Information processing system, information processing device, information processing method, and recording medium

Abstract

An information processing system (10) which is equipped with: a storage means (110) for storing first region information which depicts a clear zone from which it is possible to extract features of a ridge in a ridge image, and second region information which depicts an unclear zone, which is a region which excludes the clear zone, in association with each of a plurality of ridge images; an extraction means (120) for extracting third region information which depicts the clear zone and fourth region information which depicts the unclear zone from a ridge image; a calculation means (130) for calculating a first score based on the first region information and the second region information, and a second score based on the third region information and the fourth region information; and a selection means (140) for selecting a ridge image to be used in extraction means machine learning on the basis of the first and second scores.

Description

[Technical field]

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

[0002] Known systems of this type handle information about biological ridges (for example, lines that make up fingerprints or palm prints). Patent Document 1 discloses a technique for automatically extracting ridge regions in an image based on correlation values ​​that indicate similarity with multiple ridge template images. Patent Document 2 discloses a method for classifying regions in a fingerprint image using a model trained by machine learning. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2009-237941 A [Patent Document 2] JP 2018-165911 A Summary of the Invention [Problem to be solved by the invention]

[0004] This disclosure is intended to improve upon the techniques disclosed in the prior art documents. [Means for solving the problem]

[0005] One aspect of the information processing system of the disclosure includes a storage means for storing first region information indicating bright zones from which ridge features in a ridge image can be extracted, and second region information indicating unknown zones which are regions other than the bright zones, in association with each of a plurality of ridge images; an extraction means for extracting third region information indicating the bright zones and fourth region information indicating the unknown zones from the ridge image; a calculation means for calculating a first score based on the first region information and the second region information and a second score based on the third region information and the fourth region information; and a selection means for selecting the ridge image to be used for machine learning by the extraction means based on the first score and the second score.

[0006] One aspect of the information processing device disclosed herein comprises a storage means for storing first region information indicating bright zones from which ridge features in a ridge image can be extracted, and second region information indicating unknown zones which are regions other than the bright zones, in association with each of a plurality of ridge images; an extraction means for extracting third region information indicating the bright zones and fourth region information indicating the unknown zones from the ridge image; a calculation means for calculating a first score based on the first region information and the second region information and a second score based on the third region information and the fourth region information; and a selection means for selecting the ridge image to be used for machine learning by the extraction means based on the first score and the second score.

[0007] One aspect of the information processing method disclosed herein is an information processing method executed by at least one computer, which links first region information indicating bright zones from which ridge features can be extracted in a ridge image, and second region information indicating unknown zones which are areas other than the bright zones, to each of a plurality of ridge images and stores them, extracts third region information indicating the bright zones and fourth region information indicating the unknown zones from the ridge images, calculates a first score based on the first region information and the second region information and a second score based on the third region information and the fourth region information, and selects the ridge images to be used for machine learning of an extraction means that extracts the third region information and the fourth region information from the ridge image based on the first score and the second score.

[0008] One embodiment of the recording medium of the disclosure has recorded thereon a computer program for causing at least one computer to execute an information processing method that links first region information indicating bright zones from which ridge features in a ridge image can be extracted, and second region information indicating unknown zones which are areas other than the bright zones, to each of a plurality of ridge images, extracts third region information indicating the bright zones and fourth region information indicating the unknown zones from the ridge images, calculates a first score based on the first region information and the second region information and a second score based on the third region information and the fourth region information, and selects the ridge images to be used for machine learning of an extraction means that extracts the third region information and the fourth region information from the ridge image, based on the first score and the second score. [Brief description of the drawings]

[0009] [Figure 1] 1 is a block diagram showing a hardware configuration of an information processing system according to a first embodiment. [Diagram 2] 1 is a block diagram showing a functional configuration of an information processing system according to a first embodiment. [Diagram 3] FIG. 2 is a plan view showing an example of a bright zone and an unclear zone in a ridge image. [Figure 4] 5 is a flowchart showing the flow of a registration operation in the information processing system according to the first embodiment. [Diagram 5] 5 is a flowchart showing the flow of a selection operation in the information processing system according to the first embodiment. [Figure 6] FIG. 13 is a conceptual diagram showing an example of a score calculation method (edge ​​count) by the information processing system according to the second embodiment. [Figure 7] FIG. 11 is a plan view showing an example of score calculation by an information processing system according to a second embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of a score calculation method (island count) by the information processing system according to the third embodiment. [Figure 9]FIG. 13 is a plan view showing an example of score calculation by an information processing system according to a third embodiment. [Figure 10] FIG. 13 is a conceptual diagram showing an example of a score calculation method (binary smooth difference evaluation algorithm) by the information processing system according to the fourth embodiment. [Figure 11] FIG. 13 is a block diagram showing a functional configuration of an information processing system according to a fifth embodiment. [Figure 12] FIG. 13 is a block diagram showing a functional configuration of an information processing system according to a sixth embodiment. [Figure 13] FIG. 13 is a block diagram showing a functional configuration of an information processing system according to a seventh embodiment. [Figure 14] 13 is a table showing an example of the operation of the information processing system according to the seventh embodiment.

[0010] Hereinafter, embodiments of an information processing system, an information processing device, an information processing method, and a recording medium will be described with reference to the drawings.

[0011] First Embodiment An information processing system according to a first embodiment will be described with reference to FIGS. 1 to 5. FIG.

[0012] (Hardware configuration) First, the hardware configuration of the information processing system according to the first embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the hardware configuration of the information processing system according to the first embodiment.

[0013] 1, an information processing system 10 according to the first embodiment includes a processor 11, a RAM (Random Access Memory) 12, a ROM (Read Only Memory) 13, and a storage device 14. The information processing system 10 may further include an input device 15 and an output device 16. The above-mentioned processor 11, RAM 12, ROM 13, storage device 14, input device 15, and output device 16 are connected via a data bus 17.

[0014] The processor 11 reads a computer program. For example, the processor 11 is configured to read 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 read 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., read) a computer program from a device (not shown) disposed outside the information processing system 10 via a network interface. The processor 11 controls the RAM 12, the storage device 14, the input device 15, and the output device 16 by executing the computer program that has been read. In particular, in this embodiment, when the processor 11 executes the computer program that has been read, a functional block that executes processing related to learning using a ridge image is realized in the processor 11. That is, the processor 11 may function as a controller that executes each control of the information processing system 10.

[0015] 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 demand-side platform (DSP), or an application specific integrated circuit (ASIC). The processor 11 may be configured as one of these, or may be configured to use a plurality of these in parallel.

[0016] The RAM 12 temporarily stores a computer program executed by the processor 11. The RAM 12 temporarily stores data that is temporarily used by the processor 11 when the processor 11 is executing the computer program. The RAM 12 may be, for example, a D-RAM (Dynamic RAM).

[0017] The ROM 13 stores computer programs executed by the processor 11. The ROM 13 may also store other fixed data. The ROM 13 may be, for example, a programmable ROM (P-ROM).

[0018] The storage device 14 stores data that is to be stored long-term by the information processing system 10. The storage device 14 may operate as a temporary storage device for 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.

[0019] The input device 15 is a device that receives an input instruction from a user of the information processing system 10. 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 be configured as a mobile terminal such as a smartphone or a tablet.

[0020] The output device 16 is a device that outputs information related to the information processing system 10 to the outside. For example, the output device 16 may be a display device (e.g., a display) that can display information related to the information processing system 10. The output device 16 may also be a speaker or the like that can output information related to the information processing system 10 as audio. The output device 16 may be configured as a mobile terminal such as a smartphone or a tablet.

[0021] 1 shows an example of an information processing system 10 including a plurality of devices, but all or a part of the functions may be realized by one device (information processing device). This information processing device may be configured to include only the above-mentioned processor 11, RAM 12, and ROM 13, and the other components (i.e., storage device 14, input device 15, output device 16) may be provided by an external device connected to the information processing device. Also, the information processing device may have some of its calculation functions realized by an external device (e.g., an external server, a cloud, etc.).

[0022] (Functional configuration) Next, the functional configuration of the information processing system 10 according to the first embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing the functional configuration of the information processing system according to the first embodiment.

[0023] As shown in Fig. 2, the information processing system 10 according to the first embodiment is configured to include, as components for realizing its functions, a registration information database (DB) 110, a zone information extraction unit 120, a score calculation unit 130, and a selection unit 140. The registration information database may be configured, for example, by the above-mentioned storage device 14 (see Fig. 1). Each of the zone information extraction unit 120, the score calculation unit 130, and the selection unit 140 may be a processing block realized, for example, by the above-mentioned processor 11 (see Fig. 1).

[0024] The registration information database 110 is configured to be able to store a plurality of ridge line images. The ridge line image is an image including ridge lines of a living body, and examples thereof include a fingerprint image and a palm print image. The registration information database 110 is also configured to be able to store bright zone information and unknown zone information in association with each of the plurality of ridge line images. The bright zone information is information indicating an area (bright zone) from which a feature amount of a ridge line in a ridge line image can be extracted. The unknown zone information is information indicating an area other than the bright zone in the ridge line image (i.e., an area from which a feature amount of a ridge line in a ridge line image cannot be extracted). The bright zone information and the unknown zone information may be information indicating which part of the ridge line image the bright zone and the unknown zone are (e.g., position information of the bright zone and the unknown zone). The bright zone information and the unknown zone information may be set for each pixel, for example, or may be set for each area consisting of a plurality of pixels. The bright zone and the unknown zone will be described in detail later with a specific example.

[0025] The zone information extraction unit 120 is configured to be able to extract the bright zone information and the unknown zone information from the ridge line image stored in the registration information database 110. The zone information extraction unit 120 may be configured to extract the bright zone information and the unknown zone using a model that has been machine-learned in advance. The bright zone information and the unknown zone information extracted by the zone information extraction unit 120 (hereinafter, appropriately referred to as "extracted zone information") may be the same as the bright zone information and the unknown zone information stored in the registration information database 110 (hereinafter, appropriately referred to as "registered zone information"). For example, when the bright zone information and the unknown zone information extracted by the zone information extraction unit 120 are registered in the registration information database 110 as is, the extracted zone information and the registered zone information are the same. On the other hand, when the bright zone information and the unknown zone information extracted by the zone information extraction unit 120 are registered after being partially corrected, for example, the extracted zone information and the registered zone information are different. The correction of the bright zone information and the unknown zone information will be described in detail later.

[0026] The score calculation unit 130 is configured to be able to calculate a first score based on the registered zone information stored in the registered information database 110. The score calculation unit 130 is also configured to be able to calculate a second score based on the extracted zone information extracted by the zone information extraction unit 120. The first score and the second score are scores for calculating how suitable the registered zone information and the extracted zone information are for machine learning.

[0027] The selection unit 140 is configured to be able to select a ridge line image to be used for machine learning in the zone information extraction unit 120 based on the first score and the second score calculated by the score calculation unit 130. For example, the selection unit 140 may compare the first score and the second score with each other, and select an image having a large difference therebetween (for example, an image having a difference equal to or greater than a predetermined threshold) as a ridge line image to be used for machine learning. In this case, the predetermined threshold may be determined and set as an appropriate value in advance. Also, the predetermined threshold may be configured to be manually changeable. For example, when learning is to be performed using more ridge line images, the predetermined threshold may be lowered, and when learning is to be performed using only images more suitable for learning, the predetermined threshold may be raised. The selection unit 140 may output the bright zone information and the unknown zone information (i.e., the registered zone information) that are linked to and stored in the selected ridge line image, as data to be used for machine learning.

[0028] Note that learning using the ridge image selected by the selection unit 140 (i.e., learning by the zone information extraction unit 120) may be performed by a learning unit external to the system. However, the information processing system 10 according to this embodiment may also be equipped with a learning unit. Learning by the learning unit may be performed periodically, or in response to a user operation. For example, a "re-learn" button may be displayed on the system management screen, and learning may be performed when the user presses the button.

[0029] (Bright zone and unknown zone) Next, the bright zones and the unknown zones in a ridge line image will be specifically described with reference to Fig. 3. Fig. 3 is a plan view showing an example of the bright zones and the unknown zones in a ridge line image. Note that Fig. 3 shows a fingerprint image as an example of the ridge line image.

[0030] As shown in FIG. 3, bright zones in a ridge line image may be set as areas that include ridge lines. From bright zones set in this way, it is possible to appropriately extract features related to ridge lines. On the other hand, unknown zones in a ridge line image may be set as areas that do not include ridge lines. Furthermore, unknown zones may be set as areas that include ridge lines but from which it is difficult to extract features (for example, the wrinkled area shown in FIG. 3). Zone information extraction unit 120 will learn to be able to appropriately determine these bright zones and unknown zones.

[0031] Note that the method of setting the bright zone and the unknown zone here is merely an example, and the bright zone and the unknown zone may be set using a different logic. Furthermore, the bright zone and the unknown zone may be manually corrected as appropriate, as described in the registration operation below. For example, an area determined as a bright zone by the zone information extraction unit 120 may be manually changed to an unknown zone. Similarly, an area determined as an unknown zone by the zone information extraction unit 120 may be manually changed to a bright zone.

[0032] (Registration action) Next, a flow of operations (hereinafter, appropriately referred to as "registration operations") when registering a ridge line image, bright zone information, and unknown zone information in the registration information database 110 in the information processing system 10 according to the first embodiment will be described with reference to Fig. 4. Fig. 4 is a flowchart showing the flow of the registration operations by the information processing system according to the first embodiment.

[0033] As shown in FIG. 4, when the information processing system 10 according to the first embodiment performs a registration operation, first, a ridge line image is acquired (step S51). The ridge line image may be acquired using, for example, a camera or a scanner. Thereafter, the zone information extraction unit 120 extracts bright zone information and unknown zone information from the acquired ridge line image (step S52). That is, the bright zones and unknown zones in the ridge line image are determined. Note that information on the setting values ​​of the zone information extraction unit 120 at this time (for example, image brightness, contrast, etc.) may be stored in the registration information database 110. The stored information on the setting values ​​may be output as an element to be used for learning, together with, for example, the bright zone information and the unknown zone information.

[0034] Next, the bright zone information and the unknown zone information are manually corrected (step S53). For example, even if a region is determined as a bright zone by the zone information extraction unit 120, if it can be determined as an unknown zone when viewed by the human eye, the bright zone may be changed to an unknown zone. Similarly, even if a region is determined as an unknown zone by the zone information extraction unit 120, if it can be determined as a bright zone when viewed by the human eye, the unknown zone may be changed to a bright zone. The registration information database 110 may store information regarding the history of the correction performed in step S53. For example, information indicating the position of the region where the bright zone has been changed to an unknown zone and the position of the region where the unknown zone has been changed to a bright zone may be stored. The information regarding the history of the correction may be output as an element used for learning, for example, together with the bright zone information and the unknown zone information.

[0035] Next, the acquired ridge line image and the bright zone information and the unknown zone information extracted from the ridge line image are registered in the registration information database 110 (step S54). The above-mentioned correction of the bright zone information and the unknown zone information may not necessarily be performed before registration. That is, the process of the above-mentioned step S53 may be omitted as appropriate. For example, if it is determined that there is no area to be corrected, the information may be registered without correction. Also, if the worker who performs the correction work does not have time immediately, the extracted information may be registered as it is without correction. As a result, the bright zone information and the unknown zone information registered in the registration information database 110 include a mixture of information corrected by hand and information that has not been corrected. Also, since the amount and quality of correction depend on the skill level of the worker who performed the correction work, not all of the corrected bright zone information and the unknown zone information are necessarily corrected appropriately (in other words, suitable for learning).

[0036] (Selection action) Next, a flow of an operation (hereinafter, appropriately referred to as a "selection operation") performed when selecting an image to be used for machine learning by the zone information extraction unit 120 in the information processing system 10 according to the first embodiment will be described with reference to Fig. 5. Fig. 5 is a flowchart showing the flow of the selection operation by the information processing system according to the first embodiment. Note that the selection operation may be started at the timing of executing machine learning.

[0037] 5, when the information processing system 10 according to the first embodiment performs a selection operation, first, information (i.e., ridge line image, bright zone information, and unknown zone information) registered in the registered information database 110 is read (step S101). Then, the zone information extraction unit 120 newly extracts bright zone information and unknown zone information from the read ridge line image (step S102).

[0038] Next, the score calculation unit 130 calculates a first score based on the bright zone information and unknown zone information (i.e., registered zone information) registered in the registration information database 110, and calculates a second score based on the bright zone information and unknown zone information (i.e., extracted zone information) extracted by the zone information extraction unit 120 (step S103).

[0039] Next, based on the first score and the second score calculated by the score calculation unit 130, a ridge line image to be used for training the zone information extraction unit 120 is selected (step S104). The above-mentioned series of operations may be executed for all ridge line images registered in the registered information database 110. However, the above-mentioned series of operations may be executed for only some of the ridge line images registered in the registered information database 110. In other words, all registered ridge line images do not have to be selected by the selection operation. The operation in this way when only some of the ridge line images are the target will be described in detail in another embodiment described later.

[0040] (Technical effect) Next, technical effects obtained by the information processing system 10 according to the first embodiment will be described.

[0041] As described in FIG. 1 to FIG. 5, in the information processing system 10 according to the first embodiment, a ridge image to be used for machine learning is selected based on a first score calculated from bright zone information and unknown zone information (registered zone information) that are linked to and stored with a ridge image, and a second score calculated from the extracted bright zone information and unknown zone information (extracted zone information). In this way, it is possible to select a ridge image suitable for learning and perform more appropriate machine learning. For example, a ridge image with a large difference between the first score and the second score can be determined to have been subjected to many manual corrections. By using such a ridge image, more appropriate machine learning can be realized compared to the case of using a ridge image that has not been manually corrected (or has few corrections).

[0042] <Second embodiment> An information processing system 10 according to the second embodiment will be described with reference to Fig. 6 and Fig. 7. Note that the second embodiment shows a specific example of a score calculation method in the score calculation unit 130, and the system configuration and the overall operation flow may be the same as those of the first embodiment. Therefore, in the following, the parts that differ from the first embodiment already described will be described in detail, and the explanation of other overlapping parts will be omitted as appropriate.

[0043] (edge ​​count) First, a score calculation method by the information processing system 10 according to the second embodiment will be described with reference to Fig. 6 and Fig. 7. Fig. 6 is a conceptual diagram showing an example of a score calculation method (edge ​​count) by the information processing system according to the second embodiment. Fig. 7 is a plan view showing an example of score calculation by the information processing system according to the second embodiment.

[0044] 6, in the information processing system 10 according to the second embodiment, the score calculation unit 130 calculates the first score and the second score (hereinafter, simply referred to as "score") using an algorithm called edge count. In this embodiment, it is assumed that a bright zone and an unknown zone are set for each pixel.

[0045] The score calculation unit 130 calculates the score based on how many pixels in the unknown zone exist around a pixel in the bright zone. For example, in the example shown in FIG. 6(a), of the four pixels above, below, left, and right that exist around a pixel in the central bright zone, all four pixels are unknown zones. In this way, when there are four pixels in the unknown zone around the pixel, the score calculation unit 130 calculates the score to be "4". In the example shown in FIG. 6(b), of the four pixels above, below, left, and right that exist around a pixel in the central bright zone, two pixels above and to the right are unknown zones (the left and below are bright zones). In this way, when there are two pixels in the unknown zone around the pixel, the score calculation unit 130 calculates the score to be "2".

[0046] In the above example, the four pixels above, below, left, and right of the central bright zone are used for score calculation, but there is no particular limitation on which pixels are used as the surrounding pixels. For example, the score calculation unit 130 may use the surrounding eight pixels (i.e., above, below, left, right, upper right, lower right, upper left, and lower left) for score calculation.

[0047] As shown in FIG. 7, the score calculation unit 130 may sum up the scores calculated for all pixels in the bright zone in the ridge line image to obtain the final score for the ridge line image. For example, a score of "3229" is calculated from the zone information extracted by the zone information extraction unit 120 shown in FIG. 7(a). On the other hand, a score of "2776" is calculated from the zone information after the correction work shown in FIG. 7(b). In this way, manual corrections tend to result in a smaller score calculated by edge count. Therefore, the smaller the score calculated by edge count, the more corrections have been made. Therefore, if many manual corrections have been made, the difference between the first score and the second score becomes larger.

[0048] In the above example, the final score is calculated by adding up the scores of all pixels, but the final score may be calculated using other methods. For example, the score calculation unit 130 may calculate the final score by averaging the scores of each pixel. Alternatively, the score calculation unit 130 may calculate the final score by weighting each pixel and adding the scores.

[0049] (Technical effect) Next, technical effects obtained by the information processing system 10 according to the second embodiment will be described.

[0050] 6 and 7, in the information processing system 10 according to the second embodiment, the first score and the second score are calculated using edge count. In this way, the score of the ridge line image can be calculated easily and accurately. Therefore, it becomes possible to appropriately select a ridge line image suitable for learning.

[0051] <Third embodiment> An information processing system 10 according to the third embodiment will be described with reference to Fig. 8 and Fig. 9. As with the second embodiment described above, the third embodiment shows a specific example of a score calculation method in the score calculation unit 130, and the system configuration and overall operation flow may be the same as those of the first embodiment. Therefore, in the following, only the parts that differ from the first and second embodiments already described will be described in detail, and the description of other overlapping parts will be omitted as appropriate.

[0052] (island count) First, a score calculation method by the information processing system 10 according to the third embodiment will be described with reference to Fig. 8 and Fig. 9. Fig. 8 is a conceptual diagram showing an example of a score calculation method (island count) by the information processing system according to the third embodiment. Fig. 9 is a plan view showing an example of score calculation by the information processing system according to the third embodiment.

[0053] In FIG. 8, in the information processing system 10 according to the second embodiment, the score calculation section 130 calculates the first score and the second score using an algorithm called island count.

[0054] The score calculation unit 130 calculates the score based on the number of unknown zones surrounded by bright zones. For example, in the example shown in FIG. 7(a), the pixel of the unknown zone in the center is surrounded by pixels of the bright zone. Specifically, the eight pixels (i.e., top, bottom, left, right, upper right, lower right, upper left, and lower left) surrounding the pixel of the unknown zone in the center are all bright zones. In this case, the score calculation unit 130 counts the unknown zone in the center as one island. On the other hand, in the example shown in FIG. 7(b), the pixel of the unknown zone in the center is surrounded by pixels of the bright zone, but some of them are unknown zones. Specifically, of the eight pixels (i.e., top, bottom, left, right, upper right, lower right, upper left, and lower left) surrounding the pixel of the unknown zone in the center, the pixels other than the upper right are bright zones, but only the upper right is an unknown zone. In this case, the score calculation unit 130 does not count the unknown zone in the center as one island.

[0055] In the above example, the central unknown zone is one pixel in size, but the unknown zone may be multiple pixels in size. For example, if two adjacent unknown zones are surrounded by light zones, the two unknown zones may be counted as one island.

[0056] As shown in FIG. 9, the score calculation unit 130 may calculate the number of islands counted in the image as the score. For example, two islands exist in the zone information extracted by the zone information extraction unit 120 shown in FIG. 7(a). Therefore, the score in this case is calculated as "2". On the other hand, no islands exist in the zone information after the correction work shown in FIG. 7(b). Therefore, the score in this case is calculated as "0". In this way, manual corrections may result in a smaller score calculated by the island count. Therefore, the smaller the score calculated by the island count, the more corrections have been made. Therefore, if many manual corrections have been made, the difference between the first score and the second score becomes larger.

[0057] (Technical effect) Next, technical effects obtained by the information processing system 10 according to the third embodiment will be described.

[0058] 8 and 9, in the information processing system 10 according to the third embodiment, the first score and the second score are calculated using the island count. In this way, the score of the ridge line image can be calculated easily and accurately. Therefore, it becomes possible to appropriately select a ridge line image suitable for learning.

[0059] <Fourth embodiment> An information processing system 10 according to the fourth embodiment will be described with reference to Fig. 10. Note that the fourth embodiment, like the second and third embodiments described above, shows a specific example of a score calculation method in the score calculation unit 130, and the system configuration and overall operation flow may be the same as those of the first embodiment. Therefore, in the following, the parts that differ from the first to third embodiments already described will be described in detail, and the explanation of other overlapping parts will be omitted as appropriate.

[0060] (Binary smooth difference evaluation algorithm) First, a score calculation method by the information processing system 10 according to the fourth embodiment will be described with reference to Fig. 10. Fig. 10 is a conceptual diagram showing an example of a score calculation method (binary smooth difference evaluation algorithm) by the information processing system according to the fourth embodiment.

[0061] In FIG. 10, in the information processing system 10 according to the fourth embodiment, the score calculation section 130 calculates the first score and the second score using a binary smooth difference evaluation algorithm (hereinafter, appropriately referred to as "binary smooth").

[0062] The score calculation unit 130 first arranges nine pixels of the ridge image in a horizontal row and converts them into a bit string of "0" and "1". For example, the score calculation unit 130 converts a bright zone into "1" and an unknown zone into "0". In the example shown in FIG. 10, the leftmost pixel is a bright zone and the others are unknown zones, so the bit string is "1,0,0,0,0,0,0,0,0,0". Then, the score calculation unit 130 compares this bit string with a pre-stored table to determine whether or not to invert the central pixel. That is, the score calculation unit 130 determines whether or not to invert the central bright zone located in the center of the nine pixels into an unknown zone. In the table, for example, a value of "1" or "0" is stored for each of 256 possible values ​​of the bit string (that is, whether or not to invert is stored).

[0063] If the bright zone and the unknown zone are inverted as a result of the above-mentioned processing, the score calculation unit 130 counts the pixel as a pixel to be inverted. On the other hand, if the bright zone and the unknown zone are not inverted, the score calculation unit 130 does not count the pixel as a pixel to be inverted. Then, the score calculation unit 130 counts the pixels to be inverted for all pixels included in the ridge pixels, and calculates the total number as the score. This score is a value indicating the irregularity of the shape of the bright zone and the unknown zone, and for example, the more irregular the shape of the zone is, the larger the value becomes. Here, in particular, the irregularity is less in the zone information after the correction work compared to before the correction work, and the score calculated as above becomes smaller. Therefore, for the score calculated using the binary smooth, the smaller the value, the more corrections are made. Therefore, if many manual corrections are made, the difference between the first score and the second score becomes larger.

[0064] (Technical effect) Next, technical effects obtained by the information processing system 10 according to the fourth embodiment will be described.

[0065] 10, in the information processing system 10 according to the fourth embodiment, the first score and the second score are calculated using a binary smooth difference evaluation algorithm. In this way, the score of the ridge line image can be calculated easily and accurately. Therefore, it becomes possible to appropriately select a ridge line image suitable for learning.

[0066] It should be noted that all of the algorithms described in the second to fourth embodiments (i.e., edge count, island count, and binary smooth difference evaluation algorithm) may be made available, and one appropriate algorithm may be selected and used as appropriate. Also, a combination of multiple algorithms may be used. For example, a ridge image to be used in machine learning may be selected using an integrated score obtained by integrating scores calculated by multiple algorithms.

[0067] <Fifth embodiment> An information processing system 10 according to the fifth embodiment will be described with reference to Fig. 11. The fifth embodiment differs from the first to fourth embodiments described above only in part of the configuration and operation, and other parts may be the same as the first to fourth embodiments. Therefore, hereinafter, parts that differ from the embodiments already described will be described in detail, and explanations of other overlapping parts will be omitted as appropriate.

[0068] (Functional configuration) First, the functional configuration of the information processing system 10 according to the fifth embodiment will be described with reference to Fig. 11. Fig. 11 is a block diagram showing the functional configuration of the information processing system according to the fifth embodiment. In Fig. 12, the same elements as those shown in Fig. 2 are denoted by the same reference numerals.

[0069] As shown in FIG. 11, the information processing system 10 according to the fifth embodiment is configured to include, as components for realizing its functions, a registration information database 110, a zone information extraction unit 120, a score calculation unit 130, a selection unit 140, a version information assignment unit 150, and a first learning setting unit 160. That is, the information processing system 10 according to the fifth embodiment further includes the version information assignment unit 150 and the first learning setting unit 160 in addition to the configuration of the first embodiment (see FIG. 2). Each of the version information assignment unit 150 and the first learning setting unit 160 may be a processing block realized by, for example, the above-mentioned processor 11 (see FIG. 1).

[0070] The version information assigning unit 150 is configured to be able to assign version information indicating the version of the zone information extracting unit 120. The version of the zone information extracting unit 120 is updated every time machine learning is executed, and it is possible to identify ridge images that have already been used in machine learning from the current version information. For example, the version information assigning unit 150 links the ridge image selected by the selecting unit 140 (i.e., the image used in machine learning) to version information that is assigned after machine learning using that image. In addition, the version information may be linked to a ridge image used in previous machine learning (for example, machine learning two times before or three times before). This makes it possible to identify ridge images that have already been used in machine learning from the current version information.

[0071] The first learning setting unit 160 can set, based on the version information, not to use a ridge line image that has already been used in machine learning in subsequent machine learning. The first learning setting unit 160 acquires current version information, for example, from the zone information extraction unit 120. Then, it outputs information on a ridge line image identified from the version information to the registered information database 110. The registered information database 110, for example, prevents the ridge line image identified from the version information (i.e., a ridge line image that has already been used in machine learning) from being output as a next selection candidate. That is, a score is not calculated for the ridge line image identified from the version information.

[0072] (Technical effect) Next, technical effects obtained by the information processing system 10 according to the fifth embodiment will be described.

[0073] As described in Fig. 11, in the information processing system 10 according to the fifth embodiment, a ridge image that has already been used in machine learning will not be used in subsequent machine learning. In this way, it is possible to prevent the same image from being used in machine learning multiple times, and it is possible to realize more efficient machine learning. In addition, since the number of images for which the score is calculated can be reduced, the processing load of the selection operation can also be reduced.

[0074] Sixth embodiment An information processing system 10 according to the sixth embodiment will be described with reference to Fig. 12. The sixth embodiment differs from the first to fifth embodiments in part of its configuration and operation, and other parts may be the same as the first to fifth embodiments. Therefore, hereinafter, parts that differ from the embodiments already described will be described in detail, and other overlapping parts will be omitted as appropriate.

[0075] (Functional configuration) First, the functional configuration of the information processing system 10 according to the sixth embodiment will be described with reference to Fig. 12. Fig. 12 is a block diagram showing the functional configuration of the information processing system according to the sixth embodiment. In Fig. 12, the same elements as those shown in Fig. 2 are denoted by the same reference numerals.

[0076] As shown in FIG. 12, the information processing system 10 according to the sixth embodiment is configured to include, as components for realizing its functions, a registration information database 110, a zone information extraction unit 120, a score calculation unit 130, a selection unit 140, an update timing acquisition unit 170, a learning timing acquisition unit 180, and a second learning setting unit 190. That is, the information processing system 10 according to the sixth embodiment further includes, in addition to the configuration of the first embodiment (see FIG. 2), an update timing acquisition unit 170, a learning timing acquisition unit 180, and a second learning setting unit 190. Each of the update timing acquisition unit 170, the learning timing acquisition unit 180, and the second learning setting unit 190 may be a processing block realized by, for example, the above-mentioned processor 11 (see FIG. 1).

[0077] The update timing acquisition unit 170 is configured to be able to acquire information indicating the update timing at which the bright zone information and the unknown zone information (i.e., the registered zone information) stored in the registration information database 110 were updated. The update timing may be acquired, for example, as information indicating a date and time. The update timing information may be, for example, information indicating the timing at which either one of the bright zone information and the unknown zone information was updated, or information indicating the timing at which both the bright zone information and the unknown zone information were updated.

[0078] The learning timing acquisition unit 180 is configured to be able to acquire information indicating the timing at which learning was performed by the zone information extraction unit 120. The learning timing may be acquired as information indicating date and time, for example. Note that, as in the above-mentioned fifth embodiment, when the version information assignment unit 150 is provided (i.e., when the version of the zone information extraction unit 120 is updated every time machine learning is performed), the learning timing acquisition unit 180 may acquire information regarding the learning timing from the version information.

[0079] The second learning setting unit 190 sets a ridge line image whose update timing is later than the learning timing to be used in the next machine learning from that point on. For example, the second learning setting unit 190 instructs the registration information database 110 to output a ridge line image whose update timing is later than the learning timing as a next selection candidate. Therefore, for a ridge line image whose update timing is later than the learning timing, a first score and a second score are calculated when machine learning is executed, and a selection is made according to these scores. Note that the second learning setting unit 190 may set a ridge line image whose update timing is earlier than the learning timing not to be used in the next machine learning from that point on.

[0080] (Technical effect) Next, technical effects obtained by the information processing system 10 according to the sixth embodiment will be described.

[0081] As described in FIG. 12, in the information processing system 10 according to the sixth embodiment, a ridge image whose update timing is later than the learning timing will be used for machine learning from the next time onwards. In this way, it is possible to perform appropriate machine learning using a ridge image whose registered zone information has been newly updated. For example, even if a ridge image has already been used for machine learning, if the bright zone information and unknown zone information have been updated after the machine learning, the image will be used for machine learning according to the score. Therefore, the updated bright zone information and unknown zone information can be reflected in the learning.

[0082] Seventh embodiment An information processing system 10 according to the seventh embodiment will be described with reference to Fig. 13 and Fig. 14. The seventh embodiment differs from the first to sixth embodiments in part of its configuration and operation, and other parts may be the same as the first to sixth embodiments. Therefore, hereinafter, parts that differ from the embodiments already described will be described in detail, and other overlapping parts will be omitted as appropriate.

[0083] (Functional configuration) First, the functional configuration of the information processing system 10 according to the seventh embodiment will be described with reference to Fig. 13. Fig. 13 is a block diagram showing the functional configuration of the information processing system according to the seventh embodiment. In Fig. 13, the same elements as those shown in Fig. 2 are denoted by the same reference numerals.

[0084] As shown in Fig. 13, the information processing system 10 according to the seventh embodiment includes a registration information database 110, a zone information extraction unit 120, a score calculation unit 130, and a selection unit 140 as components for realizing the functions of the system. In particular, the score calculation unit 130 according to the seventh embodiment includes an image type determination unit 131 and an algorithm determination unit 132. The score calculation unit 130 according to the seventh embodiment is configured to be able to calculate the first score and the second score using a plurality of algorithms. For example, the score calculation unit 130 is configured to be able to calculate the score using each of the algorithms described in the second to fourth embodiments (i.e., edge count, island count, and binary smooth difference evaluation algorithm).

[0085] The image type determination unit 131 is configured to be capable of determining the type of the ridge line image for which the score is calculated. For example, the image type determination unit 131 may be configured to be capable of determining whether the ridge line image is a fingerprint image or a palm print image. Note that the method of determining the image type is not particularly limited, and existing technology may be appropriately adopted for the determination. The determination result by the image type determination unit 131 is configured to be output to the algorithm determination unit 132.

[0086] The algorithm determination unit 132 is configured to be able to change the algorithm used for score calculation according to the determination result of the image type determination unit 131. That is, the algorithm determination unit 132 is configured to be able to select an algorithm to actually be used for score calculation according to the type of image from among a plurality of algorithms that can be used for score calculation. Alternatively, the algorithm determination unit 132 may be configured to be able to change the weight of the algorithm used for score calculation according to the determination result of the image type determination unit 131. That is, the algorithm determination unit 132 can set the weight of each of the plurality of algorithms used for score calculation according to the type of image, and change the influence of each algorithm on the final score.

[0087] (Example of operation) Next, an operation example of the information processing system 10 according to the seventh embodiment (specifically, an operation example of the algorithm determination unit 132) will be described with reference to Fig. 14. Fig. 14 is a table showing an operation example of the information processing system according to the seventh embodiment.

[0088] 14, the algorithm determination unit 132 may switch the algorithm to be used depending on whether the ridge line image is a fingerprint image or a palm print image. For example, when the ridge line image is a fingerprint image, the algorithm determination unit 132 may determine to calculate the score using at least one of the edge count and the island count. On the other hand, when the ridge line image is a palm print image, the algorithm determination unit may determine to calculate the score using the binary smooth difference evaluation algorithm.

[0089] Here, since the palm print image has a larger image size than the fingerprint image, there are many large wrinkles (palm lines) in the image. In addition, in the area where there are many such wrinkles, the zone information extraction unit 120 tends to set a bright zone, and the worker who performs the correction work tends to set an unknown zone. In this case, when the zone information extraction unit 120 sets a bright zone, the edges decrease, and when the worker sets an unknown zone, the edges increase, so there is a risk that an appropriate score will not be obtained if the edge count and island count are applied. Therefore, it can be said that it is preferable to calculate the score for the palm print image using the binary smooth difference evaluation algorithm. On the other hand, it can be said that it is preferable to calculate the score for the fingerprint image using the edge count and island count, which is the opposite to the palm print image.

[0090] The algorithm determination unit 132 may change the weight set for each algorithm depending on whether the ridge line image is a fingerprint image or a palm print image. For example, when the ridge line image is a fingerprint image, the algorithm determination unit 132 may increase the weight of at least one of the edge count and the island count. Alternatively, when the ridge line image is a fingerprint image, the algorithm determination unit 132 may decrease the weight of the binary smooth difference evaluation algorithm. Alternatively, when the ridge line image is a fingerprint image, the algorithm determination unit 132 may increase the weight of at least one of the edge count and the island count while decreasing the weight of the binary smooth difference evaluation algorithm. In this way, for a fingerprint image, the influence of the edge count and the island count becomes relatively large, while the influence of the binary smooth difference evaluation algorithm becomes relatively small. Therefore, for the reasons already explained, the score can be calculated using a method suitable for a fingerprint image.

[0091] On the other hand, when the ridge line image is a palm print image, the algorithm determination unit 132 may increase the weight of the binary smooth difference evaluation algorithm. Alternatively, when the ridge line image is a palm print image, the algorithm determination unit 132 may decrease the weight of at least one of the edge count and the island count. Alternatively, when the ridge line image is a palm print image, the algorithm determination unit 132 may increase the weight of the binary smooth difference evaluation algorithm while decreasing the weight of at least one of the edge count and the island count. In this way, for palm print images, the influence of the edge count and the island count becomes relatively small, while the influence of the binary smooth difference evaluation algorithm becomes relatively large. Therefore, for the reasons already explained, the score can be calculated using a method suitable for palm print images.

[0092] (Technical effect) Next, technical effects obtained by the information processing system 10 according to the seventh embodiment will be described.

[0093] As described in Fig. 13 and Fig. 14, in the information processing system 10 according to the seventh embodiment, the algorithm used for score calculation or the weight of each algorithm is changed according to the image type. In this way, it is possible to calculate an appropriate score using a method according to the image type. As a result, it is possible to select a ridge image suitable for machine learning.

[0094] 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-mentioned 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. That is, a computer-readable recording medium is also included in the scope of each embodiment. Furthermore, not only the recording medium on which the above-mentioned program is recorded, but also the program itself is included in each embodiment.

[0095] 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. In addition, the scope of each embodiment is not limited to programs recorded on the recording media that execute processes by themselves, but also includes programs that operate on an OS in cooperation with other software and functions of an extension board to execute processes. Furthermore, the program itself may be stored in a server, and part or all of the program may be downloaded from the server to a user terminal.

[0096] <Additional Notes> The above-described embodiment may be further described as follows, but is not limited to the following.

[0097] (Appendix 1) The information processing system described in Appendix 1 is an information processing system comprising: a storage means for storing first region information indicating a bright zone from which ridge feature amounts in a ridge image can be extracted, and second region information indicating an unknown zone which is an area other than the bright zone, in association with each of a plurality of ridge line images; an extraction means for extracting third region information indicating the bright zone and fourth region information indicating the unknown zone from the ridge line image; a calculation means for calculating a first score based on the first region information and the second region information and a second score based on the third region information and the fourth region information; and a selection means for selecting the ridge line image to be used for machine learning by the extraction means based on the first score and the second score.

[0098] (Appendix 2) The information processing system described in Appendix 2 is the information processing system described in Appendix 1, wherein the bright zone and the unknown zone are set for each pixel of the ridge image, and the calculation means calculates the first score and the second score based on the number of pixels in the unknown zone adjacent to a pixel that is the bright zone.

[0099] (Appendix 3) The information processing system described in Appendix 3 is the information processing system described in Appendix 1 or 2, wherein the calculation means calculates the first score and the second score based on the number of unknown zones surrounded by the bright zones.

[0100] (Appendix 4) The information processing system described in Appendix 4 is the information processing system described in any one of Appendixes 1 to 3, wherein the calculation means calculates the first score and the second score based on the number of locations where the bright zone and the unknown zone are inverted when binary smooth processing is performed on the first region information and the second region information, and the third region information and the fourth region information.

[0101] (Appendix 5) The information processing system described in Appendix 5 is the information processing system described in any one of Appendixes 1 to 4, further comprising: an assignment means for assigning version information capable of identifying the ridge line image already used in the machine learning to the extraction means that performed the machine learning; and a first setting means for setting, based on the version information, not to use the ridge line image already used in the machine learning in subsequent machine learning operations.

[0102] (Appendix 6) The information processing system described in Appendix 6 is the information processing system described in any one of Appendixes 1 to 5, further comprising a first acquisition means for acquiring an update timing at which the first region information and the second region information stored in the storage means were updated, a second acquisition means for acquiring a learning timing at which the previous machine learning was performed on the extraction means, and a second setting means for setting the ridge image whose update timing is later than the learning timing to be used for the next or subsequent machine learning.

[0103] (Appendix 7) The information processing system described in Supplementary Note 7 is the information processing system described in any one of Supplementary Notes 1 to 6, wherein the calculation means is capable of calculating the first score and the second score using a plurality of types of algorithms, and selects the algorithm to be used when calculating the first score and the second score, or changes the weight set for each algorithm, depending on whether the ridge image includes a fingerprint or a palm print.

[0104] (Appendix 8) The information processing device described in Appendix 8 is an information processing device that includes a storage means for storing first region information indicating a bright zone from which ridge feature amounts in a ridge image can be extracted, and second region information indicating an unknown zone which is an area other than the bright zone, in association with each of a plurality of ridge images; an extraction means for extracting third region information indicating the bright zone and fourth region information indicating the unknown zone from the ridge image; a calculation means for calculating a first score based on the first region information and the second region information and a second score based on the third region information and the fourth region information; and a selection means for selecting the ridge image to be used for machine learning by the extraction means based on the first score and the second score.

[0105] (Appendix 9) The information processing method described in Appendix 9 is an information processing method executed by at least one computer, which links first region information indicating a bright zone from which ridge features in a ridge image can be extracted, and second region information indicating an unknown zone which is an area other than the bright zone, to each of a plurality of ridge images and stores the information, extracts third region information indicating the bright zone and fourth region information indicating the unknown zone from the ridge image, calculates a first score based on the first region information and the second region information and a second score based on the third region information and the fourth region information, and selects the ridge image to be used for machine learning of an extraction means that extracts the third region information and the fourth region information from the ridge image based on the first score and the second score.

[0106] (Appendix 10) The recording medium described in Appendix 10 is a recording medium having recorded thereon a computer program for executing an information processing method that links first region information indicating bright zones from which ridge features in a ridge image can be extracted and second region information indicating unknown zones, which are areas other than the bright zones, to each of a plurality of ridge images and stores the first region information indicating the bright zones and fourth region information indicating the unknown zones from the ridge images, calculates a first score based on the first region information and the second region information and a second score based on the third region information and the fourth region information, and selects the ridge images to be used for machine learning of an extraction means that extracts the third region information and the fourth region information from the ridge image based on the first score and the second score.

[0107] (Appendix 11) The computer program described in Appendix 11 is a computer program that causes at least one computer to execute an information processing method that links first region information indicating bright zones from which ridge feature amounts in a ridge image can be extracted, and second region information indicating unknown zones that are areas other than the bright zones, to each of a plurality of ridge line images, extracts third region information indicating the bright zones and fourth region information indicating the unknown zones from the ridge line images, calculates a first score based on the first region information and the second region information and a second score based on the third region information and the fourth region information, and selects the ridge line images to be used for machine learning of an extraction means that extracts the third region information and the fourth region information from the ridge line image based on the first score and the second score.

[0108] 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 systems, information processing devices, information processing methods, and recording media that involve such modifications are also included in the technical ideas of this disclosure. [Explanation of symbols]

[0109] 10. Information Processing Systems 11 Processors 14 Storage device 110 Registration Information Database 120 Zone Information Extraction Unit 130 Score Calculation Section 131 Image type determination unit 132 Algorithm Decision Unit 140 Selection Section 150 Version information section 160 First Learning Setting Section 170 Update timing acquisition unit 180 Learning timing acquisition unit 190 Second Learning Setting Section

Claims

1. a storage means for storing first region information indicating bright zones from which ridge feature amounts in a ridge image can be extracted and second region information indicating unknown zones other than the bright zones, in association with each of a plurality of ridge line images; an extraction means for extracting third region information indicating the bright zone and fourth region information indicating the unknown zone from the ridge image; a calculation means for calculating a first score based on the first region information and the second region information, and a second score based on the third region information and the fourth region information; a selection means for selecting an image in which a difference between the first score and the second score is equal to or greater than a predetermined threshold as the ridge image to be used in machine learning of the extraction means; Equipped with The first region information and the second region information include information at least partially modified by a human. Information processing system.

2. the bright zone and the unknown zone are set for each pixel of the ridge image, The calculation means calculates the first score and the second score based on the number of pixels in the unknown zone adjacent to the pixel in the bright zone. The information processing system according to claim 1 .

3. The calculation means calculates the first score and the second score based on the number of the unknown zones surrounded by the bright zones.

3. The information processing system according to claim 1 or 2.

4. the calculation means calculates the first score and the second score based on the number of points where the bright zone and the unknown zone are inverted when a binary smooth process is performed on the first region information and the second region information, and the third region information and the fourth region information. The information processing system according to claim 1 .

5. an assignment means for assigning to the extraction means having performed machine learning, version information capable of identifying the ridge image already used in the machine learning; a first setting means for setting the ridge image already used in machine learning not to be used in subsequent machine learning based on the version information; The information processing system according to claim 1 , further comprising:

6. a first acquisition means for acquiring update timings at which the first region information and the second region information stored in the storage means were updated; A second acquisition means for acquiring a learning timing at which the previous machine learning was performed on the extraction means; a second setting means for setting the ridge image whose update timing is later than the learning timing so as to be used in subsequent machine learning; The information processing system according to claim 1 , further comprising:

7. the calculation means is capable of calculating the first score and the second score using a plurality of types of algorithms, and selects the algorithm used when calculating the first score and the second score, or changes a weight set for each algorithm, depending on whether the ridge line image includes a fingerprint or a palm print. The information processing system according to claim 1 .

8. a storage means for storing first region information indicating bright zones from which ridge feature amounts in a ridge image can be extracted and second region information indicating unknown zones other than the bright zones, in association with each of a plurality of ridge line images; an extraction means for extracting third region information indicating the bright zone and fourth region information indicating the unknown zone from the ridge image; a calculation means for calculating a first score based on the first region information and the second region information, and a second score based on the third region information and the fourth region information; a selection means for selecting an image in which a difference between the first score and the second score is equal to or greater than a predetermined threshold as the ridge image to be used in machine learning of the extraction means; Equipped with The first region information and the second region information include information at least partially modified by a human. Information processing device.

9. 1. An information processing method executed by at least one computer, comprising: A first region information indicating a bright zone from which a feature amount of a ridge in a ridge line image can be extracted and a second region information indicating an unknown zone which is a region other than the bright zone are stored in association with each of the plurality of ridge line images; extracting third region information indicating the bright zone and fourth region information indicating the unknown zone from the ridge image; Calculating a first score based on the first region information and the second region information and a second score based on the third region information and the fourth region information; selecting a ridge image in which a difference between the first score and the second score is equal to or greater than a predetermined threshold as the ridge image to be used in machine learning of an extraction means for extracting the third region information and the fourth region information; The first region information and the second region information include information at least partially modified by a human. Information processing methods.

10. At least one computer A first region information indicating a bright zone from which a feature amount of a ridge in a ridge line image can be extracted and a second region information indicating an unknown zone which is a region other than the bright zone are stored in association with each of the plurality of ridge line images; extracting third region information indicating the bright zone and fourth region information indicating the unknown zone from the ridge image; Calculating a first score based on the first region information and the second region information and a second score based on the third region information and the fourth region information; selecting a ridge image in which a difference between the first score and the second score is equal to or greater than a predetermined threshold as the ridge image to be used in machine learning of an extraction means for extracting the third region information and the fourth region information; The first region information and the second region information include information at least partially modified by a human. A computer program for executing an information processing method.

Images