Information processing device, information processing method, and computer program
The information processing device enhances fingerprint matching accuracy by aligning extracted core lines with registered images through multiple extraction methods and updates, addressing discrepancies in older data lacking core lines.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- NEC CORP
- Filing Date
- 2025-01-15
- Publication Date
- 2026-07-28
AI Technical Summary
Existing fingerprint matching technologies rely on core lines and feature points, but often face inaccuracies due to discrepancies in automatically extracted core lines with the correct ones identified by forensic experts, especially in older data lacking core lines.
An information processing device and method that extracts feature points and core lines using multiple methods, selects the most similar fingerprint image, generates a difference core line image, and updates feature points and core lines based on registered images and other extracted images to align with correct core lines.
Improves fingerprint matching accuracy by generating core lines consistent with registered images, enabling more precise matching even in data lacking initial core lines.
Smart Images
Figure 2026122339000001_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the technical field of information processing apparatuses, information processing methods, and computer programs.
Background Art
[0002] It is known to use core lines in addition to feature points for fingerprint matching. For example, Patent Document 1 discloses extracting feature points and core lines from a first stripe pattern image and a second stripe pattern image in which stripe patterns are formed by ridge lines, and calculating a matching score by matching two sets of feature point data and core line data respectively extracted from the first stripe pattern image and the second stripe pattern image.
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] This disclosure aims to improve the related technologies described above.
Means for Solving the Problems
[0005] One aspect of the information processing device of this disclosure includes: acquisition means for extracting feature points and core lines from a single fingerprint image using a plurality of extraction methods and acquiring a plurality of extracted fingerprint images corresponding to each of the plurality of extraction methods; selection means for selecting one extracted fingerprint image from the plurality of extracted fingerprint images based on a registered fingerprint image including feature points corresponding to the fingerprint image and each of the plurality of extracted fingerprint images; generation means for generating a difference core line image showing the difference between core lines included in the one extracted fingerprint image and core lines included in other extracted fingerprint images other than the one extracted fingerprint image included in the plurality of extracted fingerprint images; and update means for updating feature points and core lines included in the one extracted fingerprint image based on the registered fingerprint image, the one extracted fingerprint image, the other extracted fingerprint images, and the difference core line image.
[0006] One aspect of the information processing method of this disclosure is an information processing method performed by a computer, which includes: extracting feature points and core lines from a single fingerprint image using a plurality of extraction methods, obtaining a plurality of extracted fingerprint images corresponding to each of the plurality of extraction methods; selecting one extracted fingerprint image from the plurality of extracted fingerprint images based on a registered fingerprint image containing feature points corresponding to the fingerprint image and each of the plurality of extracted fingerprint images; generating a difference core line image showing the difference between the core lines included in the one extracted fingerprint image and the core lines included in other extracted fingerprint images other than the one extracted fingerprint image included in the plurality of extracted fingerprint images; and performing an update operation to update the feature points and core lines included in the one extracted fingerprint image based on the registered fingerprint image, the one extracted fingerprint image, the other extracted fingerprint images, and the difference core line image.
[0007] One aspect of the computer program of this disclosure causes a computer to execute an information processing method that includes extracting feature points and core lines from a single fingerprint image using a plurality of extraction methods, obtaining a plurality of extracted fingerprint images corresponding to each of the plurality of extraction methods, selecting one extracted fingerprint image from the plurality of extracted fingerprint images based on a registered fingerprint image containing feature points corresponding to the fingerprint image and each of the plurality of extracted fingerprint images, generating a difference core line image showing the difference between the core lines included in the one extracted fingerprint image and the core lines included in other extracted fingerprint images other than the one extracted fingerprint image included in the plurality of extracted fingerprint images, and updating the feature points and core lines included in the one extracted fingerprint image based on the registered fingerprint image, the one extracted fingerprint image, the other extracted fingerprint images, and the difference core line image. [Brief explanation of the drawing]
[0008] [Figure 1] This is a block diagram showing the configuration of the information processing device related to this disclosure. [Figure 2] This flowchart shows the flow of information processing operations in the information processing device related to this disclosure. [Figure 3] This is a block diagram showing the configuration of the information processing device related to this disclosure. [Figure 4] This flowchart shows the flow of information processing operations in the information processing device related to this disclosure. [Figure 5] This is a schematic diagram showing an overview of the information processing operation in the information processing device related to this disclosure. [Figure 6] This is a block diagram showing the configuration of the information processing device related to this disclosure. [Figure 7] This flowchart shows the flow of information processing operations in the information processing device related to this disclosure. [Figure 8] This is a block diagram showing the configuration of the information processing device related to this disclosure. [Figure 9] This flowchart shows the flow of information processing operations in the information processing device related to this disclosure. [Modes for carrying out the invention]
[0009] The following describes embodiments of the information processing device, information processing method, and computer program with reference to the drawings. [1: First Embodiment]
[0010] A first embodiment relating to an information processing device, an information processing method, and a computer program will be described with reference to Figures 1 and 2. In the following description, the first embodiment relating to an information processing device, an information processing method, and a computer program will be described using the information processing device 10.
[0011] As shown in Figure 1, the information processing device 10 comprises an acquisition unit 11, a selection unit 12, a generation unit 13, and an update unit 14. The operations performed by the information processing device 10 will be explained with reference to the flowchart in Figure 2.
[0012] An image corresponding to a fingerprint image, which includes feature points and core lines extracted from the fingerprint image, is called an extracted fingerprint image. Feature points include at least one of the endpoints where ridges are broken and branching points where ridges branch. Ridges are linear elevations that form fingerprints on the skin of the fingers. Core lines are lines that are thinner versions of the ridges. As shown in Figure 2, the acquisition unit 11 acquires each of the multiple types of extracted fingerprint images (step S11).
[0013] A single fingerprint image may have feature points and core lines extracted using multiple different extraction methods. Therefore, each of the multiple extracted fingerprint images corresponds to the same single fingerprint image and may contain feature points and core lines extracted using different extraction methods.
[0014] Furthermore, feature points and core lines extracted using the same extraction method may coincide. For example, feature points extracted using the same extraction method may lie on core lines. Therefore, feature points contained in one extracted fingerprint image may lie on core lines contained in that extracted fingerprint image.
[0015] An image corresponding to a fingerprint image, and an image including feature points of the fingerprint image is referred to as a registered fingerprint image. The feature points of the fingerprint image included in the registered fingerprint image may be, for example, the feature points specified by a forensic examiner. The feature points of the fingerprint image included in the registered fingerprint image may be the correct feature points. The registered fingerprint image may not include a core line.
[0016] The selection unit 12 selects one extracted fingerprint image from the plurality of types of extracted fingerprint images based on the registered fingerprint image and each of the plurality of types of extracted fingerprint images (step S12). The selection unit 12 may compare the feature points included in the registered fingerprint image with the feature points included in each of the plurality of types of extracted fingerprint images and select one extracted fingerprint image. The selection unit 12 may select, as one extracted fingerprint image, the extracted fingerprint image having the most similar feature points to the registered fingerprint image among the plurality of types of extracted fingerprint images. The selection unit 12 may select, as one extracted fingerprint image, the extracted fingerprint image having the most similar feature point arrangement to the registered fingerprint image among the plurality of types of extracted fingerprint images.
[0017] An extracted fingerprint image other than one extracted fingerprint image included in the plurality of types of extracted fingerprint images is referred to as another extracted fingerprint image. The feature points and core lines extracted by different extraction methods, and the feature points and core lines existing in the corresponding regions may or may not match. Therefore, when one extracted fingerprint image and another extracted fingerprint image are overlapped, there are regions where the core lines overlap and regions where the core lines do not overlap. The generation unit 13 generates a differential core line image indicating the difference between the core line included in one extracted fingerprint image and the core line included in another extracted fingerprint image (step S13).
[0018] As described above, one extracted fingerprint image may be the extracted fingerprint image that has the most similar feature points to the registered fingerprint image among a plurality of types of extracted fingerprint images. Even when one extracted fingerprint image is the extracted fingerprint image that has the most similar feature points to the registered fingerprint image, in some cases, the feature points included in other extracted fingerprint images may be more similar to the feature points included in the registered fingerprint image than the feature points included in one extracted fingerprint image. In this case, if the feature points included in one extracted fingerprint image are partially updated with the feature points included in other extracted fingerprint images, the feature points included in one extracted fingerprint image will be more similar to the feature points included in the registered fingerprint image. Therefore, the update unit 14 updates the feature points and core lines included in one extracted fingerprint image based on the registered fingerprint image, one extracted fingerprint image, other extracted fingerprint images, and the differential core line image (step S14).
[0019] As described above, in the information processing apparatus 10, feature points and core lines are extracted from one fingerprint image by a plurality of types of extraction methods, and a plurality of extracted fingerprint images corresponding to each of the plurality of types of extraction methods are acquired. Based on the registered fingerprint image including the feature points corresponding to the fingerprint image and each of the plurality of types of extracted fingerprint images, one extracted fingerprint image is selected from the plurality of types of extracted fingerprint images. The information processing method includes performing a generation operation of a differential core line image indicating the difference between the core line included in one extracted fingerprint image and the core lines included in other extracted fingerprint images other than the one extracted fingerprint image included in the plurality of types of extracted fingerprint images, and performing an update operation of updating the feature points and core lines included in one extracted fingerprint image based on the registered fingerprint image, one extracted fingerprint image, other extracted fingerprint images, and the differential core line image.
[0020] The information processing device 10 described above may be implemented by a computer reading a computer program. In this case, the computer program may cause the computer to execute an information processing method that includes: extracting feature points and core lines from a single fingerprint image using multiple types of extraction methods and obtaining multiple extracted fingerprint images corresponding to each of the multiple types of extraction methods; selecting one extracted fingerprint image from the multiple types of extracted fingerprint images based on a registered fingerprint image containing feature points corresponding to the fingerprint image and each of the multiple types of extracted fingerprint images; generating a difference core line image showing the difference between the core lines contained in the one extracted fingerprint image and the core lines contained in other extracted fingerprint images other than the one extracted fingerprint image among the multiple types of extracted fingerprint images; and performing an update operation to update the feature points and core lines contained in the one extracted fingerprint image based on the registered fingerprint image, the one extracted fingerprint image, the other extracted fingerprint images, and the difference core line image. [Technical effects of the information processing device 10]
[0021] The information processing device 10 disclosed herein utilizes the fact that the feature points contained in the registered fingerprint image are the correct feature points, and that the core lines of the feature points extracted using the same extraction method are consistent. The information processing device 10 can generate core lines corresponding to the registered fingerprint image based on the core lines of the region of the extracted fingerprint image that contains the same feature points as the registered fingerprint image. [2: Second Embodiment]
[0022] A second embodiment relating to the information processing device, information processing method, and recording medium will be described with reference to Figures 3 to 7. In the following description, the second embodiment relating to the information processing device, information processing method, and recording medium will be described using the information processing device 20. In addition, explanations of the second embodiment that overlap with the description of the first embodiment described above will be omitted as appropriate. [2-1: Configuration of the Information Processing Device 20]
[0023] The configuration of the information processing device 20 will be described with reference to Figure 3. Figure 3 is a block diagram showing the configuration of the information processing device 20.
[0024] As shown in Figure 3, the information processing device 20 comprises an arithmetic unit 21 and a storage device 22. Furthermore, the information processing device 20 may also include a communication device 23, an input device 24, and an output device 25. However, the information processing device 20 does not have to include the communication device 23 and at least one of 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.
[0025] The arithmetic unit 21 includes at least one processor (i.e., one or more processors) as hardware. The processor may include, for example, a processor conforming to a von Neumann computer architecture. A processor conforming to a von Neumann computer architecture may include at least one of a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). The processor may also include, for example, a processor conforming to a non-von Neumann computer architecture. A processor conforming to a non-von Neumann computer architecture may include at least one of an FPGA (Field Programmable Gate Array) and an ASIC (Application Specific Circuit).
[0026] The arithmetic unit 21 reads a computer program 221 which includes at least one of computer program code and computer program directives. For example, the arithmetic unit 21 may read a computer program 221 stored in a storage device 22. For example, the arithmetic unit 21 may read a computer program 221 stored on a computer-readable and non-temporary recording medium using a recording medium reader (not shown) provided by the information processing device 20. The computer program 221 read from the recording medium may be stored in the storage device 22. The arithmetic unit 21 may obtain (i.e., download or read) a computer program 221 from a device (not shown) located outside the information processing device 20 via a communication device 23 (or other communication device). The downloaded computer program 221 may be stored in the storage device 22.
[0027] The arithmetic unit 21 executes the loaded computer program 221. As a result, logical functional blocks for executing the information processing that the information processing device 20 should perform are realized within the arithmetic unit 21. In other words, the arithmetic unit 21, together with the storage device 22 on which the computer program 221 is recorded (in other words, together with the storage device 22 and the computer program 221 recorded in the storage device 22), can function as a controller or computer for realizing logical functional blocks for executing the processing that the information processing device 20 should perform. That is, together with at least one processor in the arithmetic unit 21, the memory (recording medium) in the storage device 22 and the computer program 221 are configured so that the information processing device 20 performs the information processing that the information processing device 20 should perform.
[0028] Furthermore, the recording medium for recording the computer program 221 executed by the arithmetic unit 21 may include at least one of the following: optical discs such as CD-ROM, CD-R, CD-RW, flexible disk, MO, DVD-ROM, DVD-RAM, DVD-R, DVD+R, DVD-RW, DVD+RW, and Blu-ray®; magnetic media such as magnetic tape; magneto-optical disks; semiconductor memory such as USB memory; and any other medium capable of storing a program. The recording medium may also include equipment capable of recording computer programs (for example, general-purpose or dedicated equipment on which the computer program 221 is implemented in an executable state in at least one form such as software and firmware). Furthermore, each process and function included in the computer program 221 may be implemented by logical processing blocks realized within the arithmetic unit 21 (i.e., the processor) when the arithmetic unit 21 executes the computer program 221, or by hardware such as a predetermined gate array (FPGA (Field Programmable Gate Array), ASIC (Application Specific Integrated Circuit)) provided by the arithmetic unit 21, or in a form in which logical processing blocks and partial hardware modules that realize some elements of the hardware coexist.
[0029] The computing device 21 may implement a computational model that can be constructed by machine learning when the computing device executes a computer program 221. An example of a computational model that can be constructed by machine learning is a computational model that includes a neural network (so-called artificial intelligence (AI)). In this case, the learning of the computational model may include learning the parameters of the neural network (for example, at least one of the weights and biases). The computing device 21 may execute an information processing method using the computational model. That is, the operation of executing the information processing method may include an operation using the computational model. The computing device 21 may have a computational model that has been constructed by offline machine learning using training data implemented within it. Furthermore, the computational model implemented in the computing device 21 may be updated by online machine learning on the computing device 21. Alternatively, the computing device 21 may execute information processing using a computational model implemented in an external device (i.e., a device located outside the information processing device 20) in addition to or instead of the computational model implemented in the computing device 21.
[0030] Figure 3 shows an example of a logical functional block implemented in the arithmetic unit 21 to perform the generation of core wires corresponding to registered fingerprint images. As shown in Figure 3, the arithmetic unit 21 may implement an acquisition unit 211, a selection unit 212, a generation unit 213, an update unit 214, and a core wire addition unit 215. The "acquisition unit 211" is a component corresponding to the "acquisition unit 11" in the first embodiment described above, the "selection unit 212" is a component corresponding to the "selection unit 12" in the first embodiment described above, the "generation unit 213" is a component corresponding to the "generation unit 13" in the first embodiment described above, and the "update unit 214" is a component corresponding to the "update unit 14" in the first embodiment described above. The acquisition unit 211 may have a registered fingerprint image acquisition unit 2111 and an extraction unit 2112. The extraction unit 2112 may perform operations using an extraction model. The extraction model may be a specific example of the arithmetic model described above. The selection unit 212 may have a matching unit 2121. The generation unit 213 may have an update image selection unit 2131 and an overlay unit 2132. The update unit 214 may have a first update unit 2141, a second update unit 2142, and a third update unit 2143.
[0031] The storage device 22 includes at least one memory capable of storing desired data. In other words, the storage device 22 includes at least one memory containing desired data. For example, the storage device 22 may store a computer program 221 executed by the arithmetic unit 21. In this case, the storage device 22 (memory) may be used as the recording medium described above for recording the computer program 221 executed by the arithmetic unit 21. The storage device 22 may temporarily store data that the arithmetic unit 21 temporarily uses when it is executing the computer program 221. The storage device 22 may store data that the information processing device 20 stores long-term. The storage device 22 may include at least one of 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 a non-temporary recording medium.
[0032] The communication device 23 may be capable of communicating with devices outside the information processing device 20. Furthermore, the communication device 23 may use either wired or wireless communication.
[0033] The input device 24 is a device capable of receiving information input to the information processing device 20 from an external source. The input device 24 may include an operating device (e.g., a keyboard, mouse, touch panel, etc.) that can be operated by the user of the information processing device 20. The input device 24 may also include a recording medium reader capable of reading information recorded on a recording medium that can be attached to or detached from the information processing device 20, such as a USB (Universal Serial Bus) memory. When information is input to the information processing device 20 via the communication device 23 (in other words, when the information processing device 20 acquires information via the communication device 23), the communication device 23 may function as an input device.
[0034] The output device 25 is a device capable of outputting information to the outside of the information processing device 20. The output device 25 may output visual information such as characters and images, auditory information such as sounds, or tactile information such as vibrations. The output device 25 may include, for example, at least one of a display, speaker, printer, and vibration motor. The output device 25 may also be capable of outputting information to a recording medium that can be attached to or detached from the information processing device 20, such as a USB memory stick. When the information processing device 20 outputs information via the communication device 23, the communication device 23 may function as an output device. [2-2: Information processing operations performed by the information processing device 20]
[0035] The information processing operations performed by the information processing device 20 will be explained with reference to Figure 4. Figure 4 is a flowchart showing an example of the flow of information processing operations performed by the information processing device 20.
[0036] As shown in the information processing operation F20, the acquisition unit 211 acquires each of the multiple types of extracted fingerprint images (step S21). In step S21, the registered fingerprint image acquisition unit 2111 acquires the registered fingerprint image (step S211). The extraction unit 2112 extracts feature points and core lines from the fingerprint image corresponding to the registered fingerprint image (step S212). The extraction unit 2112 may extract feature points and core lines from the fingerprint image using one extraction method. The extraction unit 2112 may input the fingerprint image into one extraction model and output feature points and core lines.
[0037] The extraction unit 2112 may extract information indicating the position of the feature point, the direction of the feature point, and the type of feature point. The type of feature point may be either an endpoint or a branch point.
[0038] The extraction unit 2112 may, for example, extract lines as core lines by thinning the ridges contained in the fingerprint image to a width of 1 pixel. The extraction unit 2112 may also extract binary information by setting the pixel value of pixels corresponding to core lines to "1" and the pixel value of pixels that do not correspond to core lines to "0".
[0039] The acquisition unit 211 repeats the operation of step S22 until it has acquired each of the multiple types of extracted fingerprint images (step S213). For example, if the multiple types of extraction methods include the first to fourth types of extraction methods, in the first step S212, the extraction unit 2112 may extract feature points and core lines from the fingerprint image using the first type of extraction method. For example, the extraction unit 2112 may input the fingerprint image into the first type of extraction model and output feature points and core lines. In the second step S212, the extraction unit 2112 may extract feature points and core lines from the fingerprint image using the second type of extraction method. For example, the extraction unit 2112 may input the fingerprint image into the second type of extraction model and output feature points and core lines. In the third step S212, the extraction unit 2112 may extract feature points and core lines from the fingerprint image using the third type of extraction method. For example, the extraction unit 2112 may input the fingerprint image into a third type of extraction model and output feature points and core lines. Alternatively, in the fourth step S212, the extraction unit 2112 may extract feature points and core lines from the fingerprint image using a fourth type of extraction method. For example, the extraction unit 2112 may input the fingerprint image into a fourth type of extraction model and output feature points and core lines.
[0040] As shown in the information processing operation F20, the selection unit 212 selects one extracted fingerprint image from the multiple types of extracted fingerprint images based on the registered fingerprint image and each of the multiple types of extracted fingerprint images (step S22). In step S22, the matching unit 2121 matches the registered fingerprint image with each of the multiple types of extracted fingerprint images and calculates a matching score for each (step S221). The registered fingerprint image and the extracted fingerprint image may be determined based on feature points to see if corresponding regions in the images match. In other words, the matching unit 2121 may match the feature points included in the registered fingerprint image with each of the feature points included in the multiple types of extracted fingerprint images. The selection unit 212 selects the extracted fingerprint image with the highest matching score among the multiple types of extracted fingerprint images as the one extracted fingerprint image (step S222). The selection unit 212 may also associate the feature points included in the one extracted fingerprint image with the feature points included in the other extracted fingerprint images based on the feature points included in the registered fingerprint image.
[0041] As shown in the information processing operation F20, the generation unit 213 generates a difference core line image showing the difference between the core lines contained in one extracted fingerprint image and the core lines contained in another extracted fingerprint image (step S23). The extracted fingerprint images may be determined to match each other based mainly on the core lines, determining whether corresponding regions in the images match. In step S23, the update image selection unit 2131 selects another extracted fingerprint image for updating (step S231). For example, the update image selection unit 2131 may select an extracted fingerprint image from among several types of extracted fingerprint images that has the second most similar feature points to the registered fingerprint image as the other extracted fingerprint image for updating. For example, the update image selection unit 2131 may select an extracted fingerprint image from among the other extracted fingerprint images that has the least similar feature points to one of the registered fingerprint images as the other extracted fingerprint image for updating.
[0042] The core lines included in the extracted fingerprint image may be represented by a core line image. The core line image may be, for example, an image in which the pixel value of the pixel corresponding to the core line is "1" and the pixel value of the pixel that does not correspond to the core line is "0". The core line image corresponding to one extracted fingerprint image is referred to as the first core line image. The core line images corresponding to other extracted fingerprint images are referred to as other core line images. The overlay unit 2132 overlays the first core line image and the other core line images (step S232). The overlay unit 2132 may overlay the first core line image and the other core line images while performing linear transformations such as rotation and scaling using the feature point information associated by the selection unit 212.
[0043] The generation unit 213 generates a difference core line image showing the difference between one core line image and another core line image. The generation unit 213 may also generate an image representing core lines that exist only in one of the extracted fingerprint images, one extracted fingerprint image and the other extracted fingerprint image. The generation unit 213 may calculate the difference between the pixel values of each of the core line images and the other core line image. For example, the generation unit 213 may generate a difference core line image in which the pixel values of pixels with different pixel values are "1" and the pixel values of pixels with the same pixel values are "0". In other words, the generation unit 213 may generate a difference core line image in which the pixel values of pixels corresponding to core lines that exist only in one of the extracted fingerprint images, one extracted fingerprint image and the other extracted fingerprint image, are "1". In this way, the generation unit 213 generates a difference core line image showing the difference between core lines included in one extracted fingerprint image and core lines included in the other extracted fingerprint image (step S233).
[0044] As shown in the information processing operation F20, the update unit 214 updates the feature points and core lines included in the difference region of one extracted fingerprint image with the feature points and core lines included in the difference region of another extracted fingerprint image, based on the difference region in the difference core line image (step S24).
[0045] Each of the difference regions in the registered fingerprint image, the difference region in one extracted fingerprint image, and the difference region in another extracted fingerprint image may contain a predetermined number of feature points that have the same position and orientation. The predetermined number may be, for example, 3.
[0046] Figure 5 illustrates the difference regions Rx, Ry, and Rz in registered fingerprint image I0, the difference regions Rx, Ry, and Rz in one extracted fingerprint image I1, and the difference regions Rx, Ry, and Rz in another extracted fingerprint image I2. The difference region Rx may contain any of the feature points Pa, Pb, and Pc. The difference region Ry may contain any of the feature points Pd, Pe, and Pf. The difference region Rz may contain any of the feature points Pg, Ph, and Pi. Note that the core wires are omitted in Figure 5. [Step S241: Changing the type of feature point (endpoint, branch point)]
[0047] If the feature points included in a registered fingerprint image are of a different type than the feature points included in the difference region of a corresponding extracted fingerprint image, the feature points included in the registered fingerprint image are referred to as corresponding feature points, and the feature points included in the corresponding extracted fingerprint image are referred to as first feature points.
[0048] In Figure 5, the difference region Rx of the registered fingerprint image I0 includes feature points Pa, Pb, and Pc, while the difference region Rx of another fingerprint image I1 includes feature points Pa', Pb, and Pc. The corresponding feature points in the difference region Rx between the registered fingerprint image I0 and the other fingerprint image I1 match in position and direction, but feature points Pa and Pa' are of different types. For example, feature point Pa may be an endpoint, and feature point Pa' may be a branch point. In this case, feature point Pa may be called the corresponding feature point, and feature point Pa' may be called the first feature point. Furthermore, the difference region Rx of another fingerprint image I1, also illustrated in Figure 5, includes feature points Pa, Pb, and Pc. The corresponding feature points in the difference region Rx between the registered fingerprint image I0 and the other fingerprint image I2 match in position, direction, and type.
[0049] The first update unit 2141 updates the feature points and core lines included in the difference region of one extracted fingerprint image with the feature points and core lines included in the difference region of the other extracted fingerprint image if the type of feature point corresponding to the first feature point included in the other extracted fingerprint image is the same as the corresponding feature point. In the example shown in Figure 5, the first update unit 2141 may update the feature points and core lines included in the difference region Rx of one extracted fingerprint image I1 with the feature points and core lines included in the difference region Rx of the other extracted fingerprint image I2. This update changes the type of feature points in one extracted fingerprint image I1. [Step S242: Adding missing feature points]
[0050] If a feature point in the difference region of a registered fingerprint image does not correspond to a feature point in one of the extracted fingerprint images, the feature point in that registered fingerprint image is referred to as the corresponding feature point.
[0051] The difference region Ry of the registered fingerprint image I0, as illustrated in Figure 5, includes feature points Pd, Pe, and Pf, and the difference region Ry of one fingerprint image I1 also includes feature points Pd and Pe. Feature point Pf may be referred to as the corresponding feature point. The difference region Ry of one fingerprint image I1 does not contain a feature point corresponding to the corresponding feature point. Furthermore, the difference region Ry of another fingerprint image I1, as illustrated in Figure 5, includes feature points Pd, Pe, and Pf. In other words, the difference region Ry of another fingerprint image I2 contains a feature point corresponding to the corresponding feature point.
[0052] The second update unit 2142 updates the feature points and core lines included in the difference region of one extracted fingerprint image with the feature points and core lines included in the difference region of the other extracted fingerprint image if feature points corresponding to the corresponding feature points exist in other extracted fingerprint images. For example, as illustrated in Figure 5, the first update unit 2141 may update the feature points and core lines included in the difference region Ry of one extracted fingerprint image I1 with the feature points and core lines included in the difference region Ry of the other extracted fingerprint image I2. This update adds the corresponding feature points and the core lines corresponding to the corresponding feature points to one extracted fingerprint image I1. [Step S243: Deleting erroneous feature points]
[0053] If a feature point in the difference region of one extracted fingerprint image does not correspond to a feature point in the difference region of the registered fingerprint image, that feature point in the extracted fingerprint image is referred to as a third feature point.
[0054] The difference region Rz of the registered fingerprint image I0, as illustrated in Figure 5, includes feature points Pg and Ph, while the difference region Rz of another fingerprint image I1 includes feature points Pg, Ph, and Pi. Feature point Pi may be referred to as the third feature point. The difference region Rz of the registered fingerprint image I0 does not contain a feature point corresponding to the third feature point. Furthermore, the difference region Rz of the other fingerprint image I1, as illustrated in Figure 5, does not contain a feature point corresponding to the third feature point.
[0055] The third update unit 2143 updates the feature points and pinpoints included in the difference region of one extracted fingerprint image with the feature points and pinpoints included in the difference region of the other extracted fingerprint image if the feature points corresponding to the third feature point do not exist in the other extracted fingerprint image. For example, as illustrated in Figure 5, the first update unit 2141 may update the feature points and pinpoints included in the difference region Rz of one extracted fingerprint image I1 with the feature points and pinpoints included in the difference region Rz of the other extracted fingerprint image I2. This update removes the third feature point from one extracted fingerprint image I1.
[0056] Note that areas that have already been updated in steps S241 and S242 do not need to be updated even if they become candidates for deletion. Also, the order of steps S241, S242, and S243 does not matter. In other words, for example, step S242 or step S243 may be performed before step S241.
[0057] The core wire addition unit 215 associates the core wires included in the extracted fingerprint image after the update operation with the registered fingerprint image. The core wire addition unit 215 may also associate the core wires included in the extracted fingerprint image after the update operation with the registered fingerprint image 222 stored in the storage device 22 and store them therein. [2-3: Technical effects of the information processing device 20]
[0058] Fingerprint matching often utilizes the similarity of feature point arrangements. On the other hand, it has been shown that the accuracy of fingerprint matching can be improved by using the similarity of core lines in core line matching. However, for example, older data often lacks core lines. If core lines are absent, they cannot be used for fingerprint matching. The core lines included in registered fingerprint images should be information correctly added by forensic investigators. Therefore, automatically extracting core lines from the original fingerprint image often results in discrepancies with the correct core lines.
[0059] The information processing device 20 disclosed herein generates core lines of a fingerprint image based on multiple extracted fingerprint images. Therefore, it is possible to obtain core lines with the same accuracy as those included in a registered fingerprint image. Since core line matching can be performed when a fingerprint image containing core lines is used for fingerprint matching, more accurate fingerprint matching can be achieved compared to using a fingerprint image without core lines. [3: Third Embodiment]
[0060] A third embodiment relating to an information processing device, an information processing method, and a recording medium will be described with reference to Figures 6 and 7. In the following description, the third embodiment relating to an information processing device, an information processing method, and a recording medium will be described using the information processing device 30. In the third embodiment, explanations that overlap with the descriptions of the first and second embodiments described above will be omitted as appropriate. In the drawings, parts common to the first and second embodiments will be denoted by the same reference numerals.
[0061] As shown in Figure 6, the arithmetic unit 21 of the information processing device 30 includes, as logical functional blocks, an acquisition unit 211, a selection unit 212, a generation unit 313, an update unit 214, and a core wire addition unit 315. The generation unit 313 may also include an update image selection unit 3131 and an overlay unit 2132. The third embodiment differs from the second embodiment in that it determines the completion of the update operation.
[0062] As shown in Figure 7, the acquisition unit 211 acquires each of the multiple types of extracted fingerprint images (step S21). The selection unit 212 selects one extracted fingerprint image from the multiple types of extracted fingerprint images based on the registered fingerprint image and each of the multiple types of extracted fingerprint images (step S22). The generation unit 313 generates a difference core wire image that shows the difference between the core wires included in one extracted fingerprint image and the core wires included in other extracted fingerprint images (step S33).
[0063] In step S33, the update image selection unit 3131 may, for example, select another extracted fingerprint image that has not yet been used for update and whose feature points are most similar to those of the registered fingerprint image. In other words, the other extracted fingerprint image that the update image selection unit 3131 initially selects may be an extracted fingerprint image from among several types of extracted fingerprint images that has the second most similar feature points to the registered fingerprint image. Alternatively, the update image selection unit 3131 may, for example, select an extracted fingerprint image from among other extracted fingerprint images that has the least similar feature points to one of the registered fingerprint images as the other extracted fingerprint image for update.
[0064] The update unit 214 updates the feature points and core lines included in the difference region of one extracted fingerprint image with the feature points and core lines included in the difference region of another extracted fingerprint image, based on the difference region in the difference core line image (step S24).
[0065] The core wire addition unit 315 determines whether or not to terminate the updating of feature points and core wires (step S35). For example, the core wire addition unit 315 may determine to terminate the generation and update operations for each other extracted fingerprint image if the matching score between the registered fingerprint image and one extracted fingerprint image after the update operation exceeds a predetermined value. Alternatively, the core wire addition unit 315 may determine to terminate the generation and update operations for each other extracted fingerprint image if the processing time exceeds a predetermined time. Alternatively, the core wire addition unit 315 may determine to terminate the generation and update operations for each other extracted fingerprint image if it has performed generation and update operations for a predetermined number of other extracted fingerprint images.
[0066] The core wire addition unit 315 may, for example, reject the update and proceed to step S33 if the matching score between the registered fingerprint image and the extracted fingerprint image after the update operation is lower than the matching score between the registered fingerprint image and the extracted fingerprint image before the update operation. The core wire addition unit 315 may perform a comparison operation between the matching score between the registered fingerprint image and the extracted fingerprint image after the update operation and the matching score between the registered fingerprint image and the extracted fingerprint image before the update operation at each operation of steps S241, S242, and S243 shown in Figure 4. The core wire addition unit 315 may determine whether or not to reject the update at each operation of steps S241, S242, and S243 shown in Figure 4.
[0067] If it is determined that the updating of feature points and core wires is complete (step S35: Yes), the core wire addition unit 315 associates the core wires included in the extracted fingerprint image after the update operation with the registered fingerprint image (step S25). [Technical effects of the information processing device 30]
[0068] The information processing device 30 relating to this disclosure is By updating feature points and core lines using multiple extracted fingerprint images, it is possible to obtain a registered fingerprint image that accurately includes core lines. Furthermore, the information processing device 30 terminates the update operation at an appropriate time, thus suppressing unnecessary operations. [4: Fourth Embodiment]
[0069] A fourth embodiment relating to an information processing device, an information processing method, and a recording medium will be described with reference to Figures 8 and 9. In the following description, the fourth embodiment relating to an information processing device, an information processing method, and a recording medium will be described using the information processing device 40. In the fourth embodiment, explanations that overlap with the descriptions of the first to third embodiments described above will be omitted as appropriate. In the drawings, parts common to the first to third embodiments will be denoted by the same reference numerals.
[0070] As shown in Figure 8, the arithmetic unit 21 of the information processing device 40 includes, as logical functional blocks, an acquisition unit 411, a selection unit 212, a generation unit 313, an update unit 214, and a core wire addition unit 415. The acquisition unit 411 may also include a registered fingerprint image acquisition unit 4111 and an extraction unit 2112. The storage device 22 of the information processing device 40 may include an old registered fingerprint database 423 and a new registered fingerprint database 424.
[0071] As shown in Figure 9, the registered fingerprint image acquisition unit 4111 acquires a registered fingerprint image (step S41). The registered fingerprint image acquisition unit 4111 may acquire a registered fingerprint image from the old registered fingerprint database 423. In this embodiment, the old registered fingerprint database 423 may be a database in which registered fingerprint images are registered, and the registered fingerprint images registered in the old registered fingerprint database 423 may include or may not include core lines. The core lines included in the registered fingerprint images registered in the old registered fingerprint database 423 may be, for example, core lines identified by a forensic officer.
[0072] The registered fingerprint image acquisition unit 4111 determines whether the registered fingerprint image acquired in step S41 includes core lines (step S42). If the registered fingerprint image includes core lines (step S42: Yes), the core line addition unit 415 registers the registered fingerprint image including feature points and core lines in the new registered fingerprint database 424 (step S43). In this embodiment, the new registered fingerprint database 424 may be a database in which registered fingerprint images are registered, and the registered fingerprint images registered in the new registered fingerprint database 424 include feature points and core lines.
[0073] If the registered fingerprint image does not contain core lines (step S42: No), the acquisition unit 411 acquires each of the multiple types of extracted fingerprint images (step S21). The selection unit 212 selects one extracted fingerprint image from the multiple types of extracted fingerprint images based on the registered fingerprint image and each of the multiple types of extracted fingerprint images (step S22). The generation unit 213 generates a difference core line image showing the difference between the core lines contained in one extracted fingerprint image and the core lines contained in other extracted fingerprint images (step S33). The update unit 214 updates the feature points and core lines contained in the difference region of one extracted fingerprint image with the feature points and core lines contained in the difference region of other extracted fingerprint images based on the difference region containing the difference in the difference core line image (step S24).
[0074] If it is determined that the update of feature points and core lines is complete (Step S35: Yes), the core line addition unit 415 associates the core lines included in the extracted fingerprint image after the update operation with the registered fingerprint image and registers the registered fingerprint image including feature points and core lines in the new registered fingerprint database 424 (Step S43).
[0075] The registered fingerprint image acquisition unit 4111 determines whether or not there are registered fingerprint images that have not been acquired from the old registered fingerprint database 423 (step S44). If there are registered fingerprint images that have not been acquired (step S44: Yes), the process returns to step S41. If there are no registered fingerprint images that have not been acquired (step S44: No), the information processing operation in the fourth embodiment is terminated.
[0076] In this embodiment, a new registered fingerprint database 424 was constructed based on the old registered fingerprint database 423. The accuracy of fingerprint matching when a core wire is used is statistically higher than when a core wire is not used. Therefore, in general cases, it is sufficient to perform matching with registered fingerprint images registered in the new registered fingerprint database 424. However, when focusing on individual cases, the matching score may decrease. For this reason, in important cases, it is preferable to perform matching with registered fingerprint images registered in the old registered fingerprint database 423 in addition to matching with registered fingerprint images registered in the new registered fingerprint database 424. This prevents missed matches.
[0077] The information processing device 40 may be able to distinguish between registered fingerprint images containing automatically extracted core lines and registered fingerprint images containing core lines identified, for example, by a forensic officer. The core line addition unit 415 may be able to distinguish whether or not the core lines contained in registered fingerprint images registered in the new registered fingerprint database 424 are information added by the information processing device 40. For example, the core line addition unit 415 may add information indicating whether or not a registered fingerprint image contains core lines in the old registered fingerprint database 423 to the registered fingerprint images to be registered in the new registered fingerprint database 424. For example, the core line addition unit 415 may add predetermined flag information to the registered fingerprint images to which core lines contained in one extracted fingerprint image after the update operation are associated. The core line addition unit 415 may also add information indicating whether or not a core line is contained to registered fingerprint images registered in the old registered fingerprint database 423. The core wire addition section 415 may register registered fingerprint images in the new registered fingerprint database 424 so that the registered fingerprint images registered in the old registered fingerprint database 423 correspond to the registered fingerprint images registered in the new registered fingerprint database 424.
[0078] Furthermore, generally, registered fingerprint images in a fingerprint matching system often include both the fingerprint image and feature points. By restoring the core wires using the method of this embodiment and performing core wire matching in response to an inquiry request from outside the information processing device 40, the accuracy of fingerprint matching can be improved. [Technical effects of the information processing device 40]
[0079] The information processing device 40 disclosed herein can construct a new registered fingerprint database 424 in which all registered fingerprint images include core lines. Therefore, in addition to feature point matching, core line matching can be performed. [5: Results of Implementation]
[0080] Matching was performed between registered fingerprint images without core lines, registered fingerprint images including core lines identified by forensic officers, and registered fingerprint images with restored core lines, and between each of these and the found fingerprint images. For registered fingerprint images without core lines and found fingerprint images, only feature point matching was performed; core line matching was not performed. For registered fingerprint images with core lines and found fingerprint images, both feature point matching and core line matching were performed. For registered fingerprint images with restored core lines and found fingerprint images, both feature point matching and core line matching were performed. The first-place matching rate for registered fingerprint images without core lines was 70.4%, and the matching rate within 100 was 87.6%. For registered fingerprint images with core lines, the first-place matching rate was 86.0%, and the matching rate within 100 was 95.7%. For registered fingerprint images with restored core lines, the first-place matching rate was 82.9%, and the matching rate within 100 was 94.6%.
[0081] Thus, restoring the core wire allows for better matching compared to cases where the core wire is not included. Furthermore, using the restored core wire allows for matching equivalent to that performed when using a registered fingerprint image that includes the core wire.
[0082] [6: Addendum] The embodiments described above may also be described in the following appendix, but are not limited to these. [Note 1] An acquisition means for extracting feature points and core lines from a single fingerprint image using multiple types of extraction methods, and obtaining multiple extracted fingerprint images corresponding to each of the multiple types of extraction methods, A selection means for selecting one extracted fingerprint image from the multiple types of extracted fingerprint images based on a registered fingerprint image containing feature points corresponding to the aforementioned fingerprint image and each of the multiple types of extracted fingerprint images, A generation means that performs an operation to generate a difference core wire image showing the difference between a core wire included in the first extracted fingerprint image and a core wire included in other extracted fingerprint images other than the first extracted fingerprint image, which are included in the plurality of types of extracted fingerprint images. An update means that performs an update operation to update the feature points and core lines included in the first extracted fingerprint image based on the registered fingerprint image, the first extracted fingerprint image, the other extracted fingerprint image, and the difference core line image. An information processing device equipped with the following features. [Note 2] The update means updates the feature points and core lines included in the difference region in the first extracted fingerprint image with respect to the difference region in the other extracted fingerprint image, based on the difference region in the difference core line image. The information processing device described in Appendix 1. [Note 3] Each of the difference regions in the registered fingerprint image, the difference region in the first extracted fingerprint image, and the difference region in the other extracted fingerprint image contains a predetermined number of feature points that are in the same position and orientation. The update means is, The first feature point included in the difference region of the extracted fingerprint image is of a different type from the corresponding feature point included in the registered fingerprint image. If the type of feature point corresponding to the first feature point included in the other extracted fingerprint image is the same as the corresponding feature point, Update the feature points and core lines included in the difference region of the first extracted fingerprint image with the feature points and core lines included in the difference region of the other extracted fingerprint image. The information processing device described in Appendix 2. [Note 4] The update means is, If the feature points corresponding to the corresponding feature points included in the difference region of the registered fingerprint image do not exist in the first extracted fingerprint image, If a feature point corresponding to the aforementioned corresponding feature point exists in the other extracted fingerprint image, Update the feature points and core lines included in the difference region of the first extracted fingerprint image with the feature points and core lines included in the difference region of the other extracted fingerprint image. The information processing device described in Appendix 2. [Note 5] The update means is, A feature point corresponding to the third feature point included in the difference region of the first extracted fingerprint image does not exist in the difference region of the registered fingerprint image. If the feature point corresponding to the third feature point is not present in the other extracted fingerprint image, Update the feature points and core lines included in the difference region of the first extracted fingerprint image with the feature points and core lines included in the difference region of the other extracted fingerprint image. The information processing device described in Appendix 2. [Note 6] The selection means compares the registered fingerprint image with each of the multiple types of extracted fingerprint images and selects the extracted fingerprint image with the highest matching score among the multiple types of extracted fingerprint images as the first extracted fingerprint image. The information processing device described in Appendix 1. [Note 7] The generation operation and the update operation are performed for each of the multiple types of other extracted fingerprint images. The information processing device described in Appendix 1. [Note 8] If the matching score between the registered fingerprint image and the first extracted fingerprint image after the update operation exceeds a predetermined value, the generation operation and the update operation for each of the other extracted fingerprint images are terminated. The information processing device described in Appendix 7. [Note 9] The system includes a storage means for storing the core wires included in the extracted fingerprint image after the update operation, in association with the registered fingerprint image. The information processing device described in Appendix 1. [Note 10] The process involves extracting feature points and core lines from a single fingerprint image using multiple extraction methods, and obtaining multiple extracted fingerprint images corresponding to each of these multiple extraction methods. Based on the registered fingerprint image containing feature points corresponding to the aforementioned fingerprint image and each of the multiple types of extracted fingerprint images, one extracted fingerprint image is selected from the multiple types of extracted fingerprint images. The operation involves generating a difference core wire image that shows the difference between the core wires included in the first extracted fingerprint image and the core wires included in other extracted fingerprint images other than the first extracted fingerprint image, which are included in the plurality of types of extracted fingerprint images. Based on the registered fingerprint image, the first extracted fingerprint image, the other extracted fingerprint image, and the difference core wire image, an update operation is performed to update the feature points and core wires included in the first extracted fingerprint image. A method of information processing performed by a computer, including [the specified method]. [Note 11] The process involves extracting feature points and core lines from a single fingerprint image using multiple extraction methods, and obtaining multiple extracted fingerprint images corresponding to each of these multiple extraction methods. Based on the registered fingerprint image containing feature points corresponding to the aforementioned fingerprint image and each of the multiple types of extracted fingerprint images, one extracted fingerprint image is selected from the multiple types of extracted fingerprint images. The operation involves generating a difference core wire image that shows the difference between the core wires included in the first extracted fingerprint image and the core wires included in other extracted fingerprint images other than the first extracted fingerprint image, which are included in the plurality of types of extracted fingerprint images. Based on the registered fingerprint image, the first extracted fingerprint image, the other extracted fingerprint image, and the difference core wire image, an update operation is performed to update the feature points and core wires included in the first extracted fingerprint image. A computer program that causes a computer to execute an information processing method that includes such methods.
[0083] This disclosure may be modified as appropriate, insofar as it does not contradict the gist or idea of the invention as can be inferred from the claims and the specification as a whole, and information processing devices, information processing methods, and computer programs that include such modifications are also included in the technical idea of this disclosure. [Explanation of Symbols]
[0084] 10,20,30,40 Information Processing Devices 11,211,411 Acquisition Department 12,212 Selection Section 13,213,313 generation part 14,214,314 Update Department 2111,4111 Registered fingerprint image acquisition unit 2112 Extraction part 2121 Verification Unit 2131,3131 Image selection section for updates 2132 Overlap section 2141 1st update part 2142 2nd update part 2143 3rd update part 215, 315, 415 Core wire addition section 423 Old Registered Fingerprint Database 424 Newly Registered Fingerprint Database
Claims
1. An acquisition means for extracting feature points and core lines from a single fingerprint image using multiple types of extraction methods, and obtaining multiple extracted fingerprint images corresponding to each of the multiple types of extraction methods, A selection means for selecting one extracted fingerprint image from the multiple types of extracted fingerprint images based on a registered fingerprint image containing feature points corresponding to the aforementioned fingerprint image and each of the multiple types of extracted fingerprint images, A generation means that performs an operation to generate a difference core wire image showing the difference between a core wire included in the first extracted fingerprint image and a core wire included in other extracted fingerprint images other than the first extracted fingerprint image, which are included in the plurality of types of extracted fingerprint images. An update means that performs an update operation to update the feature points and core lines included in the first extracted fingerprint image based on the registered fingerprint image, the first extracted fingerprint image, the other extracted fingerprint image, and the difference core line image. An information processing device equipped with the following features.
2. The updating means updates the feature points and core lines included in the difference region in the first extracted fingerprint image based on the difference region in the difference core line image, using the feature points and core lines included in the difference region in the other extracted fingerprint image. The information processing apparatus according to claim 1.
3. Each of the difference regions in the registered fingerprint image, the difference region in the first extracted fingerprint image, and the difference region in the other extracted fingerprint image contains a predetermined number of feature points that are in the same position and orientation. The update means is, The first feature point included in the difference region of the extracted fingerprint image is of a different type from the corresponding feature point included in the registered fingerprint image. If the type of feature point corresponding to the first feature point included in the other extracted fingerprint image is the same as the corresponding feature point, Update the feature points and core lines included in the difference region of the first extracted fingerprint image with the feature points and core lines included in the difference region of the other extracted fingerprint image. The information processing apparatus according to claim 2.
4. The update means is, If the feature points corresponding to the corresponding feature points included in the difference region of the registered fingerprint image do not exist in the first extracted fingerprint image, If a feature point corresponding to the aforementioned corresponding feature point exists in the other extracted fingerprint image, Update the feature points and core lines included in the difference region of the first extracted fingerprint image with the feature points and core lines included in the difference region of the other extracted fingerprint image. The information processing apparatus according to claim 2.
5. The update means is, A feature point corresponding to the third feature point included in the difference region of the first extracted fingerprint image does not exist in the difference region of the registered fingerprint image. If the feature point corresponding to the third feature point is not present in the other extracted fingerprint image, Update the feature points and core lines included in the difference region of the first extracted fingerprint image with the feature points and core lines included in the difference region of the other extracted fingerprint image. The information processing apparatus according to claim 2.
6. The selection means compares the registered fingerprint image with each of the multiple types of extracted fingerprint images and selects the extracted fingerprint image with the highest matching score among the multiple types of extracted fingerprint images as the first extracted fingerprint image. The information processing apparatus according to claim 1.
7. The generation operation and the update operation are performed for each of the multiple types of other extracted fingerprint images. The information processing apparatus according to claim 1.
8. If the matching score between the registered fingerprint image and the first extracted fingerprint image after the update operation exceeds a predetermined value, the generation operation and the update operation for each of the other extracted fingerprint images are terminated. The information processing apparatus according to claim 7.
9. The system includes a storage means for storing the core wires included in the extracted fingerprint image after the update operation, in association with the registered fingerprint image. The information processing apparatus according to claim 1.
10. The process involves extracting feature points and core lines from a single fingerprint image using multiple extraction methods, and obtaining multiple extracted fingerprint images corresponding to each of these multiple extraction methods. Based on the registered fingerprint image containing feature points corresponding to the aforementioned fingerprint image and each of the multiple types of extracted fingerprint images, one extracted fingerprint image is selected from the multiple types of extracted fingerprint images. The operation involves generating a difference core wire image that shows the difference between the core wires included in the first extracted fingerprint image and the core wires included in other extracted fingerprint images other than the first extracted fingerprint image, which are included in the plurality of types of extracted fingerprint images. Based on the registered fingerprint image, the first extracted fingerprint image, the other extracted fingerprint image, and the difference core wire image, an update operation is performed to update the feature points and core wires included in the first extracted fingerprint image. A method of information processing performed by a computer, including [the specified method].
11. The process involves extracting feature points and core lines from a single fingerprint image using multiple extraction methods, and obtaining multiple extracted fingerprint images corresponding to each of these multiple extraction methods. Based on the registered fingerprint image containing feature points corresponding to the aforementioned fingerprint image and each of the multiple types of extracted fingerprint images, one extracted fingerprint image is selected from the multiple types of extracted fingerprint images. The operation involves generating a difference core wire image that shows the difference between the core wires included in the first extracted fingerprint image and the core wires included in other extracted fingerprint images other than the first extracted fingerprint image, which are included in the plurality of types of extracted fingerprint images. Based on the registered fingerprint image, the first extracted fingerprint image, the other extracted fingerprint image, and the difference core wire image, an update operation is performed to update the feature points and core wires included in the first extracted fingerprint image. A computer program that causes a computer to execute an information processing method that includes such methods.