagram showing a hardware configuration of a first information processing device. FIG. 2 is a side view showing the configuration of a fingerprint imaging device to which the first information processing device is applied. FIG. 3 is a block diagram showing the functional configuration of the first information processing device. FIG. 4 is a flowchart showing the operation flow of the first information processing device. FIG. 5 is a block diagram showing the functional configuration of a second information processing device. FIG. 6 is a flowchart showing the operation flow of the second information processing device. FIG. 7 is a flowchart showing the operation flow of a third information processing device. FIG. 8 is a schematic diagram (part 1) showing a specific operation example of the third information processing device. FIG. 9 is a schematic diagram (part 2) showing a specific operation example of the third information processing device. FIG. 10 is a schematic diagram showing the learning operation of a posture estimation model in a fourth information processing device. FIG. 11 is a table showing an example of posture labels of fingers handled by the fourth information processing device.

[0009] Hereinafter, embodiments of an information processing device, an information processing method, and a recording medium will be described with reference to the drawings.

[0010] First Embodiment A first information processing apparatus will be described with reference to FIGS. 1 to 4. FIG.

[0011] (Hardware Configuration) First, the hardware configuration of the first information processing apparatus will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the hardware configuration of the first information processing apparatus.

[0012] 1, the first information processing device 1 includes a processor 11, a RAM (Random Access Memory) 12, a ROM (Read Only Memory) 13, a storage device 14, an input device 15, and an output device 16. The processor 11, RAM 12, ROM 13, storage device 14, input device 15, and output device 16 are connected to each other via a data bus 17. The data bus 17 may be an interface other than a data bus (for example, a LAN, a USB, etc.).

[0013] The processor 11 loads a computer program. For example, the processor 11 is configured to load a computer program stored in at least one of the RAM 12, the ROM 13, and the storage device 14. Alternatively, the processor 11 may load a computer program stored in a computer-readable storage medium using a storage medium reading device (not shown). The processor 11 may acquire (i.e., load) the computer program from a device (not shown) located outside the first information processing device 1 via a network interface. The processor 11 executes the loaded computer program to perform various processes. When the processor 11 executes the loaded computer program, functional blocks related to the processes performed by the first information processing device 1 are realized within the processor 11. In other words, the processor 11 may function as a controller that executes each control in the first information processing device 1.

[0014] The processor 11 may be configured as, for example, a central processing unit (CPU), a graphics processing unit (GPU), a field-programmable gate array (FPGA), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or a quantum processor. The processor 11 may be configured as one of these, or may be configured to use multiple processors in parallel.

[0015] The RAM 12 temporarily stores computer programs executed by the processor 11. The RAM 12 temporarily stores data that the processor 11 temporarily uses while it is executing the computer programs. The RAM 12 may be, for example, a dynamic random access memory (D-RAM) or a static random access memory (SRAM). Alternatively, other types of volatile memory may be used instead of the RAM 12.

[0016] The ROM 13 stores computer programs executed by the processor 11. The ROM 13 may also store fixed data. The ROM 13 may be, for example, a programmable read-only memory (PROM) or an erasable read-only memory (EPROM). Alternatively, other types of non-volatile memory may be used instead of the ROM 13.

[0017] The storage device 14 stores data that is to be saved long-term by the first information processing device 1. The storage device 14 may operate as a temporary storage device for the processor 11. The storage device 14 may store computer programs executed by the processor 11. The storage device 14 may include, for example, at least one of a hard disk device, a magneto-optical disk device, an SSD (Solid State Drive), and a disk array device.

[0018] The input device 15 is a device that receives input instructions from a user of the first information processing device 1. The input device 15 may include, for example, at least one of a keyboard, a mouse, and a touch panel. The input device 15 may also be, for example, a device that includes a microphone and is capable of voice input.

[0019] The output device 16 is a device that outputs information related to the first information processing device 1 to the outside. For example, the output device 16 may be a display device (e.g., a display or a monitor) that can display information related to the first information processing device 1. The output device 16 may also be a speaker or the like that can output information related to the information processing device 1 as audio.

[0020] The first information processing device 1 may be configured to include some of the components described in Fig. 1. For example, the first information processing device 1 may be configured to include only the processor 11, RAM 12, and ROM 13 among the above-mentioned components. In this case, the storage device 14, input device 15, and output device 16 may each be provided as a device external to the first information processing device 1. Furthermore, some of the calculation functions of the first information processing device 1 may be realized by an external server, a cloud, or the like.

[0021] (Fingerprint Imaging Device) Next, a fingerprint imaging device to which the first information processing device 1 is applied will be described with reference to Fig. 2. Fig. 2 is a side view showing the configuration of the fingerprint imaging device to which the first information processing device is applied.

[0022] 2, the first information processing device 1 may be applied to a fingerprint imaging device 20 that captures a fingerprint image of a target. The fingerprint imaging device 20 includes a finger rest 21, a scanner 22, and a display 23.

[0023] The subject whose fingerprint image is to be captured places their hand on the finger rest 21 and presses their fingertips (specifically, the pads of their fingers) against the finger rest 21. The subject's fingers are then scanned by the scanner 22 installed below the finger rest 21, and a fingerprint image is captured. Note that guide information for capturing a fingerprint image may be displayed on the display 23. For example, the display 23 may be configured to output guide information (described in detail below) output by the first information processing device 1.

[0024] The fingerprint imaging device 20 may be configured as a device for registering captured fingerprint images. For example, the fingerprint imaging device 20 may be configured to store a fingerprint image acquired by capturing an image of a subject's hand in association with information about the subject (e.g., personal identification information such as the subject's name or ID).

[0025] Alternatively, the fingerprint imaging device 20 may be configured as a device that authenticates a target using a captured fingerprint image. For example, the fingerprint imaging device 20 may be configured as a device that compares a fingerprint image acquired by capturing an image of the target's hand with a pre-registered image (i.e., a fingerprint image of a registered user) to determine whether the target is the registered user.

[0026] (Functional Configuration) Next, the functional configuration of the first information processing device 1 will be described with reference to Fig. 3. Fig. 3 is a block diagram showing the functional configuration of the first information processing device.

[0027] 3, the first information processing device 1 is configured to be able to execute a process of acquiring a fingerprint image to be used for fingerprint matching. The first information processing device 1 is configured to include, as components for realizing its functions, a first acquisition unit 110, a posture estimation unit 120, a guide information output unit 130, and a second acquisition unit 140. Note that each of the first acquisition unit 110, the posture estimation unit 120, the guide information output unit 130, and the second acquisition unit 140 may be a processing block realized by the above-mentioned processor 11 (see FIG. 1).

[0028] The first acquisition unit 110 is configured to acquire a first fingerprint image. As described with reference to FIG. 2 , the first acquisition unit 110 may acquire, as the first fingerprint image, an image of the fingers of a hand placed on the finger rest 21 captured by the scanner 22. The first fingerprint image may be an image including the fingerprints of multiple fingers. For example, the fingerprint image may be an image including the fingerprints of the thumb, index finger, middle finger, ring finger, and little finger. Alternatively, the fingerprint image may be an image including the fingerprints of some of the fingers of a hand. The fingerprint image may also be an image including the entire palm (i.e., a palmprint image). The fingerprint image may be an image including the fingers of one hand or the fingers of both hands. The first fingerprint image is an image used to estimate the posture of the target hand. The first fingerprint image acquired by the first acquisition unit 110 is configured to be output to the posture estimation unit 120.

[0029] The posture estimation unit 120 is configured to be able to estimate the posture of the target hand based on the first fingerprint image acquired by the first acquisition unit 110. The posture estimation unit 120 estimates the posture of the hand using a pre-trained learning model (hereinafter referred to as the "posture estimation model" as appropriate). The posture estimation unit 120 may input the first fingerprint image to the posture estimation model and acquire information about the hand posture as its output. The posture estimation model is a model that estimates the hand posture based on at least one fingerprint included in the first fingerprint image. The posture estimation model may be, for example, a model configured of a neural network trained by deep learning. The learning of the posture estimation model will be described in detail in another embodiment described later. Information about the hand posture estimated by the posture estimation unit 120 is configured to be output to the guide information output unit 130.

[0030] The guide information output unit 130 is configured to output guide information regarding hand placement. The guide information output unit 130 outputs the guide information according to the hand posture estimated by the posture estimation unit 120. The guide information may be information indicating a hand posture suitable for capturing a fingerprint image (e.g., a hand placement that allows a high-quality fingerprint image to be captured). Alternatively, the guide information may be information that guides the movement of the subject's hand (e.g., information indicating the direction or amount of hand movement) so that the hand posture is suitable for capturing a fingerprint image. Alternatively, the guide information may be information indicating the reason why the current hand posture (i.e., the hand posture estimated by the posture estimation unit 120) is not suitable for capturing a fingerprint image (e.g., the fingertips are floating). The guide information output unit 130 may be configured to display, for example, a message or image as guide information on the display 23 (see FIG. 2 ). Alternatively, the guide information output unit 130 may be configured to output the message as guide information by voice from a speaker or the like.

[0031] The second acquisition unit 140 is configured to acquire a second fingerprint image. Similar to the first acquisition unit 110 described above, the second acquisition unit 140 may acquire, as the second fingerprint image, an image of the fingers of a hand placed on the finger rest 21 captured by the scanner 22. That is, the first fingerprint image and the second fingerprint image may be captured by the same imaging device. The second fingerprint image may be an image including fingerprints of multiple fingers. The second acquisition unit 140 acquires the second fingerprint image after guide information is output from the guide information output unit 130. That is, the second acquisition unit 140 acquires the second fingerprint image after the subject changes the position of their hand in accordance with the output guide information. The second acquisition unit 140 may capture and acquire the second fingerprint image a predetermined period after the output of the guide information. Alternatively, the second acquisition unit 140 may capture and acquire the second fingerprint image when it detects a change in the position of the hand after the guide information is acquired.

[0032] The second fingerprint image is an image used for fingerprint matching. For example, the second fingerprint image may be used as a registered image in fingerprint matching. In this case, the second acquisition unit 140 may be configured to output the second fingerprint image to a database for registered images. Alternatively, the second fingerprint image may be used as a match image in fingerprint matching (i.e., an image to be matched with the registered image). In this case, the second acquisition unit 140 may be configured to output the second fingerprint image to a fingerprint matching device.

[0033] (Flow of Operation) Next, the flow of operation by the first information processing device 1 will be described with reference to Fig. 4. Fig. 4 is a flowchart showing the flow of operation of the first information processing device.

[0034] 4 , when the operation of the first information processing device 1 starts, the first acquisition unit 110 first captures an image of the fingers of a target hand to acquire a first fingerprint image (step S101). Then, the posture estimation unit 120 estimates the posture of the hand based on the first fingerprint image acquired by the first acquisition unit 110 (step S102).

[0035] Next, the guide information output unit 130 outputs guide information in accordance with the hand posture estimated by the posture estimation unit 120 (step S103). After the guide information is output, the second acquisition unit 140 captures an image of the fingers of the target hand again to acquire a second fingerprint image (step S104).

[0036] Note that if the hand posture estimated in step S102 is already appropriate (i.e., if there is no need to change the way the hand is placed), the processing of step S103 may be omitted. That is, the second fingerprint image may be acquired without outputting guide information. Alternatively, the second fingerprint image may be acquired after outputting guide information for maintaining the hand posture. Alternatively, the first fingerprint image acquired initially may be treated as the second fingerprint image as is. That is, the first fingerprint image may be used for fingerprint matching, and a new image may not be acquired as the second fingerprint image.

[0037] (Technical Effects) Next, technical effects obtained by the first information processing device 1 will be described.

[0038] 1 to 4, in the first information processing device 1, guide information is output according to the hand posture estimated based on the first fingerprint image. Then, after the guide information is output, a second fingerprint image for fingerprint matching is acquired. In this way, it is possible to acquire a fingerprint image suitable for fingerprint matching.

[0039] When capturing a fingerprint image with a hand placed on the finger rest 21, as in this embodiment, even slight differences in how the hand is placed can result in a large difference in quality. For example, even if a part of the finger is slightly lifted from the rest 21, the quality of the fingerprint image may be reduced. However, in this embodiment, by outputting guide information regarding how the hand is placed, it is possible to appropriately guide the hand placement and improve the quality of the fingerprint image.

[0040] Another method for acquiring a fingerprint image suitable for fingerprint matching is to determine the quality of the fingerprint image. However, if the quality is determined to be poor, it is difficult to improve the quality because it is unclear how to improve the quality. However, in this embodiment, guide information regarding hand placement is output, making it possible to provide appropriate guidance on hand placement. This can improve the throughput of the fingerprint matching process, for example.

[0041] Second Embodiment A second information processing device 1 will be described with reference to Figures 5 and 6. The second information processing device 1 differs in some configurations and operations from the first information processing device 1 described above, but other parts may be similar to the first information processing device 1. Therefore, the following will describe in detail the parts that differ from the first embodiment, and will omit explanations of other overlapping parts as appropriate.

[0042] (Functional Configuration) First, the functional configuration of the second information processing device 1 will be described with reference to Fig. 5. Fig. 5 is a block diagram showing the functional configuration of the second information processing device. Note that in Fig. 5, elements similar to those shown in Fig. 3 are denoted by the same reference numerals.

[0043] 5, the second information processing device 1 is configured to include, as components for realizing its functions, a first acquisition unit 110, a posture estimation unit 120, a guide information output unit 130, a second acquisition unit 140, and a posture determination unit 150. That is, the second information processing device 1 further includes a posture determination unit 150 in addition to the configuration described in the first embodiment (see FIG. 3). Note that the posture determination unit 150 may be a processing block realized by the above-described processor 11 (see FIG. 1).

[0044] The posture determination unit 150 is configured to be able to determine whether the hand posture is suitable for capturing a second fingerprint image (hereinafter referred to as "appropriate posture"). The method for determining the hand posture by the posture determination unit 150 is not particularly limited, and the determination may be made using the estimation result by the posture estimation means 120 described above. More specifically, the posture determination unit 150 may determine whether the hand posture is appropriate based on the hand posture estimated using the first fingerprint image. The hand posture to be determined as appropriate may be set in advance, for example, based on a prior simulation. For example, multiple fingerprint images may be captured while changing the hand posture, and the hand posture that results in a high-quality fingerprint image may be set as the appropriate posture. The determination result by the posture determination unit 150 is configured to be output to the second acquisition unit 140.

[0045] The second acquisition unit 140 in the second information processing device 1 is configured to acquire a second fingerprint image in accordance with the determination result by the posture determination unit 150. Specifically, the second acquisition unit 140 acquires the second fingerprint image when the posture determination unit 150 determines that the posture is correct. In other words, the second acquisition unit 140 may not acquire a second fingerprint image until the posture determination unit 150 determines that the posture is correct.

[0046] (Operation Flow) Next, the operation flow of the second information processing device 1 will be described with reference to Fig. 6. Fig. 6 is a flowchart showing the operation flow of the second information processing device. Note that in Fig. 6, the same processes as those shown in Fig. 4 are denoted by the same reference numerals.

[0047] 6 , when the operation of the second information processing device 1 is started, the first acquisition unit 110 first captures an image of the fingers of a target hand to acquire a first fingerprint image (step S101). Then, the posture estimation unit 120 estimates the posture of the hand based on the first fingerprint image acquired by the first acquisition unit 110 (step S102).

[0048] Next, the guide information output unit 130 outputs guide information according to the hand posture estimated by the posture estimation unit 120 (step S103). After the guide information is output, the posture determination unit 150 determines whether the hand posture is appropriate (step S201). That is, the posture determination unit 150 determines whether the hand posture has changed to the appropriate posture as a result of outputting the guide information. Note that in step S201, the above-described steps S101 and S102 may be executed again to estimate the hand posture, and whether the hand posture is appropriate may be determined from the estimation result.

[0049] If the hand posture is correct (step S201: YES), the second acquisition unit 140 captures an image of the fingers of the target hand to acquire a second fingerprint image (step S104). On the other hand, if the hand posture is not correct (step S201: NO), the process of step S103 is executed again. That is, the guide information output unit 130 outputs guide information according to the current hand posture (i.e., the hand posture determined to be incorrect). By repeating this process, the second fingerprint image is acquired after the hand posture becomes correct.

[0050] (Technical Effects) Next, technical effects obtained by the second information processing device 1 will be described.

[0051] 5 and 6, the second information processing device 1 acquires a second fingerprint image when the hand posture is determined to be appropriate, thereby preventing an inappropriate second fingerprint image from being acquired.

[0052] For example, even if guide information is output, it is not guaranteed that the hand posture will be changed to the appropriate posture. Specifically, if the second fingerprint image is captured before the subject has changed the position of their hand, an inappropriate second fingerprint image will be acquired even if the guide information is appropriate. Furthermore, even if the hand position is changed according to the guide information, if the subject moves their hand in an inappropriate manner (for example, if the direction of movement is wrong or the amount of movement is inappropriate), an inappropriate second fingerprint image will be acquired. However, in this embodiment, the second fingerprint image is captured after it is determined that the hand posture has become appropriate, so that the second fingerprint image can be captured and acquired in an appropriate state.

[0053] <Third embodiment> A third information processing device 1 will be described with reference to Figures 7 to 9. The third information processing device 1 differs in some configurations and operations from the first and second information processing devices 1 described above, but other parts may be similar to the first and second information processing devices 1. Therefore, the following will describe in detail the parts that differ from the embodiments already described, and will omit explanations of other overlapping parts as appropriate.

[0054] (Operation Flow) First, the operation flow of the third information processing device 1 will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the operation flow of the third information processing device. Note that in Fig. 7, the same processes as those shown in Fig. 3 are denoted by the same reference numerals.

[0055] 7 , when the operation of the third information processing device 1 is started, the first acquisition unit 110 first captures an image of the fingers of a target hand to acquire a first fingerprint image (step S101). Then, the posture estimation unit 120 estimates the posture of the fingers of the hand based on the first fingerprint image acquired by the first acquisition unit 110 (step S301). Note that if the first fingerprint image includes fingerprints of multiple fingers, the posture estimation unit 120 estimates the posture of each of the multiple fingers.

[0056] Next, the guide information output unit 130 outputs guide information according to the finger postures estimated by the posture estimation unit 120 (step S302). Specifically, the guide information output unit 130 outputs guide information for each of the multiple fingers included in the first fingerprint image. Specific examples of guide information will be described in detail later. After the guide information is output, the second acquisition unit 140 captures an image of the fingers of the target hand again to acquire a second fingerprint image (step S104).

[0057] As described above, in the third information processing device 1, the posture of each finger of the hand is estimated as the posture of the hand, and guide information relating to each finger of the hand is output.

[0058] (Operation Example) Next, a specific operation example of the third information processing device 1 will be described with reference to Fig. 8 and Fig. 9. Fig. 8 is a schematic diagram (part 1) showing a specific operation example of the third information processing device. Fig. 9 is a schematic diagram (part 2) showing a specific operation example of the third information processing device.

[0059] 8 includes a fingerprint F1 of the index finger, a fingerprint F2 of the middle finger, a fingerprint F3 of the ring finger, and a fingerprint F4 of the little finger. In this case, the posture estimation unit 120 estimates the posture of each of the index finger, middle finger, ring finger, and little finger.

[0060] In the example shown in Figure 8, there are no particular problems with the index finger fingerprint F1 and the middle finger fingerprint F2. Therefore, the postures of the index finger and middle finger are estimated to be "correct." On the other hand, the ring finger fingerprint F3 has a blurred area E1 on the bottom. As a result, the posture of the ring finger is estimated to be "only the fingertip (i.e., the base of the finger is lifted)." Furthermore, the little finger fingerprint F4 has a blurred area E2 on the side. As a result, the posture of the little finger is estimated to be "lifted on the side."

[0061] Based on the results of estimating the posture of each finger as described above, the guide information output unit 130 outputs guide information that makes the postures of all fingers "proper." Specifically, the guide information output unit 130 outputs a message saying, "Please touch the base of your ring finger" to eliminate "only the tip" of the ring finger. Furthermore, the guide information output unit 130 outputs a message saying, "Please touch the side of your little finger" to eliminate "side lift" of the little finger. The guide information output unit 130 may display the first fingerprint image on the display 23, and may also superimpose a conspicuous color (e.g., red) on the blurred regions E1 and E2.

[0062] 9 also includes a fingerprint F1 of the index finger, a fingerprint F2 of the middle finger, a fingerprint F3 of the ring finger, and a fingerprint F4 of the little finger. In this case, the posture estimation unit 120 estimates the posture of each of the index finger, middle finger, ring finger, and little finger.

[0063] In the example shown in Figure 9, there is no particular problem with the fingerprint F3 of the ring finger and the fingerprint F4 of the little finger. Therefore, the postures of the ring finger and little finger are estimated to be "proper." On the other hand, the distance between the fingerprint F1 of the index finger and the fingerprint F2 of the middle finger is too close (for example, closer than a predetermined distance). As a result, the posture of the index finger is estimated to be "too close to the middle finger." Furthermore, the posture of the middle finger is estimated to be "too close to the index finger."

[0064] Based on the results of estimating the posture of each finger as described above, the guide information output unit 130 outputs guide information that makes the postures of all fingers "proper." Specifically, the guide information output unit 130 outputs a message saying, "Please separate your index finger and middle finger." The guide information output unit 130 may display the first fingerprint image on the display 23, as well as an animation in which the fingerprint F1 of the index finger and the fingerprint F2 of the middle finger are separating from each other.

[0065] 8 and 9 are merely examples, and various guide information may be output depending on the finger posture. In the above example, a fingerprint image including four fingers is used as an example, but the types of fingers included in the fingerprint image are not particularly limited. For example, the fingerprint image may be an image including five fingers including the thumb. Alternatively, the fingerprint image may be an image including only the two thumbs of both hands.

[0066] (Technical Effects) Next, technical effects obtained by the third information processing device 1 will be described.

[0067] As explained in Fig. 7 to Fig. 9, the third information processing device 1 estimates the posture of each finger of a hand. In this way, it is possible to estimate the posture of the hand in more detail compared to when estimating the posture of the entire hand. Furthermore, the third information processing device 1 outputs guide information that guides the posture of each finger of a hand. In this way, it is possible to guide the posture of the hand in more detail compared to when outputting guide information related to the posture of the entire hand. As a result, it becomes possible to appropriately capture images of the fingerprints of each of the multiple fingers.

[0068] <Fourth embodiment> A fourth information processing device 1 will be described with reference to Figures 10 and 11. The fourth information processing device 1 differs in some configurations and operations from the first to third information processing devices 1 described above, but other parts may be similar to the first to third information processing devices 1. Therefore, the following will describe in detail the parts that differ from the embodiments already described, and will omit explanations of other overlapping parts as appropriate.

[0069] (Learning Operation) First, the learning operation of the posture estimation model in the third information processing device 1 will be described with reference to Fig. 10. Fig. 10 is a schematic diagram showing the learning operation of the posture estimation model in the fourth information processing device.

[0070] 10 , the posture estimation model 125 in the fourth information processing device 1 is a machine learning model that is trained using training data. The training data includes fingerprint images and labels relating to the posture of each finger included in the fingerprint images (hereinafter referred to as "finger posture labels" as appropriate). In other words, the training data is a pair of a fingerprint image and its finger posture label, which is its ground truth data. The training data includes multiple pairs of fingerprint images and finger posture labels.

[0071] There are no particular limitations on the learning method for posture estimation model 125, and for example, backpropagation may be used for learning. Specifically, a loss function is calculated by comparing the estimation result when a fingerprint image is input to posture estimation model 125 with correct data, and weight parameters of posture estimation model 125 are optimized so as to reduce the loss function.

[0072] (Finger Posture Labels) Next, finger posture labels handled by the fourth information processing device 1 will be specifically described with reference to Fig. 11. Fig. 11 is a table showing an example of finger posture labels handled by the fourth information processing device.

[0073] 11, the fourth information processing apparatus handles five types of finger posture labels, labels 1 to 5. Specifically, the finger posture labels are set as label 1 indicating a correct posture, label 2 indicating that the fingerprint is only on the fingertip (i.e., the base of the finger is raised), label 3 indicating that the fingertip is raised, label 4 indicating that the side of the finger is raised, and label 5 indicating that the distance between the fingers is too close.

[0074] The above-described labels 1 to 5 may be set as correct answer data of the training data. Furthermore, the above-described labels 1 to 5 may indicate postures estimated by posture estimation unit 120. In this case, posture estimation model 125 may be configured as a model that outputs finger posture labels shown in FIG. 11. For example, posture estimation model 125 may be a model that, when a first fingerprint image including fingerprints of multiple fingers is input, outputs labels 1 to 5 for each of the multiple fingers.

[0075] The above-described labels 1 to 5 are merely examples, and other labels may be used. That is, the number and types of finger posture labels handled by the fourth information processing device 1 are not limited to the example shown in FIG. 11 .

[0076] (Technical Effects) Next, technical effects obtained by the fourth information processing device 1 will be described.

[0077] As described in FIGS. 10 and 11 , in the fourth information processing device 1, the posture estimation model 125 is trained using training data including a fingerprint image and a finger posture label. In this way, the posture estimation model 125 can be trained appropriately, and it becomes possible to appropriately estimate the finger posture from the first fingerprint image. Furthermore, in the fourth information processing device 1, posture labels of multiple fingers are used. In this way, the posture estimation model 125 can be trained appropriately by using the finger posture labels as ground truth data. Furthermore, it is possible to output the finger posture estimation result as a simple label.

[0078] The scope of each embodiment also includes a processing method in which a program that operates the configuration of each embodiment to realize the functions of the above-described embodiments is recorded on a recording medium, the program recorded on the recording medium is read as code, and the program is executed on a computer. In other words, a computer-readable recording medium is also included in the scope of each embodiment. Furthermore, each embodiment includes not only a recording medium on which the above-described program is recorded, but also the program itself.

[0079] Examples of recording media that can be used include floppy disks, hard disks, optical disks, magneto-optical disks, CD-ROMs, magnetic tapes, non-volatile memory cards, and ROMs. Furthermore, the scope of each embodiment is not limited to programs that execute processes by themselves, but also includes programs that execute processes by operating on an OS in conjunction with other software or expansion board functions. Furthermore, the program itself may be stored on a server, and part or all of the program may be downloadable from the server to a user terminal. The program may be provided to the user in, for example, a SaaS (Software as a Service) format.

[0080] <Supplementary Notes> The above-described embodiment may be further described as in the following supplementary notes, but is not limited to the following.

[0081] (Supplementary Note 1) The information processing device described in Supplementary Note 1 is an information processing device that includes a first acquisition means that captures an image of fingers of a hand placed on a finger rest to acquire a first fingerprint image, an estimation means that estimates the posture of the hand using a pre-trained learning model based on at least one fingerprint included in the first fingerprint image, an output means that outputs guide information regarding how to place the hand according to the estimated posture of the hand, and a second acquisition means that captures an image of the fingers of the hand to acquire a second fingerprint image to be used for fingerprint matching after the guide information has been output.

[0082] (Appendix 2) The information processing device described in Appendix 2 is the information processing device described in Appendix 1, further comprising a determination means for determining whether the posture of the hand is an appropriate posture suitable for capturing the second fingerprint image, and the second acquisition means, when it is determined that the posture of the hand is the appropriate posture, images the fingers of the hand to acquire the second fingerprint image.

[0083] (Supplementary Note 3) The information processing device according to Supplementary Note 3 is the information processing device according to Supplementary Note 1 or 2, wherein the estimation means estimates a posture of fingers of the hand as the posture of the hand.

[0084] (Supplementary Note 4) The information processing device according to Supplementary Note 4 is the information processing device according to Supplementary Note 3, wherein the output means outputs, as the guide information, information for guiding a posture of the fingers of the hand.

[0085] (Supplementary Note 5) The information processing device described in Supplementary Note 5 is the information processing device described in Supplementary Note 3 or 4, in which the learning model is a model that outputs information about the posture of fingers included in an input image, and is trained using learning data including a fingerprint image and information about the posture of fingers included in the fingerprint image.

[0086] (Appendix 6) The information processing device described in Appendix 6 is the information processing device described in Appendix 5, wherein the information related to the finger posture includes at least one of a first label indicating that the posture is suitable for capturing the second fingerprint image, a second label indicating that the base of the finger is lifted, a third label indicating that the fingertip is lifted, a fourth label indicating that the side of the finger is lifted, and a fifth label indicating that the distance between the fingers is too close.

[0087] (Appendix 7) The information processing method described in Appendix 7 is an information processing method that uses at least one computer to capture an image of the fingers of a hand placed on a finger rest to obtain a first fingerprint image, estimates the posture of the hand using a pre-trained learning model based on at least one fingerprint included in the first fingerprint image, outputs guide information regarding how to place the hand according to the estimated posture of the hand, and after the guide information is output, images the fingers of the hand to obtain a second fingerprint image to be used for fingerprint matching.

[0088] (Appendix 8) The recording medium described in Appendix 8 is a recording medium having recorded thereon a computer program for causing at least one computer to execute an information processing method, which comprises capturing an image of fingers of a hand placed on a finger rest to obtain a first fingerprint image, estimating a posture of the hand using a pre-trained learning model based on at least one fingerprint included in the first fingerprint image, outputting guide information regarding how to place the hand according to the estimated posture of the hand, and, after the guide information has been output, capturing an image of the fingers of the hand to obtain a second fingerprint image to be used for fingerprint matching.

[0089] (Appendix 9) The computer program described in Appendix 9 is a computer program that causes at least one computer to execute an information processing method that captures an image of fingers of a hand placed on a finger rest to obtain a first fingerprint image, estimates a posture of the hand using a pre-trained learning model based on at least one fingerprint included in the first fingerprint image, outputs guide information regarding how to place the hand according to the estimated posture of the hand, and, after the guide information has been output, captures an image of the fingers of the hand to obtain a second fingerprint image to be used for fingerprint matching.

[0090] This disclosure may be modified as appropriate within the scope that does not contradict the gist or idea of ​​the invention that can be read from the claims and the entire specification, and information processing devices, information processing methods, and recording media that involve such modifications are also included in the technical idea of ​​this disclosure.

[0091] REFERENCE SIGNS LIST 1 Information processing device 11 Processor 12 RAM 13 ROM 14 Storage device 15 Input device 16 Output device 17 Data bus 20 Fingerprint imaging device 21 Finger rest 22 Scanner 23 Display 110 First acquisition unit 120 Posture estimation unit 125 Posture estimation model 130 Guide information output unit 140 Second acquisition unit 150 Posture determination unit F1 to F4 Fingerprint E1, E2 Blurred area

Claims

1. An information processing device comprising: a first acquisition means for capturing an image of the fingers of a hand placed on a finger rest to capture a first fingerprint image; an estimation means for estimating the posture of the hand using a pre-trained learning model based on at least one fingerprint included in the first fingerprint image; an output means for outputting guide information regarding how to place the hand according to the estimated posture of the hand; and a second acquisition means for capturing an image of the fingers of the hand to capture a second fingerprint image to be used for fingerprint matching after the guide information has been output.

2. An information processing device as described in claim 1, further comprising a determination means for determining whether the hand posture is an appropriate posture for capturing the second fingerprint image, and the second acquisition means, when it is determined that the hand posture is the appropriate posture, images the fingers of the hand to capture the second fingerprint image.

3. The information processing device according to claim 1 or 2, wherein the estimation means estimates the posture of the fingers of the hand as the posture of the hand.

4. The information processing device according to claim 3, wherein the output means outputs, as the guide information, information for guiding the posture of the fingers of the hand.

5. An information processing device according to any one of claims 3, wherein the learning model is a model that outputs information about the posture of a finger contained in an input image, and is trained using learning data including a fingerprint image and information about the posture of a finger contained in the fingerprint image.

6. The information processing device of claim 5, wherein the information regarding the finger posture includes at least one of a first label indicating that the posture is suitable for capturing the second fingerprint image, a second label indicating that the base of the finger is lifted, a third label indicating that the tip of the finger is lifted, a fourth label indicating that the side of the finger is lifted, and a fifth label indicating that the distance between the fingers is too close.

7. An information processing method comprising: capturing an image of fingers of a hand placed on a finger rest to obtain a first fingerprint image by at least one computer; estimating the posture of the hand using a pre-trained learning model based on at least one fingerprint included in the first fingerprint image; outputting guide information regarding how to place the hand according to the estimated posture of the hand; and, after the guide information has been output, capturing an image of the fingers of the hand to obtain a second fingerprint image to be used for fingerprint matching.

8. A recording medium having recorded thereon a computer program for causing at least one computer to execute an information processing method, which comprises: capturing an image of fingers placed on a finger rest to obtain a first fingerprint image; estimating the posture of the hand using a pre-trained learning model based on at least one fingerprint included in the first fingerprint image; outputting guide information regarding how to place the hand according to the estimated posture of the hand; and, after the guide information has been output, capturing an image of the fingers of the hand to obtain a second fingerprint image to be used for fingerprint matching.

Images