Classifications

• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/117—Identification of persons
  • A61B5/1171—Identification of persons based on the shapes or appearances of their bodies or parts thereof
  • A61B5/1172—Identification of persons based on the shapes or appearances of their bodies or parts thereof using fingerprinting
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T7/00—Image analysis
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
  • G06V10/00—Arrangements for image or video recognition or understanding
  • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
  • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
  • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
  • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
  • G06V40/12—Fingerprints or palmprints
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
  • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
  • G06V40/50—Maintenance of biometric data or enrolment thereof

Definitions

• This disclosure relates to the technical fields of estimation devices, estimation methods, and recording media.
• Patent Document 1 discloses a technique for correcting the inclination of an image when matching a fingerprint image.
• Patent Document 2 discloses a technique for determining the finger type of a fingerprint image and detecting errors in the type of finger imprinted.
• Patent Document 3 discloses a technique for identifying abnormal areas in a fingerprint using a learning model trained by machine learning.
• One aspect of the estimation device disclosed herein includes an acquisition means for acquiring a rotated fingerprint image captured by rotating a finger, and an estimation means for estimating the type of finger contained in the rotated fingerprint image by inputting the acquired rotated fingerprint image into a trained model.
• One aspect of the estimation method disclosed herein involves using at least one computer to obtain a rotated fingerprint image captured by rotating a finger, and inputting the rotated fingerprint image into a trained model to estimate the type of finger contained in the rotated fingerprint image.
• a computer program is recorded on at least one computer to execute an estimation method for acquiring a rotated fingerprint image captured by rotating a finger, and inputting the rotated fingerprint image into a trained model to estimate the type of finger contained in the rotated fingerprint image.
• FIG. 1 is a block diagram showing a hardware configuration of an estimation device according to a first embodiment.
• FIG. 1 is a block diagram showing a functional configuration of an estimation device according to a first embodiment.
• FIG. 4 is a flowchart showing a flow of operations of the estimation device according to the first embodiment.
• FIG. 11 is a block diagram showing a functional configuration of an estimation device according to a second embodiment.
• 10 is a flowchart showing a flow of operations of the estimation device according to the second embodiment.
• FIG. 13 is a block diagram showing a functional configuration of an estimation device according to a third embodiment. 13 is a flowchart showing the flow of operations of the estimation device according to the third embodiment.
• FIG. 13 is a block diagram showing a functional configuration of an estimation device according to a fourth embodiment.
• FIG. 13 is a flowchart showing the flow of operations of the estimation device according to the fourth embodiment.
• FIG. 13 is a block diagram showing a functional configuration of an estimation device according to a fifth embodiment.
• 13 is a flowchart showing the flow of operations of the estimation device according to the fifth embodiment.
• FIG. 13 is a block diagram showing a functional configuration of an estimation device according to a sixth embodiment.
• 23 is a flowchart showing the flow of operations of the estimation device according to the sixth embodiment.
• 23 is a flowchart showing a flow of operations of an estimation device according to a modified example of the sixth embodiment.
• FIG. 23 is a schematic diagram illustrating a hardware configuration of an estimation device according to a seventh embodiment.
• FIG. 1 An estimation device according to a first embodiment will be described with reference to FIGS. 1 to 3.
• FIG. 1 An estimation device according to a first embodiment will be described with reference to FIGS. 1 to 3.
• FIG. 1 An estimation device according to a first embodiment will be described with reference to FIGS. 1 to 3.
• FIG. 1 An estimation device according to a first embodiment will be described with reference to FIGS. 1 to 3.
• FIG. 1 An estimation device according to a first embodiment will be described with reference to FIGS. 1 to 3.
• Fig. 1 is a block diagram showing the hardware configuration of the estimation device according to the first embodiment.
• the estimation device 10 includes a processor 11, a RAM (Random Access Memory) 12, and a ROM (Read Only Memory) 13.
• the estimation device 10 may further include a storage device 14, an input device 15, and an output device 16.
• the above-mentioned processor 11, RAM 12, ROM 13, storage device 14, input device 15, and output device 16 are connected via a data bus 17.
• the processor 11 reads a computer program.
• the processor 11 is configured to read a computer program stored in at least one of the RAM 12, the ROM 13, and the storage device 14.
• the processor 11 may read a computer program stored in a computer-readable storage medium using a storage medium reading device (not shown).
• the processor 11 may obtain (i.e., read) a computer program from a device (not shown) disposed outside the estimation device 10 via a network interface.
• the processor 11 controls the RAM 12, the storage device 14, the input device 15, and the output device 16 by executing the computer program that the processor 11 reads.
• a functional block for acquiring a rotated fingerprint image and estimating a finger type is realized within the processor 11.
• the processor 11 may function as a controller that executes each control in the estimation device 10.
• the processor 11 may be configured as, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (field-programmable gate array), a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), or a quantum processor.
• the processor 11 may be configured as one of these, or may be configured to use multiple processors in parallel.
• RAM 12 temporarily stores computer programs executed by processor 11.
• RAM 12 temporarily stores data that processor 11 uses temporarily while processor 11 is executing a computer program.
• RAM 12 may be, for example, a D-RAM (Dynamic Random Access Memory) or an SRAM (Static Random Access Memory). Also, other types of volatile memory may be used instead of RAM 12.
• ROM 13 stores computer programs executed by processor 11. ROM 13 may also store other fixed data. ROM 13 may be, for example, a P-ROM (Programmable Read Only Memory) or an EPROM (Erasable Read Only Memory). Also, other types of non-volatile memory may be used instead of ROM 13.
• the storage device 14 stores data that the estimation device 10 stores long-term.
• the storage device 14 may operate as a temporary storage device for the processor 11.
• the storage device 14 may include, for example, at least one of a hard disk device, a magneto-optical disk device, an SSD (Solid State Drive), and a disk array device.
• the input device 15 is a device that receives input instructions from a user of the estimation device 10.
• the input device 15 may include, for example, at least one of a keyboard, a mouse, and a touch panel.
• the input device 15 may be configured as a mobile terminal such as a smartphone or a tablet.
• the input device 15 may be, for example, a device that includes a microphone and is capable of voice input.
• the output device 16 is a device that outputs information related to the estimation device 10 to the outside.
• the output device 16 may be a display device (e.g., a display) that can display information related to the estimation device 10.
• the output device 16 may be configured as a mobile terminal such as a smartphone or a tablet.
• the output device 16 may also be a device that outputs information in a format other than an image.
• the output device 16 may be a speaker that outputs information related to the estimation device 10 as audio.
• the estimation device 10 may be configured to include only the above-mentioned processor 11, RAM 12, and ROM 13, and the other components (i.e., the storage device 14, the input device 15, and the output device 16) may be provided by an external device connected to the estimation device 10.
• the calculation functions of the estimation device 10 may be realized by an external device (e.g., an external server or cloud, etc.).
• Fig. 2 is a block diagram showing the functional configuration of the estimation device according to the first embodiment.
• the estimation device 10 is configured to include a fingerprint image acquisition unit 110 and a finger type estimation unit 120 as components for realizing its functions.
• Each of the fingerprint image acquisition unit 110 and the finger type estimation unit 120 may be a processing block realized by, for example, the above-mentioned processor 11 (see FIG. 1).
• the fingerprint image acquisition unit 110 is configured to be able to acquire a rotated fingerprint image.
• a rotated fingerprint image is a fingerprint image acquired by rotating a finger, and includes fingerprints on the side of the finger as well as the pad of the finger.
• the fingerprint image acquisition unit 110 may directly acquire a rotated fingerprint image acquired by, for example, a scanner, or may acquire a rotated fingerprint image stored in a database or the like (i.e., a rotated fingerprint image acquired in the past).
• the rotated fingerprint image acquired by the fingerprint image acquisition unit 110 is configured to be output to the finger type estimation unit 120.
• the finger type estimation unit 120 is configured to be able to estimate the type of finger (hereinafter referred to as "finger type” as appropriate) contained in the rotated fingerprint image acquired by the fingerprint image acquisition unit 110.
• the finger type estimation unit 120 estimates the finger type by inputting the rotated fingerprint image to a trained model (hereinafter referred to as "trained model” as appropriate).
• the trained model is a model trained in advance using training data, and when a rotated fingerprint image is input, it outputs the finger type of the rotated fingerprint image.
• the trained model may be, for example, a model trained by machine learning by inputting pair information of a fingerprint image and finger type, which is training data.
• the trained model may be, for example, a neural network trained by deep learning.
• the amount of training data that can be prepared is small, the amount of training data may be increased, for example, by generating similar data to the training data or by applying perturbations to the training data.
• the training data may be generated, for example, using a GAN (generative adversarial network).
• Fig. 3 is a flowchart showing the flow of operations of the estimation device according to the first embodiment.
• the fingerprint image acquisition unit 110 first acquires a rotated fingerprint image (step S101). Then, the finger type estimation unit 120 inputs the rotated fingerprint image acquired by the fingerprint image acquisition unit 110 into the learning model (step S102).
• the type of finger contained in the rotated fingerprint image is estimated (step S103).
• the finger type estimation unit 120 outputs finger type information indicating the type of finger contained in the rotated fingerprint image (step S104).
• the finger type information output by the finger type estimation unit 120 may be stored (registered), for example, in association with the rotated fingerprint image. The registration process using finger type information will be described in detail in another embodiment described later.
• the type of finger contained in a rotated fingerprint image is estimated by inputting the rotated fingerprint image into a learning model.
• Finger type estimation using a rotated fingerprint image alone is not easy, even for example, a forensic examiner who specializes in fingerprints.
• the estimation device 10 according to the present embodiment makes it possible to estimate the type of finger contained in a rotated fingerprint image with high accuracy.
• the estimation device 10 according to the second embodiment will be described with reference to Fig. 4 and Fig. 5.
• the second embodiment differs from the first embodiment described above only in some configurations and operations, and other parts may be the same as those of the first embodiment. Therefore, hereinafter, parts that differ from the first embodiment already described will be described in detail, and other overlapping parts will be omitted as appropriate.
• Fig. 4 is a block diagram showing the functional configuration of the estimation device according to the second embodiment.
• the same components as those shown in Fig. 2 are denoted by the same reference numerals.
• the estimation device 10 according to the second embodiment is configured to include, as components for realizing its functions, a fingerprint image acquisition unit 110, a finger type estimation unit 120, a fingerprint image storage unit 130, and a registered finger type determination unit 140. That is, the estimation device 10 according to the second embodiment further includes a fingerprint image storage unit 130 and a registered finger type determination unit 140 in addition to the configuration of the first embodiment (see FIG. 2). Each of the fingerprint image storage unit 130 and the registered finger type determination unit 140 may be realized by, for example, the above-mentioned processor 11 or storage device 14 (see FIG. 1).
• the fingerprint image storage unit 130 is configured to be able to store rotated fingerprint images in association with the type of finger.
• the fingerprint image storage unit 130 adds information indicating that the image is a "thumb" to a rotated fingerprint image taken from, for example, the thumb, and stores the image.
• the fingerprint image storage unit 130 may be configured to be able to store rotated fingerprint images of multiple fingers in association with the type of finger.
• the fingerprint image storage unit 130 may be configured to store rotated fingerprint images of ten fingers on both hands in association with the type of finger, respectively.
• the fingerprint image storage unit 130 may also be configured to store planar fingerprint images (i.e., fingerprint images of the pads of the fingers that can be taken without rotating the fingers) in addition to the rotated fingerprint images.
• the planar fingerprint images may also be able to be stored in association with the type of finger.
• the fingerprint image storage unit 130 may also be configured to store rotated fingerprint images for each user.
• the fingerprint image storage unit 130 may be configured to store ten rotated fingerprint images of both hands of user A, ten rotated fingerprint images of both hands of user B, and ten rotated fingerprint images of both hands of user C.
• the rotated fingerprint images stored in the fingerprint image storage unit 130 can be read out as needed by the registered finger type determination unit 140.
• Fingerprint image storage unit 130 may be configured as a database that stores fingerprint images used in a fingerprint matching system, for example. More specifically, fingerprint image storage unit 130 may be configured as a database for a fingerprint matching system managed by the police.
• the registered finger type determination unit 140 is configured to be able to determine whether the finger type stored in the fingerprint image storage unit 130 (i.e., the finger type stored in association with the rotated fingerprint image) matches the finger type estimated by the finger type estimation unit 120 (i.e., the finger type estimated by inputting the rotated fingerprint image into a learning model).
• the registered finger type determination unit 140 is configured to be able to output information indicating that the finger type stored in the fingerprint image storage unit 130 is incorrect if the finger type stored in the fingerprint image storage unit 130 does not match the finger type estimated by the finger type estimation unit 120.
• FIG. 5 is a flowchart showing the flow of operations of the estimation device according to the second embodiment.
• the same processes as those described in Fig. 3 are denoted by the same reference numerals.
• the fingerprint image acquisition unit 110 first acquires the rotated fingerprint image stored in the fingerprint image storage unit 130 (step S201).
• the finger type estimation unit 120 inputs the rotated fingerprint image acquired by the fingerprint image acquisition unit 110 into the learning model (step S102). Then, based on the rotated fingerprint image into which the learning model has been input, the finger type contained in the rotated fingerprint image is estimated (step S103).
• the registered finger type determination unit 140 reads out the finger type stored in the fingerprint image storage unit 130 (step S202). That is, it reads out information indicating the finger type that is linked to the rotated fingerprint image acquired in step S201 and stored. The registered finger type determination unit 140 then determines whether the finger type stored in the fingerprint image storage unit 130 matches the finger type estimated by the finger type estimation unit 120 (step S203).
• the registered finger type determination unit 140 outputs information indicating that the finger type stored in the fingerprint image storage unit 130 is incorrect (hereinafter referred to as "registration error information") (step S204).
• the registered finger type determination unit 140 may display the registration error information to the user (administrator) of the device via a display or the like. For example, the registered finger type determination unit 140 may display the rotated fingerprint image with the incorrectly stored finger type, the already stored finger type (i.e., the incorrect finger type), and the estimated finger type (i.e., the correct finger type). The registered finger type determination unit 140 may also execute a process to correct or delete the finger type for the rotated fingerprint image with the incorrectly stored finger type. Alternatively, the registered finger type determination unit 140 may output a message or the like encouraging re-registration for the rotated fingerprint image with the incorrectly stored finger type. For example, the registered finger type determination unit 140 may output a message saying, "The finger type for this rotated fingerprint image has been registered incorrectly. Please re-register the correct finger type.”
• step S204 the processing of step S204 described above is omitted. That is, the registered finger type determination unit 140 does not output registration error information. In this case, the registered finger type determination unit 140 may output information indicating that the finger type stored in the fingerprint image storage unit 130 is correct.
• the estimation device 10 may be configured to determine whether the stored finger type is correct for all of the multiple rotated fingerprint images stored in the fingerprint image storage unit 130.
• the estimation device 10 determines whether the finger type of the stored rotated fingerprint image matches the finger type estimated from the rotated fingerprint image. In this way, it becomes possible to appropriately determine whether the finger type of the stored rotated fingerprint image is incorrect.
• the estimation device 10 according to the third embodiment will be described with reference to Fig. 6 and Fig. 7.
• the third embodiment differs from the first and second embodiments in part of the configuration and operation, and other parts may be the same as the first and second embodiments. Therefore, hereinafter, parts that differ from the embodiments already described will be described in detail, and other overlapping parts will be omitted as appropriate.
• Fig. 6 is a block diagram showing the functional configuration of the estimation device according to the third embodiment.
• the same reference numerals are used to designate the same elements as those described in Fig. 2.
• the estimation device 10 according to the third embodiment is configured to include, as components for realizing its functions, a fingerprint image acquisition unit 110, a finger type estimation unit 120, a finger type designation unit 150, and a designated finger type determination unit 160. That is, the estimation device 10 according to the third embodiment further includes, in addition to the configuration of the first embodiment (see FIG. 2), a finger type designation unit 150 and a designated finger type determination unit 160.
• Each of the finger type designation unit 150 and the designated finger type determination unit 160 may be a processing block realized by, for example, the processor 11 described above.
• the finger type designation unit 150 is configured to be able to designate the type of finger from which a rotated fingerprint image is to be collected.
• the finger type designation unit 150 may designate a preset finger type.
• the finger type designation unit 150 may designate the finger types from which a rotated fingerprint image is to be collected sequentially according to a preset collection order.
• the finger type designation unit 150 may output information indicating the designated finger type to the subject from whom a rotated fingerprint image is to be collected.
• the finger type designation unit 150 may display a message such as "Please scan the fingerprint of your right index finger" on the display.
• the specified finger type determination unit 160 is configured to be able to determine whether the finger type specified by the finger type designation unit 150 matches the finger type estimated by the finger type estimation unit 120 using the collected rotated fingerprint image.
• the specified finger type determination unit 160 is also configured to be able to output information indicating that the type of finger from which the rotated fingerprint image was collected is incorrect if the finger type specified by the finger type designation unit 150 does not match the finger type estimated by the finger type estimation unit 120.
• Fig. 7 is a flowchart showing the flow of operations of the estimation device according to the third embodiment.
• the same processes as those described in Fig. 3 are denoted by the same reference numerals.
• the finger type designation unit 150 first outputs information designating the finger type from which a rotated fingerprint image is to be collected (step S301). This results in an operation to scan the designated finger as a target. Then, the fingerprint image acquisition unit 110 acquires the rotated fingerprint image collected from the target (step S302).
• the finger type estimation unit 120 inputs the rotated fingerprint image acquired by the fingerprint image acquisition unit 110 into the learning model (step S102). Then, based on the rotated fingerprint image into which the learning model has been input, the finger type contained in the rotated fingerprint image is estimated (step S103).
• the specified finger type determination unit 160 determines whether the finger type specified by the finger type specification unit 150 matches the finger type estimated by the finger type estimation unit 120 (step S303). In other words, the specified finger type determination unit 160 determines whether the type of finger specified to be collected matches the type of finger that was actually collected.
• the specified finger type determination unit 160 outputs information indicating that the finger type from which the rotated fingerprint image was collected is incorrect (hereinafter referred to as "collection error information") (step S304).
• the specified finger type determination unit 160 may display the collection error information to the subject (the user who collected the rotated fingerprint image) via a display or the like. For example, the specified finger type determination unit 160 may display the collected rotated fingerprint image, the finger type specified by the finger type designation unit 150, and the actually collected finger type (i.e., the type of finger that was incorrectly collected). The specified finger type determination unit 160 may also output a message or the like that encourages the user to re-collect a rotated fingerprint image of the specified finger type. For example, the specified finger type determination unit 160 may output a message that reads, "It appears that the fingerprint of the middle finger of your right hand has been scanned by mistake. Please scan the fingerprint of the index finger of your right hand.”
• step S303: YES if the finger type specified by the finger type specifying unit 150 and the finger type estimated by the finger type estimation unit 120 match (step S303: YES), the processing of step S304 described above is omitted. That is, the specified finger type determination unit 160 does not output collection error information. In this case, the specified finger type determination unit 160 may output information indicating that the type of finger from which the rotated fingerprint image was collected is correct.
• the estimation device 10 determines whether the type of finger from which the rotated fingerprint image was taken matches the type of the specified finger. In this way, it is possible to properly detect the wrong finger from which the rotated fingerprint image was taken. Therefore, the rotated fingerprint image of the specified finger can be taken without mistake. Furthermore, if the order of the fingers to be taken is specified, the rotated fingerprint images can be taken in the specified order. As a result, for example, it is possible to prevent the taken rotated fingerprint image from being registered as that of a different finger.
• the estimation device 10 according to the fourth embodiment will be described with reference to Fig. 8 and Fig. 9.
• the fourth embodiment differs from the first to third embodiments in some configurations and operations, and other parts may be the same as the first to third embodiments. Therefore, hereinafter, parts that differ from the embodiments already described will be described in detail, and other overlapping parts will be omitted as appropriate.
• Fig. 8 is a block diagram showing the functional configuration of the estimation device according to the fourth embodiment.
• the same reference numerals are used to designate the same elements as those described in Fig. 2.
• the estimation device 10 according to the fourth embodiment is configured to include a fingerprint image acquisition unit 110, a finger type estimation unit 120, and a fingerprint image registration unit 170 as components for realizing its functions. That is, the estimation device 10 according to the fourth embodiment further includes a fingerprint image registration unit 170 in addition to the configuration of the first embodiment (see FIG. 2).
• the fingerprint image registration unit 170 may be realized by, for example, the above-mentioned processor 11 or storage device 14 (see FIG. 1).
• the fingerprint image registration unit 170 is configured to be able to register a rotated fingerprint image by linking it to the finger type of the rotated fingerprint image.
• the fingerprint image registration unit 170 is configured to be able to register a rotated fingerprint image acquired by the fingerprint image acquisition unit 110 and a finger type estimated from the rotated fingerprint image by linking them to each other.
• the fingerprint image registration unit 170 may be configured to store (register) the rotated fingerprint image and the finger type in, for example, the fingerprint image storage unit 130 (see FIG. 4) described in the second embodiment.
• Fig. 9 is a flowchart showing the flow of operations of the estimation device according to the fourth embodiment.
• the same processes as those described in Fig. 3 are denoted by the same reference numerals.
• the fingerprint image acquisition unit 110 first acquires a rotated fingerprint image (step S101).
• the fingerprint image acquisition unit 110 acquires a rotated fingerprint image collected from a subject using a scanner or the like.
• the finger type estimation unit 120 inputs the rotated fingerprint image acquired by the fingerprint image acquisition unit 110 into the learning model (step S102). Then, based on the rotated fingerprint image into which the learning model has been input, the finger type contained in the rotated fingerprint image is estimated (step S103).
• the fingerprint image registration unit 170 links the rotated fingerprint image acquired by the fingerprint image acquisition unit 110 and the finger type estimated by the finger type estimation unit 120 to each other and registers them (step S401). For example, if the acquired rotated fingerprint image is estimated to be that of the index finger of the right hand, the fingerprint image registration unit 170 links the acquired rotated fingerprint image to information indicating that the rotated fingerprint image is that of the index finger of the right hand and registers them.
• a rotated fingerprint image is registered in association with the type of finger of the rotated fingerprint image.
• the finger type estimation unit 120 can estimate the finger type of a rotated fingerprint image with high accuracy, which can prevent the rotated fingerprint image from being registered with an incorrect finger type.
• the rotated fingerprint image can be properly registered without specifying the order of the fingers to be captured.
• the estimation device 10 according to the fifth embodiment will be described with reference to Fig. 10 and Fig. 11.
• the fifth embodiment differs from the fourth embodiment described above only in some configurations and operations, and other parts may be the same as the fourth embodiment. Therefore, hereinafter, parts that differ from the embodiments already described will be described in detail, and other overlapping parts will be omitted as appropriate.
• Fig. 10 is a block diagram showing the functional configuration of the estimation device according to the fifth embodiment.
• the same elements as those described in Fig. 8 are denoted by the same reference numerals.
• the estimation device 10 according to the fifth embodiment is configured to include, as components for realizing its functions, a fingerprint image acquisition unit 110, a finger type estimation unit 120, a fingerprint image registration unit 170, and a missing finger type determination unit 180. That is, the estimation device 10 according to the fifth embodiment further includes a missing finger type determination unit 180 in addition to the configuration of the fourth embodiment (see FIG. 8).
• the missing finger type determination unit 180 may be a processing block realized by, for example, the above-mentioned processor 11 (see FIG. 1).
• the missing finger type determination unit 180 is configured to be able to determine whether or not there are any missing rotated fingerprint images registered by the fingerprint image registration unit 170.
• the missing finger type determination unit 180 may be configured to determine whether or not rotated fingerprint images have been registered for all ten fingers on both hands. If there are any missing rotated fingerprint images in the registered rotated fingerprint images, the missing finger type determination unit 180 is configured to output information (hereinafter referred to as "missing information" as appropriate) that prompts the user to collect a rotated fingerprint image of the missing finger.
• the missing information may include, for example, information indicating the type of the missing finger.
• the missing information may also include information indicating the type of fingers that have already been collected.
• Fig. 11 is a flowchart showing the flow of operations of the estimation device according to the fifth embodiment.
• the same processes as those described in Fig. 9 are denoted by the same reference numerals.
• the fingerprint image acquisition unit 110 first acquires a rotated fingerprint image (step S101). Then, the finger type estimation unit 120 inputs the rotated fingerprint image acquired by the fingerprint image acquisition unit 110 into the learning model (step S102).
• the fingerprint image registration unit 170 links the rotated fingerprint image acquired by the fingerprint image acquisition unit 110 and the finger type estimated by the finger type estimation unit 120 to each other and registers them (step S401).
• the missing finger type determination unit 180 determines whether there is a missing part in the rotated fingerprint image registered by the fingerprint image registration unit 170 (step S501).
• the process of determining whether there is a missing part in the rotated fingerprint image i.e., the process of step S501
• the process of step S501 may be executed some time after the process of step S401 is completed.
• the missing finger type determination unit 180 may determine whether there is a missing part in a past rotated fingerprint image registered several months or several years ago.
• the missing finger type determination unit 180 If there are missing registered rotated fingerprint images (step S501: YES), the missing finger type determination unit 180 outputs missing information (step S502). For example, if there are missing rotated fingerprint images of the right index finger, the missing finger type determination unit 180 may output a message such as "There are missing fingerprints of the right index finger. Please obtain a fingerprint of the right index finger.”
• step S501 if there are no missing registered rotated fingerprint images (step S501: NO), the processing of step S502 described above is omitted. In other words, the missing finger type determination unit 180 does not output missing information. In this case, the missing finger type determination unit 180 may output information indicating that all rotated fingerprint images are complete.
• the estimation device 10 when a finger type is missing from the registered rotated fingerprint images, information is output to prompt the user to collect a rotated fingerprint image of the missing finger type.
• the missing finger type in the registered rotated fingerprint images can be properly detected.
• the missing rotated fingerprint images can be promptly replenished.
• the estimation device 10 according to the sixth embodiment will be described with reference to Fig. 12 and Fig. 13.
• the sixth embodiment differs from the first to fifth embodiments in part of its configuration and operation, and other parts may be the same as the first to fifth embodiments. Therefore, hereinafter, parts that differ from the embodiments already described will be described in detail, and other overlapping parts will be omitted as appropriate.
• Fig. 12 is a block diagram showing the functional configuration of the estimation device according to the sixth embodiment.
• the same reference numerals are used to designate the same elements as those described in Fig. 2.
• the estimation device 10 according to the sixth embodiment is configured to include, as components for realizing its functions, a fingerprint image acquisition unit 110, a finger type estimation unit 120, an image quality determination unit 190, and an alternative registration unit 200. That is, the estimation device 10 according to the sixth embodiment further includes, in addition to the configuration of the first embodiment (see FIG. 2), an image quality determination unit 190 and an alternative registration unit 200. Each of the image quality determination unit 190 and the alternative registration unit 200 may be realized, for example, by the above-mentioned processor 11 or storage device 14 (see FIG. 1).
• the image quality determination unit 190 is configured to be able to determine the quality of the rotated fingerprint image acquired by the fingerprint image acquisition unit 110. Specifically, the image quality determination unit 190 is configured to be able to determine whether or not the quality of the rotated fingerprint image satisfies a predetermined standard.
• the "predetermined standard” here is a standard that is set in advance as a standard for determining whether or not the quality of the rotated fingerprint image is sufficient for its operational use. For example, the predetermined standard may be set as a standard for determining whether or not the quality of the rotated fingerprint image is suitable for fingerprint matching.
• the alternative registration unit 200 is configured to be able to register a planar fingerprint image of the same type as the rotated fingerprint image in place of the rotated fingerprint image when it is determined that the quality of the rotated fingerprint image does not meet a predetermined standard. For example, when the quality of the rotated fingerprint image of a right index finger does not meet a predetermined standard, the alternative registration unit 200 registers the planar fingerprint image of the right index finger by linking it to information indicating that the finger type contained in the image is a right index finger.
• the planar fingerprint image registered in place of the rotated fingerprint image may be an image that has already been registered. In other words, the planar fingerprint image may be one that has already been registered and that has been collected separately from the rotated fingerprint image.
• the alternative registration unit 200 may register the rotated fingerprint image in association with information indicating the finger type.
• the alternative registration unit 200 may have the same functions as the fingerprint image registration unit 170 (see FIG. 8) described in the fourth embodiment.
• Fig. 13 is a flowchart showing the flow of operations of the estimation device according to the sixth embodiment.
• the same processes as those described in Fig. 3 are denoted by the same reference numerals.
• the fingerprint image acquisition unit 110 first acquires a rotated fingerprint image (step S101). After that, the finger type estimation unit 120 inputs the rotated fingerprint image acquired by the fingerprint image acquisition unit 110 into a learning model (step S102). Then, based on the rotated fingerprint image into which the learning model has been input, the finger type included in the rotated fingerprint image is estimated (step S103).
• the image quality determination unit 190 determines whether the quality of the rotated fingerprint image acquired by the fingerprint image acquisition unit 110 meets a predetermined standard (step S601).
• the process of determining the quality of the rotated fingerprint image may be executed immediately after the rotated fingerprint image is acquired. That is, the process of step S601 may be executed simultaneously in parallel with the processes of steps S102 and S103, or may be executed before or after the processes of steps S102 and S103.
• step S601 If the quality of the rotated fingerprint image meets the predetermined criteria (step S601: YES), the alternative registration unit 200 links the rotated fingerprint image to information indicating the estimated finger type and registers it (step S602). On the other hand, if the quality of the rotated fingerprint image does not meet the predetermined criteria (step S601: NO), the alternative registration unit 200 registers a flat fingerprint image of the same finger type as the rotated fingerprint image instead of the rotated fingerprint image (step S603).
• a flat fingerprint image is registered instead of the rotated fingerprint image. This makes it possible to prevent a low-quality rotated fingerprint image that is not suitable for operation from being registered. Furthermore, by registering a flat fingerprint image instead of a rotated fingerprint image, it is possible to prevent missing finger types.
• the process of alternatively registering a planar fingerprint image described in the sixth embodiment may be executed when it is determined that the finger type is incorrect.
• the alternative registration unit 200 may be configured to execute a process of registering a planar fingerprint image instead of an already stored rotated fingerprint image when it is determined in the registered finger type determination unit 140 described in the second embodiment that the finger type stored in the fingerprint image storage unit 130 does not match the finger type estimated by the finger type estimation unit 120.
• the flow of operations of this modified example will be specifically described below.
• Fig. 14 is a flowchart showing the flow of operations of the estimation device according to the modified example of the sixth embodiment.
• the same processes as those described in Figs. 5 and 13 are denoted by the same reference numerals.
• the fingerprint image acquisition unit 110 first acquires the rotated fingerprint image stored in the fingerprint image storage unit 130 (step S201).
• the finger type estimation unit 120 inputs the rotated fingerprint image acquired by the fingerprint image acquisition unit 110 into the learning model (step S102). Then, based on the rotated fingerprint image into which the learning model has been input, the finger type contained in the rotated fingerprint image is estimated (step S103).
• the registered finger type determination unit 140 reads out the finger type stored in the fingerprint image storage unit 130 (step S202). The registered finger type determination unit 140 then determines whether the finger type stored in the fingerprint image storage unit 130 matches the finger type estimated by the finger type estimation unit 120 (step S203).
• the alternative registration unit 200 registers a flat fingerprint image of the same finger type as the rotated fingerprint image instead of the rotated fingerprint image (step S603). That is, the alternative registration unit 200 overwrites and saves the flat fingerprint image of the correct finger type over the rotated fingerprint image (the rotated fingerprint image with the incorrect finger type registered) already stored in the fingerprint image storage unit 130.
• step S603 if the finger type stored in the fingerprint image storage unit 130 matches the finger type estimated by the finger type estimation unit 120 (step S203: YES), the processing of step S603 described above is omitted. In other words, the alternative registration unit 200 does not execute the processing of registering a flat fingerprint image instead of a rotated fingerprint image.
• the estimation device 10 As described in FIG. 14, in the estimation device 10 according to the modified example of the sixth embodiment, if the registered finger type is incorrect, a flat fingerprint image is registered instead of a rotated fingerprint image. In this way, even if a rotated fingerprint image of the wrong finger type is registered, the mistake in finger type can be corrected by replacing it with a flat fingerprint image of the correct finger type.
• the estimation device 10 according to the seventh embodiment will be described with reference to Fig. 15.
• the seventh embodiment is an embodiment that describes a more specific hardware configuration of the estimation device 10 described in the first to sixth embodiments, and the functional configuration and operation flow may be the same as those of the first to sixth embodiments. Therefore, in the following, the parts that differ from the embodiments already described will be described in detail, and the description of the other overlapping parts will be omitted as appropriate.
• Fig. 15 is a schematic diagram showing the hardware configuration of the estimation device according to the seventh embodiment.
• the estimation device 10 is configured to include a touch panel 51, a scanner unit 52, a display 53, and a control unit 54.
• Touch panel 51 is a panel on which the subject whose fingerprint is to be collected touches the finger. To collect a rotated fingerprint image, the subject simply moves their finger in a rotating motion on touch panel 51.
• Scanner unit 52 is disposed below touch panel 51, and scans the fingerprint image of the finger that touches touch panel 51. The fingerprint image scanned by scanner unit 52 is acquired by fingerprint image acquisition unit 110 (see FIG. 2, etc.).
• the display 53 is configured to be capable of displaying the fingerprint image scanned by the scanner unit 52.
• the display 53 may also be configured to display information regarding the finger type estimated from the scanned rotated fingerprint image.
• the display 53 may further be configured to be capable of displaying various information such as the registration error information (see Figures 4 and 5) described in the second embodiment, the information indicating the specified finger and the collection error information (see Figures 6 and 7) described in the third embodiment, and the missing information (see Figures 10 and 11) described in the fifth embodiment.
• the control unit 54 is a controller including, for example, the processor 11, and is configured to realize the components of the estimation device 10 according to each of the above-mentioned embodiments. Specifically, the control unit 54 may realize the functions of the fingerprint image acquisition unit 110, the finger type estimation unit 120, the fingerprint image storage unit 130, the registered finger type determination unit 140, the finger type designation unit 150, the designated finger type determination unit 160, the fingerprint image registration unit 170, the missing finger type determination unit 180, the image quality determination unit 190, and the alternative registration unit 200.
• the estimation device 10 can capture a rotated fingerprint image of a target and estimate with high accuracy the type of finger contained in the rotated fingerprint image.
• This estimation device 10 can be used, for example, as a device used to register fingerprints in a fingerprint matching system used by the police. It can also be used as a device for capturing fingerprints during immigration inspections at airports, etc.
• the estimation device 10 according to each of the above-described embodiments can be applied to, for example, mobile terminals such as smartphones, general home appliances, and the like.
• the estimation device 10 can estimate the type of finger that touched, eliminating the need to register the finger in advance.
• a touch with the index finger may execute the "page forward” function
• a touch with the middle finger may execute the "magnifier” function
• a touch with the index finger may execute the "play” function
• a touch with the middle finger may execute the "fast forward” function.
• a function corresponding to the finger used may be activated after the lock is released.
• answers to questions asked during initial setup may be selected according to the type of finger used to touch. Specifically, “yes” may be answered by touching with the index finger, and “no” may be answered by touching with the middle finger.
• This type of function is particularly effective in devices such as car navigation systems that are desired to be operated without looking at the screen.
• a remote control for a television or the like it can be used to change channels or adjust the volume with a specific finger. If it is installed in an electronic piano, it can be used to practice fingering when playing a song.
• each embodiment also includes a processing method in which a program that operates the configuration of each embodiment to realize the functions of the above-mentioned embodiments is recorded on a recording medium, the program recorded on the recording medium is read as code, and executed on a computer.
• computer-readable recording media are also included in the scope of each embodiment.
• each embodiment includes not only the recording medium on which the above-mentioned program is recorded, but also the program itself.
• the recording medium may be, for example, a floppy disk, hard disk, optical disk, magneto-optical disk, CD-ROM, magnetic tape, non-volatile memory card, or ROM.
• the scope of each embodiment is not limited to programs recorded on the recording medium that execute processes by themselves, but also includes programs that operate on an OS in conjunction with other software or the functions of an expansion board to execute processes.
• the program itself may be stored on a server, and part or all of the program may be made downloadable from the server to a user terminal.
• the program may be provided to the user in, for example, a SaaS (Software as a Service) format.
• the estimation device described in Appendix 1 is an estimation device that includes an acquisition means for acquiring a rotated fingerprint image collected by rotating a finger, and an estimation means for estimating the type of finger contained in the rotated fingerprint image by inputting the acquired rotated fingerprint image into a trained model.
• the estimation device described in Appendix 2 is the estimation device described in Appendix 1, further comprising: a storage means for storing the rotated fingerprint image in association with a finger type; and a first output means for outputting information indicating that the finger type stored in the storage means is incorrect when the finger type estimated by the estimation means from the rotated fingerprint image differs from the finger type stored in association with the rotated fingerprint image.
• the estimation device described in Appendix 3 is the estimation device described in Appendix 1 or 2, further comprising: a designation means for designating a type of finger from which the rotated fingerprint image is to be collected; and a second output means for outputting information indicating that the type of finger from which the rotated fingerprint image is to be collected is incorrect when the type of finger estimated by the estimation means from the collected rotated fingerprint image differs from the type of finger designated by the designation means.
• the estimation device described in Supplementary Note 4 is the estimation device described in any one of Supplementary Note 1 to 3, further comprising a registration means for registering the collected rotated fingerprint image in association with the finger type estimated by the estimation means.
• the estimation device described in Appendix 5 is the estimation device described in Appendix 4, further comprising a third output means for outputting information prompting a user to take a rotated fingerprint image of a missing finger when the rotated fingerprint image registered by the registration means has a missing finger type.
• the estimation device described in Supplementary Note 6 is the estimation device described in any one of Supplementary Note 1 to 5, further comprising: a determination means for determining whether or not the quality of the rotated fingerprint image satisfies a predetermined standard; and an alternative registration means for registering a flat fingerprint image of the same finger type as the rotated fingerprint image instead of the rotated fingerprint image if the quality of the rotated fingerprint image does not satisfy the predetermined standard.
• the estimation device described in Appendix 7 is the estimation device described in any one of Appendixes 1 to 6, further comprising: a storage means for storing the rotated fingerprint image in association with a finger type; and an alternative registration means for registering a flat fingerprint image of the same finger type as the rotated fingerprint image in place of the rotated fingerprint image when the finger type estimated by the estimation means from the rotated fingerprint image is different from the finger type stored in association with the rotated fingerprint image.
• the estimation device described in Supplementary Note 8 is the estimation device described in any one of Supplementary Notes 1 to 7, further including a touch panel on which a subject touches with his/her finger, and a scanner that scans the finger touching the touch panel to obtain the rotated fingerprint image.
• the estimation device described in Supplementary Note 9 is the estimation device described in any one of Supplementary Notes 1 to 8, further comprising a display that displays at least one of the rotated fingerprint image or information regarding the finger type estimated from the rotated fingerprint image.
• Appendix 10 The estimation method described in Appendix 10 is an estimation method in which a rotated fingerprint image is acquired by rotating a finger using at least one computer, and the rotated fingerprint image is input to a trained model to estimate the type of finger contained in the rotated fingerprint image.
• Appendix 11 The computer program described in Appendix 11 is a computer program that causes at least one computer to execute an estimation method for acquiring a rotated fingerprint image captured by rotating a finger, and inputting the rotated fingerprint image into a trained model, thereby estimating the type of finger contained in the rotated fingerprint image.
• the recording medium described in Appendix 12 is a recording medium having recorded thereon a computer program for causing at least one computer to execute an estimation method for acquiring a rotated fingerprint image captured by rotating a finger, and inputting the rotated fingerprint image into a trained model, thereby estimating the type of finger contained in the rotated fingerprint image.

Landscapes

• Engineering & Computer Science (AREA)
• Physics & Mathematics (AREA)
• Theoretical Computer Science (AREA)
• General Physics & Mathematics (AREA)
• Health & Medical Sciences (AREA)
• Multimedia (AREA)
• Life Sciences & Earth Sciences (AREA)
• Human Computer Interaction (AREA)
• Computer Vision & Pattern Recognition (AREA)
• Evolutionary Computation (AREA)
• General Health & Medical Sciences (AREA)
• Medical Informatics (AREA)
• Heart & Thoracic Surgery (AREA)
• Veterinary Medicine (AREA)
• Molecular Biology (AREA)
• Surgery (AREA)
• Animal Behavior & Ethology (AREA)
• Pathology (AREA)
• Public Health (AREA)
• Biomedical Technology (AREA)
• Biophysics (AREA)
• Artificial Intelligence (AREA)
• Computing Systems (AREA)
• Databases & Information Systems (AREA)
• Software Systems (AREA)
• Collating Specific Patterns (AREA)
• Image Input (AREA)

Priority Applications (1)

Applications Claiming Priority (2)

Publications (1)

Family

ID=92421434

Family Applications (1)

Country Status (2)

Citations (4)

Family Cites Families (1)

• 2024
  • 2024-01-17 JP JP2025500731A patent/JPWO2024171699A1/ja active Pending
  • 2024-01-17 WO PCT/JP2024/001107 patent/WO2024171699A1/ja not_active Ceased

Patent Citations (4)

Also Published As

Similar Documents

Legal Events