Fingerprint information processing device, fingerprint information processing method, and recording medium

Abstract

This fingerprint information processing device (1, 2) comprises: an outputting means (11, 211) for using a fingerprint image and a learning model constructed by machine learning that uses training data including a sample image showing a fingerprint so as to output a degree of certainty, which is an indicator indicating the likelihood that the fingerprint shown by the fingerprint image corresponds to at least one among a plurality of pattern types; and a processing means (12, 212) for executing a process based on the degree of certainty.

Description

[Technical Field]

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

[0002] For example, a device has been proposed that generates a ridge direction pattern from a fingerprint image and classifies fingerprints based on the shape of the ridges near the core of the ridge direction pattern and the tendency of the ridge directions (see Patent Document 1). Other prior art documents related to this disclosure include Patent Documents 2 and 3. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 6-139338 [Patent Document 2] Japanese Patent Application Publication No. 9-161054 [Patent Document 3] International Publication No. 2012 / 090287 Summary of the Invention [Problem to be solved by the invention]

[0004] An object of this disclosure is to provide a fingerprint information processing device, a fingerprint information processing method, and a recording medium that aim to improve upon the techniques described in prior art documents. [Means for solving the problem]

[0005] One aspect of the fingerprint information processing device disclosed herein includes an output means for outputting a confidence level, which is an index indicating the likelihood that a fingerprint represented by a fingerprint image corresponds to at least one of a plurality of pattern types, using a fingerprint image and a learning model constructed by machine learning using learning data including sample images representing fingerprints, and a processing means for executing processing based on the confidence level. The output means outputs the degree of certainty using an already registered fingerprint image as the fingerprint image and the learning model, and the processing means estimates the pattern type of the fingerprint indicated by the one fingerprint image based on the degree of certainty as the processing, and if the estimated pattern type differs from the pattern type already associated with the one fingerprint image, performs at least one of notifying and updating the pattern type already associated with the one fingerprint image. .

[0006] One aspect of the fingerprint information processing method of this disclosure is to The computer using a fingerprint image and a learning model constructed by machine learning using learning data including sample images of fingerprints, outputting a certainty factor which is an index indicating the likelihood that the fingerprint shown by the fingerprint image corresponds to at least one of a plurality of pattern types; The computer Execute a process based on the confidence level A fingerprint information processing method, in which the computer outputs the degree of certainty using an already registered fingerprint image as the fingerprint image and the learning model, and the computer, as the processing, estimates the pattern type of the fingerprint indicated by the one fingerprint image based on the degree of certainty, and if the estimated pattern type differs from the pattern type already associated with the one fingerprint image, performs at least one of notifying and updating the pattern type already associated with the one fingerprint image. .

[0007] One aspect of the recording medium of this disclosure is a computer-readable recording medium that uses a fingerprint image and a learning model constructed by machine learning using learning data including sample images of fingerprints, outputs a certainty factor that is an index indicating the likelihood that a fingerprint represented by the fingerprint image corresponds to at least one of a plurality of pattern types, and executes processing based on the certainty factor. A fingerprint information processing method, which uses an already registered fingerprint image as the fingerprint image and the learning model to output the certainty factor, and as the processing, estimates the pattern type of the fingerprint indicated by the one fingerprint image based on the certainty factor, and if the estimated pattern type differs from the pattern type already associated with the one fingerprint image, performs at least one of notifying and updating the pattern type already associated with the one fingerprint image. A computer program for executing the fingerprint information processing method is recorded. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a block diagram illustrating an example of a configuration of an information processing device. [Figure 2] FIG. 10 is a block diagram showing another example of the configuration of the information processing device. [Figure 3] FIG. 10 is a diagram illustrating an example of an output image. [Figure 4] FIG. 10 is a diagram showing another example of an output image. [Figure 5] 10 is a flowchart showing an operation according to the second embodiment. [Figure 6] 10 is a flowchart showing an operation according to the third embodiment. [Figure 7] 10 is a flowchart showing an operation according to the fourth embodiment. [Figure 8] 11 is a flowchart showing an operation according to the fifth embodiment. [Figure 9] 13 is a flowchart showing an operation according to the sixth embodiment. [Figure 10]13 is a flowchart showing the operation according to the seventh embodiment. [Figure 11] 13 is a flowchart showing the operation according to the eighth embodiment. DETAILED DESCRIPTION OF THE INVENTION

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

[0010] First Embodiment A first embodiment of a fingerprint information processing device, a fingerprint information processing method, and a recording medium will be described with reference to Fig. 1. The fingerprint information processing device, the fingerprint information processing method, and a recording medium according to the first embodiment will be described below using an information processing device 1. Fig. 1 is a block diagram showing the configuration of the information processing device 1.

[0011] 1, information processing device 1 includes output unit 11 and processing unit 12. Using a fingerprint image and a learning model constructed by machine learning using learning data including sample images of fingerprints, output unit 11 outputs a certainty factor, which is an index indicating the likelihood that a fingerprint represented by a fingerprint image corresponds to at least one of a plurality of pattern types. Processing unit 12 executes processing based on the certainty factor.

[0012] In the information processing device 1, first, the output unit 11 may output a certainty factor using a fingerprint image and a learning model. Next, the processing unit 12 may execute processing based on the certainty factor. In other words, the information processing device 1 may output a certainty factor using a fingerprint image and a learning model, and execute processing based on the certainty factor. Such an information processing device 1 may be realized, for example, by a computer reading a computer program recorded on a recording medium. In this case, it can be said that the recording medium stores a computer program that causes a computer to output a certainty factor using a fingerprint image and a learning model, and execute processing based on the certainty factor.

[0013] The fingerprint image may include, for example, an image generated by detecting a fingerprint with a sensor, and an image generated by capturing an impression fingerprint or a latent fingerprint with a camera or reading it with a scanner. The sensor for detecting a fingerprint may be, for example, a contact sensor such as an optical type, a capacitance type, or an ultrasonic type, or a non-contact sensor such as an OCT (Optical Coherence Tomography) or a 3D fingerprint scanner. The fingerprint type refers to a grouping of patterns (i.e., fingerprints) formed by the ridges of a fingertip that share a common form based on, for example, the shape or flow direction of the ridges. The fingerprint type may include, for example, an arched pattern, a loop-shaped pattern, a whorl pattern, etc.

[0014] Various existing methods can be applied to the method of constructing a learning model by machine learning using training data including sample images of fingerprints. Therefore, detailed explanation of the method of constructing the learning model will be omitted. The learning model may be constructed by deep learning, which is one type of machine learning. A learning model constructed by deep learning may refer to a mathematical model constructed by machine learning using a multi-layer neural network with multiple intermediate layers (which may also be called hidden layers). The neural network may be, for example, a convolutional neural network. For example, VGG, MobileNet, etc. may be used as a model structure related to a convolutional neural network.

[0015] The certainty is an index that indicates the likelihood that a fingerprint corresponds to at least one of a plurality of pattern types. The more likely that a fingerprint corresponds to one pattern type, the higher the certainty. In other words, the less likely that a fingerprint corresponds to one pattern type, the lower the certainty. Note that the certainty may be expressed numerically, or may be expressed by a grade or rank, such as A, B, .... The certainty may also be referred to as a probability.

[0016] The output unit 11 may use a fingerprint image and a learning model to determine, for example, a certainty factor for one of a plurality of pattern types and output the determined certainty factor. The output unit 11 may use a fingerprint image and a learning model to determine, for example, a plurality of certainty factors corresponding to each of a plurality of pattern types and output the highest certainty factor among the determined certainty factors. The output unit 11 may use a fingerprint image and a learning model to determine, for example, a plurality of certainty factors corresponding to each of a plurality of pattern types and output one or more certainty factors higher than a predetermined value among the determined certainty factors. The output unit 11 may use a fingerprint image and a learning model to determine, for example, a plurality of certainty factors corresponding to each of a plurality of pattern types and output all of the determined certainty factors. The output unit 11 may output the certainty factors to, for example, a display device. In this case, the certainty factors output from the output unit 11 may be displayed on the screen of the display device.

[0017] The processing unit 12 executes processing based on the confidence level output from the output unit 11. "Processing based on the confidence level" may include processing that is directly based on the confidence level and processing that is indirectly based on the confidence level.

[0018] The process directly based on the certainty factor may include, for example, a process of estimating, from a plurality of pattern types, the pattern type to which the fingerprint shown in the fingerprint image corresponds, based on the certainty factor. The process indirectly based on the certainty factor may include, for example, a process of matching the fingerprint shown in the fingerprint image after limiting the objects to be matched based on the pattern type to which the fingerprint shown in the fingerprint image corresponds, estimated based on the certainty factor.

[0019] According to the first embodiment, it is possible to improve the conventional technology.

[0020] Second Embodiment A second embodiment of a fingerprint information processing device, a fingerprint information processing method, and a recording medium will be described with reference to Fig. 2 to Fig. 5. The fingerprint information processing device, the fingerprint information processing method, and a recording medium according to the second embodiment will be described below using an information processing device 2. Fig. 2 is a block diagram showing the configuration of the information processing device 2.

[0021] 2, the information processing device 2 includes a calculation device 21 and a storage device 22. The information processing device 2 may also include a communication device 23, an input device 24, and an output device 25. The information processing device 2 does not necessarily include at least one of the communication device 23, the input device 24, and the output device 25. In the information processing device 2, the calculation device 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.

[0022] The arithmetic device 21 may include, for example, at least one of a central processing unit (CPU), a graphics processing unit (GPU), and a field programmable gate array (FPGA).

[0023] The storage device 22 may include, for example, at least one of a RAM (Random Access Memory), a ROM (Read Only Memory), a hard disk device, a magneto-optical disk device, an SSD (Solid State Drive), and an optical disk array. In other words, the storage device 22 may include a non-transitory recording medium. The storage device 22 is capable of storing desired data. For example, the storage device 22 may temporarily store a computer program executed by the calculation device 21. The storage device 22 may temporarily store data that is temporarily used by the calculation device 21 when the calculation device 21 is executing a computer program.

[0024] The communication device 23 may be capable of communicating with devices external to the information processing device 2 via a communication network (not shown). The communication network may be a wide area network such as the Internet, or a narrow area network such as a LAN (Local Area Network). The communication device 23 may perform wired communication or wireless communication.

[0025] The input device 24 is a device capable of accepting information input to the information processing device 2 from the outside. It may include an operation device (e.g., a keyboard, a mouse, a touch panel, etc.) that can be operated by an operator of the information processing device 2. The input device 24 may include a recording medium reading device that can read information recorded on a recording medium that is detachable from the information processing device 2, such as a USB (Universal Serial Bus) memory. Note that when information is input to the information processing device 2 via the communication device 23 (in other words, when the information processing device 2 obtains information via the communication device 23), the communication device 23 may function as an input device.

[0026] The output device 25 is a device capable of outputting information to the outside of the information processing device 2. The output device 25 may output, as the information, visual information such as characters or images, auditory information such as sound, or tactile information such as vibration. The output device 25 may include, for example, at least one of a display, a speaker, a printer, and a vibration motor. The output device 25 may be capable of outputting information to a recording medium detachable from the information processing device 2, such as a USB memory. Note that when the information processing device 2 outputs information via the communication device 23, the communication device 23 may function as the output device.

[0027] The arithmetic device 21 may have an output unit 211 and a processing unit 212, for example, as logically realized functional blocks or as physically realized processing circuits. At least one of the output unit 211 and the processing unit 212 may be realized in a form in which a logical functional block and a physical processing circuit (i.e., hardware) are mixed. When at least a part of the output unit 211 and the processing unit 212 is a functional block, at least a part of the output unit 211 and the processing unit 212 may be realized by the arithmetic device 21 executing a predetermined computer program.

[0028] The arithmetic device 21 may acquire (in other words, read) the predetermined computer program from, for example, the storage device 22. The arithmetic device 21 may, for example, read the predetermined computer program stored in a computer-readable, non-transitory recording medium using a recording medium reading device (not shown) included in the information processing device 2. The arithmetic device 21 may acquire (in other words, download or read) the predetermined computer program from a device (not shown) external to the information processing device 2 via the communication device 23. Note that the recording medium for recording the predetermined computer program executed by the arithmetic device 21 may be at least one of an optical disk, a magnetic medium, a magneto-optical disk, a semiconductor memory, and any other medium capable of storing a program.

[0029] The output unit 211 has a learning model constructed by machine learning using learning data including sample images of fingerprints. The output unit 211 inputs a fingerprint image to the learning model, and thereby acquires a confidence level from the learning model. The confidence level is an index indicating the likelihood that the fingerprint shown in the fingerprint image corresponds to at least one of a plurality of pattern types. For this reason, the output unit 211 may acquire the confidence level in association with the pattern type.

[0030] The input device 24 may include, for example, a sensor capable of detecting a fingerprint. A fingerprint image may be generated by the sensor detecting the fingerprint. The output unit 211 may acquire the generated fingerprint image. The input device 24 may include, for example, a scanner. A fingerprint image may be generated by the scanner reading an inked fingerprint or a latent fingerprint. The output unit 211 may acquire the generated fingerprint image. The input device 24 may include, for example, an image acquisition device capable of acquiring an image captured by a camera. A fingerprint image may be generated by the camera capturing an inked fingerprint or a latent fingerprint. The output unit 211 may acquire the fingerprint image via the image acquisition device included in the input device 24.

[0031] The output unit 211 transmits (outputs) a signal indicating the degree of certainty to the processing unit 212. In this case, the output unit 211 may transmit, for example, a signal indicating the degree of certainty and a pattern type associated with the degree of certainty to the processing unit 212. The output unit 211 may transmit, for example, a signal indicating the degree of certainty and a pattern type associated with the degree of certainty to, for example, the output device 25. In this case, the output device 25 may display (in other words, output) at least one of text and an image indicating at least one pattern type, and at least one of text and an image indicating the degree of certainty linked to the at least one pattern type. As a result, for example, an image such as that shown in FIG. 3 may be displayed.

[0032] The processing unit 212 executes processing based on the certainty factor. For example, when signals indicating the certainty factor and the pattern type associated with the certainty factor are transmitted from the output unit 211 to the processing unit 212 and the output device 25, respectively, the processing unit 212 may determine the order of the pattern types, for example, based on the certainty factor. Then, the processing unit 212 may transmit a signal indicating the determined order of the pattern types to the output device 25. In this case, the output device 25 may display at least one of text and an image indicating the pattern type and at least one of text and an image indicating the certainty factor associated with the pattern type, according to the determined order of the pattern types. As a result, for example, an image such as that shown in FIG. 4 may be displayed.

[0033] For example, when a signal indicating a certainty level and a pattern type associated with the certainty level is transmitted from the output unit 211 to the processing unit 212, the processing unit 212 may compare the certainty level with a first predetermined value. Here, it is assumed that the certainty level is expressed as a numerical value. When the certainty level is higher than the first predetermined value, the processing unit 212 may associate the pattern type associated with a certainty level higher than the first predetermined value with the fingerprint image. In other words, the processing unit 212 may classify the fingerprint indicated by the fingerprint image into a pattern type associated with a certainty level higher than the first predetermined value. When there is no pattern type associated with a certainty level higher than the first predetermined value, the processing unit 212 may classify the fingerprint indicated by the fingerprint image as an incomplete fingerprint, for example.

[0034] If the multiple certainty levels associated with each of the multiple pattern types are higher than a first predetermined value, the processing unit 212 may associate the multiple pattern types with a fingerprint image. In this case, the processing unit 212 may set the pattern type associated with the highest certainty level as the primary pattern (i.e., the main pattern type). The processing unit 212 may set the pattern types associated with the certainty levels excluding the highest level, among the multiple certainty levels higher than the first predetermined value, as secondary pattern types (i.e., auxiliary pattern types).

[0035] The "first predetermined value" is a value that determines whether a fingerprint image can be associated with a certain pattern type, in other words, whether a fingerprint represented by a fingerprint image can be classified into a certain pattern type. The first predetermined value may be a fixed value set in advance, or a variable value corresponding to some physical quantity or parameter. The first predetermined value may be set as follows. For example, the certainty factor for each pattern type output from the output unit 211 for a certain fingerprint image may be linked to the analysis result of a fingerprint expert analyzing the fingerprint represented by the certain fingerprint image. This process may be performed for multiple fingerprint images. The first predetermined value may be set based on a distribution of certainty factors in which the pattern type associated with the highest certainty factor matches the pattern type represented by the analysis result.

[0036] The processing unit 212 may transmit, for example, a signal indicating a fingerprint image and a pattern type associated with the fingerprint image to a device capable of performing fingerprint matching, different from the information processing device 2, via the communication device 23. For example, if the storage device 22 includes a fingerprint database, the processing unit 212 may perform fingerprint matching using the fingerprint database. Note that various existing aspects can be applied to fingerprint matching. Therefore, a detailed description of fingerprint matching will be omitted, but an overview will be provided below.

[0037] In the fingerprint database, each of the multiple fingerprint images may be associated with a pattern classification. Various existing methods can be used for the association. For example, a method of generating or updating table information indicating the correspondence between fingerprint images and pattern types can be used. For example, a method of adding data indicating the pattern type to the header of image data related to the fingerprint image can be used.

[0038] The processing unit 212 may extract a fingerprint image to be matched with a given fingerprint image from the fingerprint database based on the pattern type associated with the given fingerprint image. As a result, a fingerprint image associated with the same pattern type as the pattern type associated with the given fingerprint image is extracted from the fingerprint database as a target for matching the given fingerprint image. On the other hand, a fingerprint image associated with a pattern type different from the pattern type associated with the given fingerprint image does not have to be extracted from the fingerprint database as a target for matching the given fingerprint image. Note that when a pattern type as a main pattern and a pattern type as a secondary pattern are associated with a given fingerprint image, a fingerprint image associated with the same pattern type as the main pattern and a fingerprint image associated with the same pattern type as the secondary pattern may be extracted from the fingerprint database. The processing unit 212 may match two fingerprints by comparing multiple feature points of a fingerprint indicated by the given fingerprint image with multiple feature points of a fingerprint indicated by a fingerprint image to be matched. The processing unit 212 may determine that the two fingerprints match when some (for example, 12 minutiae) of the multiple minutiae match between the two fingerprints.

[0039] The processing unit 212 may, for example, associate a fingerprint image and a pattern type associated with the fingerprint image with each other and store them in the storage device 22. As a result, for example, a fingerprint database may be constructed or updated. The processing unit 212 may also associate the certainty factor associated with the pattern type associated with the fingerprint image with the fingerprint image and store it in the storage device. The processing unit 212 may, for example, transmit a signal indicating the fingerprint image and the pattern type associated with the fingerprint image to a device that manages the fingerprint database, different from the information processing device 2, via the communication device 23. As a result, the fingerprint database may be updated.

[0040] The operation of information processing device 2 will be further described with reference to the flowchart in Fig. 5. In Fig. 5, output unit 211 of arithmetic device 21 acquires a fingerprint image (step S101). Output unit 211 uses the fingerprint image and a learning model to output a confidence level (step S102). Processing unit 212 of arithmetic device 21 executes processing based on the confidence level (step S103).

[0041] The above-described operations may be realized by the information processing device 2 reading a computer program recorded on a recording medium. In this case, it can be said that the recording medium has recorded thereon a computer program for causing the information processing device 2 to execute the above-described operations. The arithmetic device 21 of the information processing device 2 may correspond to the information processing device 1 according to the first embodiment described above.

[0042] According to the second embodiment, the conventional technology can be improved.

[0043] <Third embodiment> A third embodiment of a fingerprint information processing device, a fingerprint information processing method, and a recording medium will be described with reference to Figs. 2 and 6. The following describes the fingerprint information processing device, the fingerprint information processing method, and a recording medium according to the third embodiment using an information processing device 2. The third embodiment differs from the second embodiment in that the output unit 211 of the arithmetic device 21 has a plurality of learning models. Other aspects of the third embodiment may be the same as those of the second embodiment.

[0044] The output unit 211 may have, for example, a first model and a second model each constructed by machine learning using learning data including sample images showing fingerprints. That is, the output unit 211 may have the first model and the second model as the learning models in the second embodiment described above. Note that the output unit 211 may have three or more learning models.

[0045] Here, the first model and the second model are learning models that have different output tendencies relative to inputs. Such first model and second model may be constructed, for example, by making the number of intermediate layers constituting the neural network different from each other. The first model and the second model may be constructed, for example, by making the number of nodes included in the intermediate layers constituting the neural network different from each other. The first model and the second model may be constructed, for example, by making the model structures related to the neural network different from each other. The first model and the second model may be constructed, for example, by making the training data used for machine learning of the neural network different from each other.

[0046] The output unit 211 inputs one fingerprint image into a first model, thereby obtaining first certainty data indicating the certainty as an output result of the first model. The output unit 211 inputs the one fingerprint image into a second model, thereby obtaining second certainty data indicating the certainty as an output result of the second model. The first certainty data and the second certainty data are data indicating a plurality of certainty levels corresponding to a plurality of pattern types, respectively. In the third embodiment, the certainty levels are represented by numerical values.

[0047] The output unit 211 combines the first certainty factor data and the second certainty factor data. Specifically, the output unit 211 combines, for each pattern type, multiple certainty factors corresponding to the multiple pattern types indicated by the first certainty factor data and the second certainty factor data. In this case, the output unit 211 may combine the certainty factor corresponding to a pattern type indicated by the first certainty factor data with the certainty factor corresponding to the pattern type indicated by the second certainty factor data to obtain a combined value of the certainty factor corresponding to the single pattern type. The "combined certainty factor value" may be, for example, an average value or an added value. Note that, when obtaining the combined certainty factor value, the output tendency of each of the first and second models relative to the input may be used as a weight for the combination. For example, the detection accuracy of right-flow hoofprints of the first model is assumed to be better than the detection accuracy of right-flow hoofprints of the second model, and the detection accuracy of left-flow hoofprints of the second model is assumed to be better than the detection accuracy of left-flow hoofprints of the first model. For example, when determining a composite value of certainty for a right-handed hoofprint, the certainty may be combined by weighting the certainty corresponding to the right-handed hoofprint indicated by the first certainty data greater than the certainty corresponding to the right-handed hoofprint indicated by the second certainty data. Similarly, when determining a composite value of certainty for a left-handed hoofprint, the certainty may be combined by weighting the certainty corresponding to the left-handed hoofprint indicated by the second certainty data greater than the certainty corresponding to the left-handed hoofprint indicated by the first certainty data.

[0048] The first certainty factor data and the second certainty factor data are combined to generate third certainty factor data indicating the certainty factor after combination for each pattern type. The output unit 211 transmits a signal indicating the certainty factor after combination to the processing unit 212 based on the third certainty factor data.

[0049] The operation of the information processing device 2 will be further described with reference to the flowchart of FIG. 6. In FIG. 6, the output unit 211 of the arithmetic device 21 acquires a fingerprint image (step S101). The output unit 211 acquires first certainty factor data by inputting the fingerprint image into a first model (step S201). In parallel with the processing of step S201, the output unit 211 acquires second certainty factor data by inputting the fingerprint image into a second model (step S202). Note that the output unit 211 may execute the processing of step S202 on the condition that the first certainty factor data has been acquired in the processing of step S201. In other words, the output unit 211 may acquire the second certainty factor data after acquiring the first certainty factor data. Alternatively, the output unit 211 may acquire the first certainty factor data after acquiring the second certainty factor data. The output unit 211 combines the first certainty factor data and the second certainty factor data (step S203). The output unit 211 outputs the combined certainty indicated by the third certainty data generated by combining the first certainty data and the second certainty data (step S102). The processing unit 212 of the calculation device 21 executes processing based on the certainty (step S103).

[0050] The above-described operations may be realized by the information processing device 2 reading a computer program recorded on a recording medium. In this case, it can be said that the recording medium records a computer program for causing the information processing device 2 to execute the above-described operations.

[0051] According to the third embodiment, the accuracy of the confidence factor output from the output unit 211 can be improved.

[0052] <Fourth embodiment> A fourth embodiment of a fingerprint information processing device, a fingerprint information processing method, and a recording medium will be described with reference to Figs. 2 and 7. The following describes the fingerprint information processing device, the fingerprint information processing method, and a recording medium according to the fourth embodiment, using an information processing device 2. Here, an example will be given in which the information processing device 2 is applied to a review of an existing fingerprint database. In the fourth embodiment, the processing performed by the processing unit 212 (i.e., processing based on the confidence factor) will be mainly described. Other aspects of the fourth embodiment may be the same as those of the second and third embodiments.

[0053] In fingerprint databases, fingerprints are often classified and registered according to their pattern type. In other words, in fingerprint databases, fingerprint images representing fingerprints are often associated with the pattern type into which the fingerprints are classified. This is done, for example, to perform fingerprint matching efficiently. Specifically, by limiting the search range of the fingerprint database based on the pattern type, it is possible to limit (i.e., reduce) the number of objects to be matched.

[0054] For example, fingerprint databases managed by public institutions may contain fingerprint data collected over several decades. Conventionally, fingerprint pattern types have often been determined rule-based (i.e., according to rules written by humans). Rule-based determination can determine a fingerprint pattern type with relatively high accuracy as long as the rule is met. On the other hand, fingerprint pattern types cannot be identified from perspectives that cannot be written as rules. For this reason, for example, when a fingerprint can be interpreted as multiple pattern types, the fingerprint may be classified as the wrong pattern type. For example, in fingerprint matching, in which the search range of a fingerprint database is limited based on the pattern type, fingerprints classified as the wrong pattern type will be omitted from the matching subjects.

[0055] If a learning model constructed by deep learning is used as the learning model in the second and third embodiments described above, it is expected that it will be possible to identify fingerprint pattern types that take into account aspects that cannot be described as rules, for example. Therefore, an existing fingerprint database may be reconsidered using the method described below.

[0056] The information processing device 2 may perform the following operations, for example, to support the work of reviewing the fingerprint database. The output unit 211 of the calculation device 21 acquires a fingerprint image registered in the fingerprint database. The output unit 211 acquires a certainty factor for the fingerprint image by inputting the fingerprint image into a learning model constructed by deep learning. In this case, the output unit 211 may acquire multiple certainty factors for the fingerprint image, each corresponding to a multiple pattern type. The output unit 211 transmits a signal indicating the certainty factor for the fingerprint image to the processing unit 212 of the calculation device 21.

[0057] The processing unit 212 compares the certainty factor associated with one fingerprint image with a first predetermined value (see the second embodiment). The processing unit 212 estimates the fingerprint pattern type of the fingerprint indicated by one fingerprint image based on the comparison result between each of the plurality of certainty factors corresponding to each of the plurality of pattern types and the first predetermined value.

[0058] For one fingerprint image, if the multiple certainty factors corresponding to the multiple pattern types include a certainty factor higher than a first predetermined value, the processing unit 212 estimates that the pattern type of the fingerprint represented by the one fingerprint image is a pattern type corresponding to a certainty factor higher than the first predetermined value. In this case, the processing unit 212 associates the one fingerprint image with the pattern type corresponding to a certainty factor higher than the first predetermined value. If the multiple certainty factors associated with the multiple pattern types are higher than the first predetermined value, the processing unit 212 may associate the one fingerprint image with the multiple pattern types.

[0059] If the multiple certainty factors respectively corresponding to the multiple pattern types do not include a certainty factor higher than the first predetermined value, the processing unit 212 may estimate that the pattern type of the fingerprint represented by one fingerprint image is an incomplete pattern. In this case, the processing unit 212 may associate one fingerprint image with the incomplete pattern type.

[0060] The processing unit 212 determines whether the pattern type associated with a fingerprint image in the fingerprint database is the same as the pattern type associated with the fingerprint image based on the certainty factor. If the pattern type associated with a fingerprint image in the fingerprint database is different from the pattern type associated with the fingerprint image based on the certainty factor, the processing unit 212 issues a notification to prompt the user to reconsider the pattern type.

[0061] As a notification, the processing unit 212 may send an email to, for example, the administrator of the fingerprint database, urging them to review the pattern type. As a notification, the processing unit 212 may display a fingerprint image in which the pattern type associated with the fingerprint image in the fingerprint database is different from the pattern type associated with the fingerprint image based on the confidence level. Note that the notification method is not limited to these, and various existing methods can be applied.

[0062] Furthermore, if the pattern type linked to a fingerprint image in the fingerprint database differs from the pattern type associated with the fingerprint image based on the certainty, processing unit 212 may issue a notification to encourage the user to reconsider the pattern type if the certainty corresponding to the pattern type associated with the fingerprint image based on the certainty is higher than a second predetermined value.

[0063] The "second predetermined value" is a value that determines whether or not to notify that the pattern types are different. The second predetermined value may be a fixed value set in advance, or may be a variable value depending on some physical quantity or parameter. The second predetermined value may be set as follows. For example, when the pattern type associated with a fingerprint image in the fingerprint database differs from the pattern type associated with the fingerprint image based on the certainty factor, a relationship between the certainty factor and a fingerprint in which the fingerprint expert has corrected the pattern type may be found. The second predetermined value may be set based on the found relationship.

[0064] The operation of information processing device 2 will be further described with reference to the flowchart in Fig. 7. In Fig. 7, output unit 211 of arithmetic device 21 acquires one fingerprint image from the fingerprint database (step S101). Output unit 211 acquires a certainty factor for one fingerprint image by inputting the one fingerprint image to a learning model constructed by deep learning. Output unit 211 outputs the certainty factor for one fingerprint image (step S102).

[0065] The processing unit 212 of the computing device 21 compares each of the multiple confidence levels corresponding to each of the multiple pattern types with a first predetermined value based on the confidence level for one fingerprint image. The processing unit 212 estimates the pattern type of the fingerprint indicated by one fingerprint image based on the comparison result between each of the multiple confidence levels corresponding to each of the multiple pattern types and the first predetermined value (step S301).

[0066] In the processing of step S301, if the multiple certainty factors corresponding to the multiple pattern types for a single fingerprint image include a certainty factor higher than the first predetermined value, the processing unit 212 infers that the pattern type of the fingerprint represented by the single fingerprint image is a pattern type corresponding to a certainty factor higher than the first predetermined value. In this case, the processing unit 212 associates the single fingerprint image with the pattern type corresponding to a certainty factor higher than the first predetermined value. If the multiple certainty factors associated with each of the multiple pattern types are higher than the first predetermined value, the processing unit 212 may associate the single fingerprint image with the multiple pattern types. If the multiple certainty factors corresponding to the multiple pattern types do not include a certainty factor higher than the first predetermined value, the processing unit 212 may infer that the pattern type of the fingerprint represented by the single fingerprint image is an incomplete pattern. In this case, the processing unit 212 may associate the single fingerprint image with the incomplete pattern type.

[0067] Processing unit 212 determines whether the pattern type associated with one fingerprint image in the fingerprint database is different from the pattern type associated with one fingerprint image based on the certainty factor (i.e., the pattern type associated with one fingerprint image in the processing of step S301) (step S302). If it is determined in the processing of step S302 that the pattern type associated with one fingerprint image in the fingerprint database is the same as the pattern type associated with one fingerprint image based on the certainty factor (step S302: No), the operation shown in FIG. 7 is terminated.

[0068] In the processing of step S302, if it is determined that the pattern type linked to a fingerprint image in the fingerprint database is different from the pattern type associated with the fingerprint image based on the confidence level (step S302: Yes), processing unit 212 issues a notification to prompt the user to review the pattern type (step S303).

[0069] In the process of step S302, if it is determined that the pattern type associated with a fingerprint image in the fingerprint database is different from the pattern type associated with the fingerprint image based on the certainty factor (step S302: Yes), the processing unit 212 may determine whether the certainty factor corresponding to the pattern type associated with the fingerprint image based on the certainty factor is higher than a second predetermined value. If it is determined that the certainty factor is higher than the second predetermined value, the processing unit 212 may issue a notification to prompt the user to reconsider the pattern type. On the other hand, if it is determined that the certainty factor is lower than the second predetermined value, the processing unit 212 may not issue a notification to prompt the user to reconsider the pattern type. If the certainty factor and the second predetermined value are equal, the two may be treated as being included in either one.

[0070] The above-described operations may be realized by the information processing device 2 reading a computer program recorded on a recording medium. In this case, it can be said that the recording medium records a computer program for causing the information processing device 2 to execute the above-described operations.

[0071] According to the fourth embodiment, it is possible to detect fingerprints that may be classified into the wrong pattern type from among a plurality of fingerprints registered in the fingerprint database.

[0072] (First Modification) Instead of issuing a notification to prompt the user to review the pattern type, the processing unit 212 may, for example, replace the pattern type associated with a fingerprint image in the fingerprint database with the pattern type associated with the fingerprint image based on the certainty factor. That is, if it is determined in the processing of step S302 above that the pattern type associated with a fingerprint image in the fingerprint database is different from the pattern type associated with the fingerprint image based on the certainty factor (step S302: Yes), the processing unit 212 may replace the pattern type associated with the fingerprint image in the fingerprint database with the pattern type associated with the fingerprint image based on the certainty factor. In this case, the processing unit 212 may issue a notification that the pattern type has been replaced. Note that replacing the pattern type associated with a fingerprint image in the fingerprint database may be considered equivalent to updating the pattern type associated with the fingerprint image in the fingerprint database.

[0073] (Second Modification) Alternatively, instead of issuing a notification to prompt the user to review the pattern type, processing unit 212 may, for example, register the pattern type associated with a fingerprint image based on the certainty factor in the fingerprint database as a secondary pattern type associated with the fingerprint image. That is, if it is determined in the processing of step S302 above that the pattern type associated with the fingerprint image in the fingerprint database is different from the pattern type associated with the fingerprint image based on the certainty factor (step S302: Yes), processing unit 212 may associate the pattern type associated with the fingerprint image based on the certainty factor with the fingerprint image as a secondary pattern type associated with the fingerprint image. In this case, processing unit 212 may issue a notification that the secondary pattern type has been registered. Registering a secondary pattern type associated with a fingerprint image in the fingerprint database may be considered equivalent to updating the pattern type associated with the fingerprint image in the fingerprint database.

[0074] Fifth Embodiment A fifth embodiment of a fingerprint information processing device, a fingerprint information processing method, and a recording medium will be described with reference to Figs. 2 and 8. Below, the fingerprint information processing device, the fingerprint information processing method, and a recording medium according to the fifth embodiment will be described using an information processing device 2. Here, an example will be given in which the information processing device 2 is applied to a fingerprint registration operation. In the fifth embodiment, the processing executed by the processing unit 212 (i.e., processing based on the confidence factor) will be mainly described. Other aspects of the fifth embodiment may be the same as those of the second to fourth embodiments.

[0075] Fingerprint classification is often performed by someone with specialized knowledge, such as a fingerprint expert. For this reason, an organization that does not have someone with specialized knowledge often requests another organization that has someone with specialized knowledge to classify the fingerprints indicated by newly collected fingerprint images. In this case, the first organization may not be able to register the newly collected fingerprint images in its fingerprint database until the other organization has completed the fingerprint classification work. Therefore, the first organization may classify fingerprints using the method described below.

[0076] The information processing device 2 may perform the following operations to support, for example, the fingerprint registration work: Here, it is assumed that the information processing device 2 is installed in the above-mentioned one organization.

[0077] The output unit 211 of the arithmetic device 21 acquires one fingerprint image as a newly collected fingerprint image. The output unit 211 acquires a certainty factor for the one fingerprint image by inputting the one fingerprint image to a learning model. In this case, the output unit 211 may acquire multiple certainty factors for the one fingerprint image, each corresponding to a multiple pattern type. The output unit 211 transmits a signal indicating the certainty factor for the one fingerprint image to the processing unit 212 of the arithmetic device 21.

[0078] The processing unit 212 compares the certainty factor associated with one fingerprint image with a first predetermined value (see the second embodiment). The processing unit 212 estimates the fingerprint pattern type of the fingerprint indicated by one fingerprint image based on the comparison result between each of the plurality of certainty factors corresponding to each of the plurality of pattern types and the first predetermined value.

[0079] For one fingerprint image, if the multiple certainty factors corresponding to the multiple pattern types include a certainty factor higher than a first predetermined value, the processing unit 212 estimates that the pattern type of the fingerprint represented by the one fingerprint image is a pattern type corresponding to a certainty factor higher than the first predetermined value. In this case, the processing unit 212 associates the one fingerprint image with the pattern type corresponding to a certainty factor higher than the first predetermined value. If the multiple certainty factors associated with the multiple pattern types are higher than the first predetermined value, the processing unit 212 may associate the one fingerprint image with the multiple pattern types.

[0080] If the multiple certainty factors respectively corresponding to the multiple pattern types do not include a certainty factor higher than the first predetermined value, the processing unit 212 may estimate that the pattern type of the fingerprint represented by one fingerprint image is an incomplete pattern. In this case, the processing unit 212 may associate one fingerprint image with the incomplete pattern type.

[0081] The processing unit 212 may transmit a signal indicating the type of pattern associated with one fingerprint image to the output device 25. In other words, the processing unit 212 may transmit a signal indicating the estimated type of pattern to the output device 25. As a result, at least one of a character and an image indicating the type of pattern associated with one fingerprint image may be displayed.

[0082] The operation of information processing device 2 will be further described with reference to the flowchart of Fig. 8. In Fig. 8, output unit 211 of arithmetic device 21 acquires one fingerprint image as a newly collected fingerprint image (step S101). Output unit 211 inputs the one fingerprint image to a learning model to acquire a confidence factor for the one fingerprint image. Output unit 211 outputs the confidence factor for the one fingerprint image (step S102).

[0083] The processing unit 212 of the arithmetic unit 21 compares each of the plurality of certainty factors corresponding to each of the plurality of pattern types with a first predetermined value based on the certainty factor associated with one fingerprint image (step S401). Based on the comparison result, the processing unit 212 determines whether the plurality of certainty factors corresponding to each of the plurality of pattern types includes a certainty factor higher than the first predetermined value (step S402).

[0084] If it is determined in the processing of step S402 that a certainty level higher than the first predetermined value is included (step S402: Yes), the processing unit 212 estimates that the fingerprint pattern type indicated by the one fingerprint image is a pattern type corresponding to a certainty level higher than the first predetermined value (step S403). In this case, the processing unit 212 associates the one fingerprint image with the pattern type corresponding to a certainty level higher than the first predetermined value. If the multiple certainty levels associated with the multiple pattern types are higher than the first predetermined value, the processing unit 212 may associate the one fingerprint image with the multiple pattern types.

[0085] In the process of step S402, if it is determined that the certainty factor higher than the first predetermined value is not included (step S402: No), the processing unit 212 may estimate that the fingerprint pattern type indicated by the one fingerprint image is an incomplete fingerprint (step S404). In this case, the processing unit 212 may associate the one fingerprint image with the incomplete fingerprint pattern type.

[0086] The above-described operations may be realized by the information processing device 2 reading a computer program recorded on a recording medium. In this case, it can be said that the recording medium records a computer program for causing the information processing device 2 to execute the above-described operations.

[0087] According to the fifth embodiment, the one organization can relatively quickly register a fingerprint by, for example, referring to the pattern type associated with a fingerprint image by the information processing device 2, without requesting fingerprint classification from another organization. Since the fingerprint registration can be performed relatively quickly, for example, a newly registered fingerprint can be compared with a previously registered fingerprint relatively quickly. For example, if a previously registered fingerprint is linked to various pieces of information about the individual corresponding to that fingerprint, and a previously registered fingerprint that matches the newly registered fingerprint is found during fingerprint comparison, various pieces of information about the individual corresponding to the newly registered fingerprint can be obtained relatively quickly.

[0088] (Variation) After step S403 or S404, the processing unit 212 may, for example, associate one fingerprint image with the pattern type associated with that fingerprint image and register them in the fingerprint database.

[0089] Sixth Embodiment A sixth embodiment of a fingerprint information processing device, a fingerprint information processing method, and a recording medium will be described with reference to Figs. 2 and 9. The following describes the fingerprint information processing device, the fingerprint information processing method, and a recording medium according to the sixth embodiment, using an information processing device 2. Here, an example will be given in which the information processing device 2 is applied to a fingerprint registration operation. In the sixth embodiment, the processing executed by the processing unit 212 (i.e., processing based on the confidence factor) will be mainly described. Other aspects of the sixth embodiment may be the same as those of the second to fifth embodiments.

[0090] In the case of a latent fingerprint, for example, the ridges may be unclear, only part of the fingerprint may remain, or noise may be superimposed on the fingerprint. In order to properly perform fingerprint matching for a latent fingerprint, the matching range may be limited based on a central axis indicating the center position of the fingerprint. The central axis may be set not only for latent fingerprints, but also for all fingerprints. The central axis may be set, for example, when a newly acquired fingerprint is registered.

[0091] The "central axis" is an axis that passes through the center position of a fingerprint (which may also be called the center point) and extends in a specific direction. This specific direction (i.e., the direction in which the central axis extends) is toward the fingertip in the case of an arch-shaped fingerprint, and is the direction of the central hoof line in the case of fingerprint types other than an arch-shaped fingerprint. The "core hoof line" refers to the innermost horseshoe-shaped ridge of a fingerprint. The center position of a fingerprint may be a position corresponding to the hoof tip of the horseshoe represented by the core hoof line. The "direction of the core hoof line" refers to the front-to-back direction of the horseshoe represented by the core hoof line. The direction of the core hoof line often differs depending on the type of fingerprint. Therefore, the direction in which the central axis extends often differs depending on the type of fingerprint.

[0092] The information processing device 2 may perform the following operations to assist, for example, the fingerprint registration process.

[0093] The output unit 211 of the arithmetic device 21 acquires one fingerprint image as a newly collected fingerprint image. The output unit 211 acquires a certainty factor for the one fingerprint image by inputting the one fingerprint image to a learning model. In this case, the output unit 211 may acquire multiple certainty factors for the one fingerprint image, each corresponding to a multiple pattern type. The output unit 211 transmits a signal indicating the certainty factor for the one fingerprint image to the processing unit 212 of the arithmetic device 21.

[0094] The processing unit 212 compares the certainty factor associated with one fingerprint image with a first predetermined value (see the second embodiment). The processing unit 212 estimates the fingerprint pattern type of the fingerprint indicated by one fingerprint image based on the comparison result between each of the plurality of certainty factors corresponding to each of the plurality of pattern types and the first predetermined value.

[0095] For one fingerprint image, if the multiple certainty factors corresponding to the multiple pattern types include a certainty factor higher than a first predetermined value, the processing unit 212 estimates that the pattern type of the fingerprint represented by the one fingerprint image is a pattern type corresponding to a certainty factor higher than the first predetermined value. In this case, the processing unit 212 associates the one fingerprint image with the pattern type corresponding to a certainty factor higher than the first predetermined value. If the multiple certainty factors associated with the multiple pattern types are higher than the first predetermined value, the processing unit 212 may associate the one fingerprint image with the multiple pattern types.

[0096] If the multiple certainty factors respectively corresponding to the multiple pattern types do not include a certainty factor higher than the first predetermined value, the processing unit 212 may estimate that the pattern type of the fingerprint represented by one fingerprint image is an incomplete pattern. In this case, the processing unit 212 may associate one fingerprint image with the incomplete pattern type.

[0097] The processing unit 212 sets a central axis based on the pattern type associated with one fingerprint image and the fingerprint image itself. If multiple pattern types are associated with one fingerprint image, the processing unit 212 may set multiple central axes corresponding to the multiple pattern types, respectively. In other words, the processing unit 212 may set one central axis for each pattern type associated with one fingerprint image. Note that if one fingerprint image is associated with an incomplete fingerprint, the processing unit 212 does not need to set a central axis.

[0098] If a fingerprint image is associated with an arch-shaped pattern, the processing unit 212 may set a central axis extending in the direction of the fingertip. If a fingerprint image is associated with a pattern type other than an arch-shaped pattern, the processing unit 212 may set a central axis extending in the direction of the central hoof line. Note that various existing methods can be applied to the method of identifying the fingertip direction or the central hoof line direction from the fingerprint represented by a fingerprint image. Therefore, detailed explanations thereof will be omitted.

[0099] The processing unit 212 may transmit a signal indicating the pattern type associated with one fingerprint image and the central axis corresponding to the pattern type to the output device 25. As a result, at least one of a character and an image indicating the pattern type associated with one fingerprint image and the central axis corresponding to the pattern type may be displayed.

[0100] The operation of information processing device 2 will be further described with reference to the flowchart of Fig. 9. In Fig. 9, output unit 211 of arithmetic device 21 acquires one fingerprint image as a newly collected fingerprint image (step S101). Output unit 211 inputs the one fingerprint image to a learning model to acquire a confidence factor for the one fingerprint image. Output unit 211 outputs the confidence factor for the one fingerprint image (step S102).

[0101] The processing unit 212 of the computing device 21 compares each of the plurality of certainty factors corresponding to each of the plurality of pattern types with a first predetermined value based on the certainty factor associated with one fingerprint image. The processing unit 212 estimates the pattern type of the fingerprint indicated by one fingerprint image based on the comparison result between each of the plurality of certainty factors corresponding to each of the plurality of pattern types and the first predetermined value (step S501).

[0102] In the processing of step S501, if the multiple certainty factors corresponding to the multiple pattern types for a single fingerprint image include a certainty factor higher than the first predetermined value, the processing unit 212 infers that the pattern type of the fingerprint represented by the single fingerprint image is a pattern type corresponding to a certainty factor higher than the first predetermined value. In this case, the processing unit 212 associates the single fingerprint image with the pattern type corresponding to a certainty factor higher than the first predetermined value. If the multiple certainty factors associated with each of the multiple pattern types are higher than the first predetermined value, the processing unit 212 may associate the single fingerprint image with the multiple pattern types. If the multiple certainty factors corresponding to the multiple pattern types do not include a certainty factor higher than the first predetermined value, the processing unit 212 may infer that the pattern type of the fingerprint represented by the single fingerprint image is an incomplete pattern. In this case, the processing unit 212 may associate the single fingerprint image with the incomplete pattern type.

[0103] Next, the processing unit 212 sets a central axis based on the pattern type associated with one fingerprint image and the one fingerprint image (step S502). If multiple pattern types are associated with one fingerprint image, the processing unit 212 may set multiple central axes corresponding to the multiple pattern types, respectively, in the processing of step S502.

[0104] The above-described operations may be realized by the information processing device 2 reading a computer program recorded on a recording medium. In this case, it can be said that the recording medium records a computer program for causing the information processing device 2 to execute the above-described operations.

[0105] In the information processing device 2, a central axis is set for each pattern type associated with one fingerprint image. A person registering a fingerprint can register a central axis for each pattern type for one fingerprint image by referring to the central axis set in the information processing device 2. If a fingerprint represented by one fingerprint image can be interpreted as multiple pattern types, multiple central axes may be registered for one fingerprint image. According to the sixth embodiment, for example, it is possible to support fingerprint registration work. For example, if a fingerprint represented by one fingerprint image can be interpreted as multiple pattern types, registering multiple central axes for one fingerprint image can reduce the occurrence of matching errors in fingerprint matching using one fingerprint image.

[0106] (Variation) Instead of or in addition to outputting a signal indicating the pattern type associated with a fingerprint image and the central axis corresponding to the pattern type, processing unit 212 may register the fingerprint image, the pattern type associated with the fingerprint image, and the central axis corresponding to the pattern type. In this case, processing unit 212 may perform fingerprint matching for the fingerprint image based on the registered central axis. If multiple central axes are registered for a fingerprint image, processing unit 212 may perform fingerprint matching for the fingerprint image based on each of the multiple central axes.

[0107] Seventh Embodiment A seventh embodiment of a fingerprint information processing device, a fingerprint information processing method, and a recording medium will be described with reference to Figs. 2 and 10. The following describes the fingerprint information processing device, the fingerprint information processing method, and a recording medium according to the seventh embodiment, using an information processing device 2. Here, an example will be given in which the information processing device 2 is applied to fingerprint registration and editing work. In the seventh embodiment, the processing executed by the processing unit 212 (i.e., processing based on the confidence factor) will be mainly described. Other aspects of the seventh embodiment may be the same as those of the second to sixth embodiments.

[0108] For example, in a fingerprint database managed by a public institution, fingerprint data may be registered using the following procedure: A person with specialized knowledge, such as a fingerprint expert, determines the type of fingerprint pattern represented by a fingerprint image. The fingerprint image and the determined type of pattern are then registered as fingerprint data related to the fingerprint image.

[0109] The fingerprint database allows editing of registered fingerprints. Therefore, when a new fingerprint image is registered, only that fingerprint image may be registered in the fingerprint database first. After that, when the fingerprint pattern type indicated by the fingerprint image is determined, the fingerprint data related to the fingerprint image may be edited to add (register) the determined pattern type.

[0110] The information processing device 2 may perform the following operations to support at least one of the fingerprint registration and editing operations, for example. Here, it is assumed that a fingerprint database is created in the storage device 22 of the information processing device 2.

[0111] The output unit 211 of the arithmetic device 21 acquires one fingerprint image as a newly collected fingerprint image. The output unit 211 acquires a certainty factor for the one fingerprint image by inputting the one fingerprint image to a learning model. In this case, the output unit 211 may acquire multiple certainty factors for the one fingerprint image, each corresponding to a multiple pattern type. The output unit 211 transmits a signal indicating the certainty factor for the one fingerprint image to the processing unit 212 of the arithmetic device 21.

[0112] The processing unit 212 compares the certainty factor associated with one fingerprint image with a first predetermined value (see the second embodiment). The processing unit 212 estimates the fingerprint pattern type of the fingerprint indicated by one fingerprint image based on the comparison result between each of the plurality of certainty factors corresponding to each of the plurality of pattern types and the first predetermined value.

[0113] For one fingerprint image, if the multiple certainty factors corresponding to the multiple pattern types include a certainty factor higher than a first predetermined value, the processing unit 212 estimates that the pattern type of the fingerprint represented by the one fingerprint image is a pattern type corresponding to a certainty factor higher than the first predetermined value. In this case, the processing unit 212 associates the one fingerprint image with the pattern type corresponding to a certainty factor higher than the first predetermined value. If the multiple certainty factors associated with the multiple pattern types are higher than the first predetermined value, the processing unit 212 may associate the one fingerprint image with the multiple pattern types.

[0114] If the multiple certainty factors respectively corresponding to the multiple pattern types do not include a certainty factor higher than the first predetermined value, the processing unit 212 may estimate that the pattern type of the fingerprint represented by one fingerprint image is an incomplete pattern. In this case, the processing unit 212 may associate one fingerprint image with the incomplete pattern type.

[0115] For example, when a pattern type associated with a fingerprint image is registered or edited via the input device 24 (in other words, when a user of the information processing device 2 registers or edits a pattern type associated with a fingerprint image), the processing unit 212 determines whether the registered or edited pattern type is the same as the pattern type that the processing unit 212 has associated with the fingerprint image. If the registered or edited pattern type is different from the pattern type that the processing unit 212 has associated with the fingerprint image, the processing unit 212 issues a warning, for example, to prompt the user to reconfirm the pattern type. Note that when the input device 24 receives, for example, information indicating the registration or editing of a pattern type (for example, information indicating that a button indicating "register" or "update" has been pressed), the processing unit 212 may determine that the pattern type has been registered or edited.

[0116] If the registered or added pattern type differs from the pattern type that the processing unit 212 has associated with one fingerprint image, the processing unit 212 may determine whether the certainty factor corresponding to the pattern type that the processing unit 212 has associated with one fingerprint image is higher than a second predetermined value (see the fourth embodiment). If the certainty factor is higher than the second predetermined value, the processing unit 212 may issue a warning to, for example, urge the user to reconfirm the pattern type. On the other hand, if the certainty factor is lower than the second predetermined value, the processing unit 212 may not issue a warning. If the certainty factor is equal to the second predetermined value, the case may be treated as including either case.

[0117] The operation of information processing device 2 will be further described with reference to the flowchart in Fig. 10. In Fig. 10, output unit 211 of arithmetic device 21 acquires one fingerprint image (step S101). Output unit 211 inputs the one fingerprint image to a learning model, thereby acquiring a confidence factor for the one fingerprint image. Output unit 211 outputs the confidence factor for the one fingerprint image (step S102).

[0118] The processing unit 212 of the computing device 21 compares each of the multiple confidence levels corresponding to each of the multiple pattern types with a first predetermined value based on the confidence level for one fingerprint image. The processing unit 212 estimates the pattern type of the fingerprint indicated by one fingerprint image based on the comparison result between each of the multiple confidence levels corresponding to each of the multiple pattern types and the first predetermined value (step S601).

[0119] In the processing of step S601, if the multiple certainty factors corresponding to the multiple pattern types for a single fingerprint image include a certainty factor higher than the first predetermined value, the processing unit 212 infers that the pattern type of the fingerprint represented by the single fingerprint image is a pattern type corresponding to a certainty factor higher than the first predetermined value. In this case, the processing unit 212 associates the single fingerprint image with the pattern type corresponding to a certainty factor higher than the first predetermined value. If the multiple certainty factors associated with each of the multiple pattern types are higher than the first predetermined value, the processing unit 212 may associate the single fingerprint image with the multiple pattern types. If the multiple certainty factors corresponding to the multiple pattern types do not include a certainty factor higher than the first predetermined value, the processing unit 212 may infer that the pattern type of the fingerprint represented by the single fingerprint image is an incomplete pattern. In this case, the processing unit 212 may associate the single fingerprint image with the incomplete pattern type.

[0120] The processing unit 212 determines whether the pattern type associated with one fingerprint image has been registered or edited (step S602). If it is determined in the process of step S602 that the pattern type has not been registered or edited (step S602: No), the processing unit 212 performs the process of step S602 again. In other words, the processing unit 212 may be in a standby state until the pattern type is registered or edited.

[0121] If it is determined in the process of step S602 that the pattern type has been registered or edited (step S602: Yes), processing unit 212 determines whether the registered or edited pattern type is the same as the pattern type that processing unit 212 has associated with one fingerprint image (step S603).If it is determined in the process of step S603 that the registered or edited pattern type is the same as the pattern type that processing unit 212 has associated with one fingerprint image (step S603: Yes), the operation shown in FIG. 10 ends.

[0122] In the processing of step S603, if it is determined that the registered or edited pattern type is not the same as the pattern type that the processing unit 212 has associated with a fingerprint image (step S603: No), the processing unit 212 issues a warning, for example, urging the user to reconfirm the pattern type (step S604).

[0123] In the process of step S604, the processing unit 212 may determine whether the certainty factor corresponding to the pattern type that the processing unit 212 has associated with one fingerprint image is higher than a second predetermined value. If the certainty factor is higher than the second predetermined value, the processing unit 212 may issue a warning to, for example, prompt the user to reconfirm the pattern type. On the other hand, if the certainty factor is lower than the second predetermined value, the processing unit 212 may not issue a warning.

[0124] The above-described operations may be realized by the information processing device 2 reading a computer program recorded on a recording medium. In this case, it can be said that the recording medium records a computer program for causing the information processing device 2 to execute the above-described operations.

[0125] According to the seventh embodiment, for example, a warning is issued to prompt the user to reconfirm the pattern type, so that it is possible to prevent mistakes in registering the pattern type when registering or editing fingerprint data.

[0126] Eighth Embodiment An eighth embodiment of a fingerprint information processing device, a fingerprint information processing method, and a recording medium will be described with reference to Figs. 2 and 11. Below, the fingerprint information processing device, the fingerprint information processing method, and a recording medium according to the eighth embodiment will be described using an information processing device 2. Here, an example will be given in which the information processing device 2 is applied to fingerprint registration and editing work. In the eighth embodiment, the processing executed by the processing unit 212 (i.e., processing based on the confidence factor) will be mainly described. Other aspects of the eighth embodiment may be the same as those of the second to seventh embodiments.

[0127] For example, in a fingerprint database managed by a public institution, fingerprint data may be registered using the following procedure: A person with specialized knowledge, such as a fingerprint expert, determines the type of fingerprint pattern shown in a fingerprint image. A person different from the person who determined the type of pattern determines the central axis of the fingerprint shown in the fingerprint image. The fingerprint image, the determined type of pattern, and the determined central axis are registered as fingerprint data related to the fingerprint image.

[0128] The fingerprint database allows editing of registered fingerprints. Therefore, when a fingerprint image is newly registered, only the fingerprint image may be registered in the fingerprint database first. After that, when the type of fingerprint pattern represented by the fingerprint image is determined, the determined type of pattern may be added (registered) by editing the fingerprint data for the fingerprint image. Similarly, when the central axis of the fingerprint represented by the fingerprint image is determined, the determined central axis may be added (registered) by editing the fingerprint data for the fingerprint image.

[0129] As explained in the sixth embodiment, the direction in which the central axis extends often differs depending on the pattern type. If a fingerprint represented by a single fingerprint image can be interpreted as multiple pattern types, multiple central axes corresponding to the multiple pattern types may be registered for the single fingerprint image. As mentioned above, the person who determines the pattern type may be different from the person who determines the central axis. For example, a single pattern type may be registered with a central axis that does not correspond to the single pattern type. In this case, there is a possibility that fingerprint matching will not be performed properly for the single fingerprint image because the central axis associated with the single pattern type is incorrect.

[0130] For example, if two central axes are registered for one fingerprint image, when matching the fingerprint image with a matching target limited based on the pattern type associated with the fingerprint image, it is possible to perform both fingerprint matching within a matching range limited by one of the two central axes and fingerprint matching within a matching range limited by the other of the two central axes, without taking into account the correspondence between the pattern type and the central axes. This configuration allows fingerprint matching to be performed appropriately for one fingerprint image. However, this increases the processing load associated with fingerprint matching, for example.

[0131] The information processing device 2 may perform the following operations to support at least one of the fingerprint registration and editing operations, for example. Here, it is assumed that a fingerprint database is created in the storage device 22 of the information processing device 2.

[0132] The output unit 211 of the arithmetic device 21 acquires one fingerprint image. The output unit 211 acquires a certainty factor for one fingerprint image by inputting the one fingerprint image to a learning model. In this case, the output unit 211 may acquire multiple certainty factors for one fingerprint image, each corresponding to a multiple pattern type. The output unit 211 transmits a signal indicating the certainty factor for one fingerprint image to the processing unit 212 of the arithmetic device 21.

[0133] The processing unit 212 compares the certainty factor associated with one fingerprint image with a first predetermined value (see the second embodiment). The processing unit 212 estimates the fingerprint pattern type of the fingerprint indicated by one fingerprint image based on the comparison result between each of the plurality of certainty factors corresponding to each of the plurality of pattern types and the first predetermined value.

[0134] For one fingerprint image, if the multiple certainty factors corresponding to the multiple pattern types include a certainty factor higher than a first predetermined value, the processing unit 212 estimates that the pattern type of the fingerprint represented by the one fingerprint image is a pattern type corresponding to a certainty factor higher than the first predetermined value. In this case, the processing unit 212 associates the one fingerprint image with the pattern type corresponding to a certainty factor higher than the first predetermined value. If the multiple certainty factors associated with the multiple pattern types are higher than the first predetermined value, the processing unit 212 may associate the one fingerprint image with the multiple pattern types.

[0135] If the multiple certainty factors respectively corresponding to the multiple pattern types do not include a certainty factor higher than the first predetermined value, the processing unit 212 may estimate that the pattern type of the fingerprint represented by one fingerprint image is an incomplete pattern. In this case, the processing unit 212 may associate one fingerprint image with the incomplete pattern type.

[0136] The processing unit 212 sets a central axis based on the pattern type associated with one fingerprint image and the fingerprint image itself. If multiple pattern types are associated with one fingerprint image, the processing unit 212 may set multiple central axes corresponding to the multiple pattern types, respectively. In other words, the processing unit 212 may set one central axis for each pattern type associated with one fingerprint image.

[0137] For example, when multiple pattern types and multiple central axes are registered or edited for one fingerprint image via the input device 24 (in other words, when the user of the information processing device 2 registers or edits multiple pattern types and multiple central axes for one fingerprint image), the processing unit 212 determines whether the multiple central axes associated with each of the multiple pattern types are correct. In this case, the processing unit 212 may, for example, compare the central axis associated with one pattern type with the central axis set for that pattern type by the processing unit 212. Based on the comparison result, the processing unit 212 may determine whether the multiple central axes associated with each of the multiple pattern types are correct. When it is determined that the central axis associated with at least one of the multiple pattern types is incorrect, the processing unit 212 issues a warning, for example, urging the user to recheck the central axis.

[0138] It is assumed that the pattern type associated with a registered or edited fingerprint image is the same as the pattern type associated with the fingerprint image based on the confidence level by processing unit 212. If the pattern type associated with a registered or edited fingerprint image is different from the pattern type associated with the fingerprint image based on the confidence level by processing unit 212, processing unit 212 may issue a warning to, for example, urge the user to reconfirm the pattern type, as described in the seventh embodiment.

[0139] The operation of information processing device 2 will be further described with reference to the flowchart in Fig. 11. In Fig. 11, output unit 211 of arithmetic device 21 acquires one fingerprint image (step S101). Output unit 211 inputs the one fingerprint image to a learning model, thereby acquiring a confidence factor for the one fingerprint image. Output unit 211 outputs the confidence factor for the one fingerprint image (step S102).

[0140] The processing unit 212 of the computing device 21 compares each of the multiple confidence levels corresponding to each of the multiple pattern types with a first predetermined value based on the confidence level for one fingerprint image. The processing unit 212 estimates the pattern type of the fingerprint indicated by one fingerprint image based on the comparison result between each of the multiple confidence levels corresponding to each of the multiple pattern types and the first predetermined value (step S701).

[0141] In the processing of step S701, if the multiple certainty factors corresponding to the multiple pattern types for a single fingerprint image include a certainty factor higher than the first predetermined value, the processing unit 212 infers that the pattern type of the fingerprint represented by the single fingerprint image is a pattern type corresponding to a certainty factor higher than the first predetermined value. In this case, the processing unit 212 associates the single fingerprint image with the pattern type corresponding to a certainty factor higher than the first predetermined value. If the multiple certainty factors associated with each of the multiple pattern types are higher than the first predetermined value, the processing unit 212 may associate the single fingerprint image with the multiple pattern types. If the multiple certainty factors corresponding to the multiple pattern types do not include a certainty factor higher than the first predetermined value, the processing unit 212 may infer that the pattern type of the fingerprint represented by the single fingerprint image is an incomplete pattern. In this case, the processing unit 212 may associate the single fingerprint image with the incomplete pattern type.

[0142] Next, the processing unit 212 sets a central axis based on the fingerprint image and the pattern type associated with the fingerprint image (step S702). If multiple pattern types are associated with the fingerprint image, the processing unit 212 may set multiple central axes corresponding to the multiple pattern types, respectively, in the processing of step S702.

[0143] The processing unit 212 determines whether at least one of the pattern type and the central axis has been registered or edited for one fingerprint image (step S703). If it is determined in the process of step S703 that the pattern type and the central axis have not been registered or edited (step S703: No), the processing unit 212 performs the process of step S703 again. In other words, the processing unit 212 may be in a standby state until at least one of the pattern type and the central axis has been registered or edited.

[0144] If it is determined in the process of step S703 that at least one of the pattern type and the central axis has been registered or edited (step S703: Yes), the processing unit 212 determines whether the number of pattern types associated with one fingerprint image is two or more (step S704). If it is determined in the process of step S704 that the number of pattern types is not two or more (step S704: No), the operation shown in FIG. 11 is terminated.

[0145] If it is determined in the process of step S704 that there are two or more pattern types (step S704: Yes), the processing unit 212 determines whether the multiple central axes associated with the multiple pattern types are correct (step S705). If it is determined in the process of step S705 that the multiple central axes associated with the multiple pattern types are correct (step S705: Yes), the operation shown in FIG. 11 ends.

[0146] In the processing of step S705, if it is determined that the central axis associated with at least one of the multiple pattern types is incorrect (step S705: No), the processing unit 212 issues a warning, for example, urging the user to recheck the central axis (step S706).

[0147] The above-described operations may be realized by the information processing device 2 reading a computer program recorded on a recording medium. In this case, it can be said that the recording medium records a computer program for causing the information processing device 2 to execute the above-described operations.

[0148] According to the eighth embodiment, for example, a warning is issued to prompt the user to reconfirm the central axis associated with the pattern type, thereby preventing errors in registering the central axis when registering or editing fingerprint data. In the fingerprint database, the central axis is associated with the pattern type. For example, if two pattern types and two central axes associated with the two pattern types are registered for one fingerprint image, fingerprint matching for the one fingerprint image is performed as follows. When matching a fingerprint image with a matching target limited based on one of the two pattern types, fingerprint matching is performed after the matching range is limited by the central axis associated with the one pattern type. Furthermore, when matching a fingerprint image with a matching target limited based on the other of the two pattern types, fingerprint matching is performed after the matching range is limited by the central axis associated with the other pattern type. Therefore, fingerprint matching for one fingerprint image can be performed appropriately without increasing the processing load related to fingerprint matching.

[0149] (Variation) In the processing of step S706 described above, instead of or in addition to issuing a warning to urge the user to reconfirm the central axis, the processing unit 212 may link the multiple pattern types associated with one fingerprint image in the processing of step S701 described above with the multiple central axes respectively corresponding to the multiple pattern types set in the processing of step S702 described above, and register them in the fingerprint database.

[0150] <Additional Notes> The following additional notes are provided regarding the above-described embodiment.

[0151] (Appendix 1) an output means for outputting a confidence level, which is an index indicating the likelihood that the fingerprint shown in the fingerprint image corresponds to at least one of a plurality of pattern types, using a fingerprint image and a learning model constructed by machine learning using learning data including sample images showing fingerprints; a processing means for executing a process based on the confidence level; A fingerprint information processing device comprising:

[0152] (Appendix 2) the output means outputs the certainty by combining an output result of a first model as the learning model when the fingerprint image is input to the first model and an output result of a second model as the learning model when the fingerprint image is input to the second model; The first model and the second model have different output tendencies relative to inputs. 2. A fingerprint information processing device according to claim 1.

[0153] (Appendix 3) the output means outputs the certainty factor using one fingerprint image that has already been registered as the fingerprint image and the learning model; The processing means performs the following processing: estimating the type of fingerprint pattern represented by the one fingerprint image based on the degree of certainty; If the estimated pattern type differs from the pattern type already associated with the one fingerprint image, at least one of a notification and an update of the pattern type already associated with the one fingerprint image is performed. 3. The fingerprint information processing device according to claim 1 or 2.

[0154] (Appendix 4) The processing means performs the following processing: estimating the type of fingerprint pattern represented by the fingerprint image based on the degree of certainty; If the fingerprint represented by the fingerprint image corresponds to two or more of the plurality of pattern types, a plurality of central axes corresponding to the two or more pattern types are set. 4. The fingerprint information processing device according to any one of claims 1 to 3.

[0155] (Appendix 5) When the two or more pattern types include an arch-shaped pattern and another pattern type different from the arch-shaped pattern, the processing means sets a central axis extending in the direction of the fingertip of the fingerprint shown in the fingerprint image as the central axis corresponding to the arch-shaped pattern, and sets a central axis extending in the direction of the central hoof line of the fingerprint shown in the fingerprint image as the central axis corresponding to the one pattern type. 5. A fingerprint information processing device according to claim 4.

[0156] (Appendix 6) As the processing, the processing means performs fingerprint matching on the fingerprint image using a plurality of central axes respectively corresponding to the two or more pattern types. 6. The fingerprint information processing device according to claim 4 or 5.

[0157] (Appendix 7) The processing means performs the following processing: estimating the type of fingerprint pattern represented by the fingerprint image based on the degree of certainty; When the type of pattern input by the user for the fingerprint shown in the fingerprint image differs from the estimated type of pattern, a notification is made. 7. A fingerprint information processing device according to any one of appendices 1 to 6.

[0158] (Appendix 8) The processing means performs the following processing: estimating the type of fingerprint pattern represented by the fingerprint image based on the degree of certainty; if the fingerprint represented by the fingerprint image corresponds to two or more of the plurality of pattern types, a plurality of central axes are set corresponding to the two or more pattern types, respectively; When the correspondence between the two or more pattern types and the set plurality of central axes differs from the correspondence between the pattern type and central axis input by the user for the fingerprint shown in the fingerprint image, a notification is made. 8. A fingerprint information processing device according to any one of appendices 1 to 7.

[0159] (Appendix 9) using a fingerprint image and a learning model constructed by machine learning using learning data including sample images of fingerprints, outputting a certainty factor which is an index indicating the likelihood that the fingerprint shown by the fingerprint image corresponds to at least one of a plurality of pattern types; Execute a process based on the confidence level Fingerprint information processing method.

[0160] (Appendix 10) On the computer, using a fingerprint image and a learning model constructed by machine learning using learning data including sample images of fingerprints, outputting a certainty factor which is an index indicating the likelihood that the fingerprint shown by the fingerprint image corresponds to at least one of a plurality of pattern types; Execute a process based on the confidence level A recording medium on which a computer program for executing a fingerprint information processing method is recorded.

[0161] This disclosure is not limited to the above-described embodiments. For example, if palm prints can be classified into patterns, this disclosure may be applied to palm prints in addition to fingerprints. This disclosure may be modified as appropriate within the scope of the claims and the gist or concept of the invention as can be read from the entire specification. Fingerprint information processing devices, fingerprint information processing methods, and recording media incorporating such modifications are also included within the technical scope of this disclosure.

[0162] To the extent permitted by law, this application claims priority based on Japanese Patent Application No. 2022-120344, filed on July 28, 2022, the disclosure of which is incorporated herein in its entirety. Furthermore, to the extent permitted by law, all publications and papers mentioned in this specification are incorporated herein by reference. [Explanation of symbols]

[0163] 1, 2 Information processing device 11, 211 Output section 12, 212 Processing section 21 Arithmetic unit 22 Storage device 23 Communication equipment 24 input devices 25 Output Devices

Claims

1. an output means for outputting a confidence level, which is an index indicating the likelihood that the fingerprint shown in the fingerprint image corresponds to at least one of a plurality of pattern types, using a fingerprint image and a learning model constructed by machine learning using learning data including sample images showing fingerprints; a processing means for executing a process based on the confidence level; Equipped with the output means outputs the certainty factor using one fingerprint image that has already been registered as the fingerprint image and the learning model; The processing means performs the following processing: estimating the type of fingerprint pattern represented by the one fingerprint image based on the degree of certainty; If the estimated pattern type differs from the pattern type already associated with the one fingerprint image, at least one of a notification and an update of the pattern type already associated with the one fingerprint image is performed. Fingerprint information processing device.

2. the output means outputs the certainty by combining an output result of a first model as the learning model when the fingerprint image is input to the first model and an output result of a second model as the learning model when the fingerprint image is input to the second model, The first model and the second model have different output tendencies relative to inputs. The fingerprint information processing device according to claim 1 .

3. The processing means performs the following processing: estimating the type of fingerprint pattern represented by the fingerprint image based on the degree of certainty; If the fingerprint represented by the fingerprint image corresponds to two or more of the plurality of pattern types, a plurality of central axes corresponding to the two or more pattern types are set. The fingerprint information processing device according to claim 1 .

4. When the two or more pattern types include an arch-shaped pattern and one pattern type different from the arch-shaped pattern, the processing means sets a central axis extending in the direction of the fingertip of the fingerprint shown in the fingerprint image as the central axis corresponding to the arch-shaped pattern, and sets a central axis extending in the direction of the central hoof line of the fingerprint shown in the fingerprint image as the central axis corresponding to the one pattern type. The fingerprint information processing device according to claim 3 .

5. As the processing, the processing means performs fingerprint matching on the fingerprint image using a plurality of central axes respectively corresponding to the two or more pattern types. The fingerprint information processing device according to claim 3 .

6. The processing means performs the following processing: estimating the type of fingerprint pattern represented by the fingerprint image based on the degree of certainty; When the type of pattern input by the user for the fingerprint shown in the fingerprint image differs from the estimated type of pattern, a notification is made. The fingerprint information processing device according to claim 1 .

7. The processing means performs the following processing: estimating the type of fingerprint pattern represented by the fingerprint image based on the degree of certainty; if the fingerprint represented by the fingerprint image corresponds to two or more of the plurality of pattern types, a plurality of central axes are set corresponding to the two or more pattern types, respectively; When the correspondence between the two or more pattern types and the set plurality of central axes differs from the correspondence between the pattern type and central axis input by the user for the fingerprint shown in the fingerprint image, a notification is made. The fingerprint information processing device according to claim 1 .

8. A computer uses a fingerprint image and a learning model constructed by machine learning using learning data including sample images of fingerprints, and outputs a certainty index that indicates the likelihood that a fingerprint represented by the fingerprint image corresponds to at least one of a plurality of pattern types; The computer executes a process based on the confidence level. A fingerprint information processing method, comprising: the computer uses an already registered fingerprint image as the fingerprint image and the learning model to output the confidence level; The computer performs the process as follows: estimating the type of fingerprint pattern represented by the one fingerprint image based on the degree of certainty; If the estimated pattern type differs from the pattern type already associated with the one fingerprint image, at least one of a notification and an update of the pattern type already associated with the one fingerprint image is performed. Fingerprint information processing method.

9. On the computer, using a fingerprint image and a learning model constructed by machine learning using learning data including sample images of fingerprints, outputting a certainty factor which is an index indicating the likelihood that the fingerprint shown by the fingerprint image corresponds to at least one of a plurality of pattern types; Execute a process based on the confidence level A fingerprint information processing method, comprising: outputting the confidence level using one fingerprint image that has already been registered as the fingerprint image and the learning model; As the processing, estimating the type of fingerprint pattern represented by the one fingerprint image based on the degree of certainty; If the estimated pattern type differs from the pattern type already associated with the one fingerprint image, at least one of a notification and an update of the pattern type already associated with the one fingerprint image is performed. A recording medium on which a computer program for executing a fingerprint information processing method is recorded.

Images