WO2019130670A1 - 生体認証システム - Google Patents

生体認証システム Download PDF

Info

Publication number
WO2019130670A1
WO2019130670A1 PCT/JP2018/033656 JP2018033656W WO2019130670A1 WO 2019130670 A1 WO2019130670 A1 WO 2019130670A1 JP 2018033656 W JP2018033656 W JP 2018033656W WO 2019130670 A1 WO2019130670 A1 WO 2019130670A1
Authority
WO
WIPO (PCT)
Prior art keywords
authentication
blood vessel
biometric
information
category
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2018/033656
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
友輔 松田
洋 野々村
三浦　直人
渓一郎 中崎
長坂　晃朗
宮武　孝文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hitachi Ltd
Original Assignee
Hitachi Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hitachi Ltd filed Critical Hitachi Ltd
Priority to CN201880048838.4A priority Critical patent/CN110945520B/zh
Priority to US16/640,663 priority patent/US11113493B2/en
Publication of WO2019130670A1 publication Critical patent/WO2019130670A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • 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
    • G06V40/14—Vascular patterns
    • G06V40/145—Sensors therefor
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30101—Blood vessel; Artery; Vein; Vascular
    • 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
    • G06V40/1341—Sensing with light passing through the finger
    • 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
    • G06V40/14—Vascular patterns

Definitions

  • the present invention relates to a biometric authentication system that performs authentication using biometric information of a user.
  • biometrics authentication has attracted attention as personal authentication with a low risk of unauthorized use.
  • finger vein authentication technology can realize a high degree of security because it uses a blood vessel pattern inside the finger.
  • the conventional finger vein authentication device presents a finger at a predetermined position of the authentication device, thereby improving the reproducibility of a captured vein image and realizing high accuracy authentication.
  • a device in which an unspecified number of people make finger contact at the time of authentication may cause hygiene problems.
  • an authentication apparatus that performs authentication using a vein image acquired without a living body contacting the apparatus.
  • the position of the finger is not fixed, so the presentation position or posture of the finger is likely to fluctuate, and the reproducibility of the captured vein image becomes low.
  • a biometric information acquisition unit for acquiring biometric information for verification from a user's living body, and a verification unit for collating registered biometric information registered in advance with the biometric information for verification
  • a registration unit for registering registered biometric information and posture feature of the living body in association with each other, and classifying the plurality of posture features registered by the registration unit into one or more classes in advance
  • a classification unit for associating the registered biometric information registered in the group with the class to which the posture feature corresponding to the registered biometric information belongs, and the registration unit is configured to perform the posture when the matching by the matching unit is successful.
  • the class to which the feature belongs belongs is determined, and the posture feature is registered as a new posture feature belonging to the class, and the registered biometric information associated with the class is not registered.
  • the posture feature amount to the living body information extraction apparatus characterized in that the crosscheck biometric information associated additionally registers as registered biological information related to the class have been disclosed.
  • JP-A-2015-106386 As the number of classes increases, the number of biometric information to be registered also increases, so the number of pieces of biometric information to be collated at the time of authentication may increase and the authentication speed may decrease. Further, in the technology disclosed in Japanese Patent Laid-Open No. 2015-106386, the position at which the living body is presented is fixed, and variations in the posture of the living body presented are not taken into consideration.
  • the following is a representative example of the invention disclosed in the present application. That is, it is a biometric authentication system that authenticates using registered registered biometric information, and a light source unit for irradiating light to a living body, and imaging for capturing a blood vessel image by light emitted from the light source unit and transmitted through the living body
  • a control unit that generates biometric information for authentication from a blood vessel image captured by the imaging unit, and auxiliary information including information on the position and orientation of the living body acquired at the imaging timing of the blood vessel image,
  • a category selection unit that selects a category corresponding to the authentication biometric information, and an authentication unit that performs authentication victory by comparing registered biometric information of the selected category with the authentication biometric information. It is characterized by
  • biometric information is collated after selecting a category, so high-speed and high-accuracy biometric authentication can be performed.
  • FIG. 1 is a diagram showing a configuration of a biometric authentication system according to a first embodiment.
  • FIG. 2 is a diagram showing a configuration of a living body information extraction terminal of Example 1.
  • FIG. 2 is a diagram showing a configuration of a server of Example 1;
  • FIG. 2 is a diagram showing the configuration of a biometric information database of Example 1;
  • FIG. 6 is a diagram for explaining an authentication method of the first embodiment.
  • 7 is a flowchart of an authentication process of the first embodiment.
  • FIG. 6 is a diagram for explaining a registration method of the first embodiment.
  • 5 is a flowchart of registration processing of the first embodiment.
  • FIG. 7 is a diagram for explaining the configuration of a blood vessel image capturing apparatus according to a second embodiment.
  • FIG. 7 is a flowchart of an authentication process of the second embodiment.
  • FIG. 14 is a diagram for explaining a category classification method based on information other than the position and posture of the finger in the second embodiment.
  • 21 is a flowchart of registration processing of the third embodiment.
  • FIG. 18 is a view showing an example of a blood vessel image photographing apparatus for photographing blood vessel images of a plurality of fingers presented simultaneously according to a fourth embodiment.
  • FIG. 18 is a diagram for explaining an example of the finger presentation position and posture change in the fourth embodiment.
  • FIG. 18 is a diagram for explaining an example of the finger presentation position and posture change in the fourth embodiment.
  • FIG. 18 is a diagram for explaining an example of the finger presentation position and posture change in the fourth embodiment.
  • Example 1 in the biometric authentication system using the presented blood vessel image of the living body (finger), a plurality of categories corresponding to the position and posture of the finger are created, and the blood vessel image registered in each category is referred to.
  • a system will be described which selects and executes registration data (blood vessel image) corresponding to a category corresponding to the detected hand position and posture.
  • FIG. 1 is a diagram showing the configuration of the biometric authentication system 501 of the first embodiment.
  • the biometric authentication system 501 of this embodiment has a server 502 (see FIG. 3) that performs arithmetic processing and at least one biometric information extraction terminal 503 (see FIG. 2).
  • the server 502 and the biometric information extraction terminal 503 are , Are connected via the network 504.
  • FIG. 2 is a diagram showing the configuration of the living body information extraction terminal 503 of the first embodiment.
  • the biological information extraction terminal 503 includes a blood vessel image capturing device 2, a control unit 6, a storage device 11, a speaker 13, a display unit 14, a user ID input unit 16, a data input unit 50 and a light source control unit 51.
  • An opening 3 for presenting the finger 1 to the blood vessel image photographing apparatus 2 at the time of blood vessel image photographing is provided on the surface of the casing of the blood vessel image photographing apparatus 2.
  • the opening 3 uses a material (for example, a transparent member such as acrylic or glass) that transmits light (near infrared light) emitted from the light source 10. If a film that allows only near infrared light to pass is attached to the opening 3, the inside of the blood vessel image photographing device 2 becomes difficult to visually recognize from the outside, and security can be improved.
  • An imaging unit 4 is disposed inside the housing below the opening 3.
  • the imaging unit 4 receives light (near infrared light) that has passed through the optical filter 5 and outputs an electrical signal (for example, a CMOS) Sensor).
  • the light received by the imaging unit 4 is converted into an electrical signal, and is taken into the control unit 6 as a blood vessel image through the data input unit 50.
  • An opening 9 is provided on the upper surface of the casing surface of the blood vessel imaging device 2, and a light source 10 is disposed inside the opening 9.
  • Determine the amount of light emitted by the The positional relationship between the light source 10, the imaging unit 4 and the finger 1 (living body presentation area 1A) in the blood vessel image capturing apparatus 2 of the present embodiment is the living body presentation area 1A between the light source 10 and the opening 3 (imaging section 4). It is sufficient that the living body 1 irradiated with the light from the light source 10 can be photographed by the imaging unit 4 through the opening 3 in addition to the above.
  • a mode in which the light source 10 is provided on the side or below the living body 1 and light that is emitted from the light source 10 via the opening 3 and scattered in the living body 1 is captured by the imaging unit 4 via the opening 3 May be.
  • the imaging unit 4 may capture a blood vessel image by light transmitted through the inside of the finger 1 with illumination light or natural light emitted to the finger 1.
  • the visible light source 15 is provided in the opening 3, and the state of the authentication process is provided to the user by emitting light in different colors for standby, when a hand is detected, authentication processing, authentication success, authentication failure, etc. May be notified.
  • the control unit 6 has a CPU 7, a memory 8 and an interface 17.
  • the CPU 7 executes a program stored in the memory 8 and calculates the position of the finger 1, the posture of the finger 1, the brightness of the finger area of the blood vessel image, and the like based on the blood vessel image taken into the control unit 6.
  • a light source control unit 51, a storage device 11, a speaker 13, a display unit 14, a user ID input unit 16, a data input unit 50, and a network 504 are connected to the interface 17.
  • the storage device 11 stores data necessary for the authentication process. For example, as described later, when the biometric information extraction terminal 503 performs an authentication process, the storage device 11 may store biometric information for comparison.
  • the speaker 13 notifies the user of the authentication result by sound (voice, chime sound, etc.).
  • the display unit 14 is a display device that notifies the user of the authentication result by characters or figures.
  • a personal identification number or an ID may be input, or a magnetic card or an IC chip may be read.
  • the user ID input unit 16 receives the presentation of the personal identification number, the ID, the magnetic card, and the IC chip, it is possible to narrow down the collating object from the large number of registered biometric information, and the search speed and the authentication accuracy can be improved.
  • the data input unit 50 is an interface that connects the blood vessel imaging device 2 and the control unit 6 and performs necessary data conversion.
  • the light source control unit 51 determines the light amount value irradiated by the light source 10 disposed inside the opening 9 based on the calculation result.
  • the light source 10 emits light in accordance with the set light amount value, and irradiates light to the finger.
  • the finger blood vessel image taken into the control unit 6 is stored in the memory 8, and the CPU 7 extracts the feature amount of the biological information from the image stored in the memory 8 and transmits the feature amount to the server 502.
  • the living body information extraction terminal 503 of the present embodiment detects the position of the finger and the posture of the finger using the image captured by the imaging unit 4, but using the finger and a distance detection unit such as a distance sensor described later
  • the position of the finger or the posture of the finger may be detected accurately and at high speed.
  • FIG. 3 is a diagram showing the configuration of the server 502 of the first embodiment.
  • the server 502 collates the biological information (for example, a blood vessel pattern of a finger) acquired by the biological information extraction terminal 503 by the operation unit 512 executing a predetermined program, thereby authenticating the individual.
  • the server 502 is a computer having an arithmetic unit 512, a memory 519, a storage unit 513, and a communication interface 520.
  • the arithmetic unit 512 executes the program stored in the memory 519 to execute an authentication process. Specifically, the calculation unit 512 functions as a category selection unit 514, a category creation unit 515, and an authentication unit 516.
  • the category selection unit 514 selects a category corresponding to the photographed finger blood vessel image in the authentication process and registration process described later.
  • the category creating unit 515 newly creates a category for registering the captured finger blood vessel image in a registration process described later.
  • the authentication unit 516 authenticates the person who presented the finger by comparing the feature amount of the captured finger blood vessel image with the registered feature amount in authentication processing and registration processing described later.
  • the memory 519 includes a ROM, which is a non-volatile storage element, and a RAM, which is a volatile storage element.
  • the ROM stores an immutable program (for example, BIOS).
  • BIOS an immutable program
  • the RAM is a high-speed and volatile storage element such as a dynamic random access memory (DRAM), and temporarily stores a program executed by the computing unit 512 and data used when the program is executed.
  • DRAM dynamic random access memory
  • the storage unit 513 is formed of, for example, a large-capacity non-volatile storage device such as a semiconductor storage device (SSD) including a magnetic storage device (HDD), a flash memory, etc., and stores a program to be executed by the computing unit 512. Do. That is, the program is read from the storage unit 513, loaded into the memory 519, and executed by the operation unit 512.
  • the storage unit 513 stores a biometric information database 518. An exemplary configuration of the biometric information database 518 will be described later with reference to FIG.
  • the communication interface 520 is a communication interface device that controls communication with other devices via the network 504 in accordance with a predetermined protocol.
  • the server 502 may have an input interface and an output interface.
  • the input interface is an interface to which a keyboard, a mouse, etc. are connected and which receives input from a user.
  • the output interface is an interface to which a display device, a printer, and the like are connected, and which outputs the execution result of the program in a format that can be viewed by the operator.
  • the program executed by the computing unit 512 is provided to the server 502 via a removable medium (CD-ROM, flash memory or the like) or the network 504, and is stored in the non-volatile storage unit 513 which is a non-transitory storage medium.
  • the server 502 may have an interface for reading data from removable media.
  • the server 502 is a computer system configured physically on one computer, or on a plurality of logically or physically configured computers, and may operate on multiple threads on the same computer. It may well operate on a virtual computer built on a plurality of physical computer resources.
  • the server 502 executes the authentication process based on the information of the blood vessel image captured by the biometric information extraction terminal 503 in FIGS. 1 to 3, the biometric information extraction terminal 503 is provided with an authentication unit, and the authentication process is performed. It may be executed.
  • FIG. 4 is a diagram showing the configuration of the biological information database 518 of the first embodiment.
  • the biometric information database 518 is a database in which biometric information for authentication is registered, and includes a category 5181, a feature amount 5182, a registration date 5183, an ID 5184, and a quality 5185.
  • the category 5181 indicates a category of registered biometric information.
  • the feature amount 5182 is a feature amount of the registered biometric information.
  • the registration date 5183 is the date when biometric information was registered.
  • the registration date 5183 may include information on the time when biometric information was registered.
  • the ID 5184 is identification information for uniquely identifying a user who has presented biometric information.
  • the quality 5185 is a quality of biometric information registered, and may hold data ranked in a plurality of stages (for example, three stages of good, average, and evil).
  • the biometric information database 518 may store personal information (name, gender, authentication code, etc.) of the user who presented the biometric information in addition to the ID 5184.
  • FIG. 5 is a diagram for explaining an authentication method of the first embodiment.
  • a category corresponding to the position and posture of the finger is prepared in advance, and registration data (blood vessel image) corresponding to the category corresponding to the position and posture of the finger presented at the time of authentication is selected, and a blood vessel image of the presented finger is selected.
  • FIG. 6 is a flowchart of the authentication process of the first embodiment.
  • the control unit 6 detects the finger in step 102, and the light source 10 uses near-infrared light as a finger to capture a blood vessel image.
  • the control value (light quantity) of the initial light source 10 to be irradiated is determined.
  • the imaging unit 4 captures a near infrared image of the presented finger.
  • the control unit 6 detects the position and posture of the finger using the photographed near-infrared image.
  • the position and posture of a finger can be detected by how light strikes the finger.
  • step 105 the control unit 6 determines whether a finger is detected, and if the finger is not detected, the process returns to step 102. On the other hand, if the finger is detected, the light amount for controlling the light source 10 in step 106 based on the detected position and posture of the finger, the luminance information of the photographed finger blood vessel image, etc. Decide. The determined light amount is used to capture the next near-infrared image after it is determined that the authentication has failed in step 114, and the blood vessels of the finger are clearly captured.
  • step 107 the control unit 6 executes a normalization process to correct the magnification and distortion depending on the position and posture of the finger in the photographed blood vessel image.
  • control unit 6 extracts blood vessel characteristics from the finger blood vessel image after normalization processing.
  • the extracted feature amount is transmitted to the server 502.
  • step 109 the category selection unit 514 of the server 502 determines a category in accordance with the detected finger position and posture, and selects one or more categories n corresponding to the detected finger position and posture. One or more categories may be selected in step 109, or all categories may be selected if an appropriate category can not be selected.
  • step 110 the authentication unit 516 of the server 502 collates the feature amount of the blood vessel registered corresponding to the selected category with the feature amount of the extracted blood vessel to calculate a matching score.
  • the data for collation is not registered into the selected category, it collates with the data of the category except selected.
  • step 111 the authentication unit 516 compares the calculated matching score with the predetermined threshold TH1. If the matching score is greater than the threshold TH1, the authentication success post process is executed (step 112), and the authentication process is ended. (Step 113). On the other hand, if the verification score is less than or equal to the threshold TH1, then in step 114, the server 502 determines an authentication timeout. If the predetermined time-out time has not elapsed from the start of the authentication (for example, the imaging of an image), the process returns to step 103 to newly capture a near-infrared image and repeat the authentication process. At this time, a near infrared image is taken under the condition (light quantity) determined in step 106. On the other hand, if the predetermined time-out time has elapsed, the authentication processing is ended as an authentication failure (step 113).
  • distance detection means such as a distance sensor mentioned later and a distance image camera
  • distance detection means photographs distance information at Step 103 at near-infrared image photographing timing.
  • the control unit 6 detects the position and posture of the finger using the acquired distance information. As described above, when the distance information is used, the position and posture of the finger can be detected with high accuracy.
  • FIG. 7 is a diagram for explaining the registration method of the first embodiment.
  • the blood vessel image of the finger taken at the time of authentication is additionally registered in the category corresponding to the position and posture of the finger at the time of authentication, or the registered image is updated.
  • the registration images corresponding to a plurality of categories are not prepared, blood vessel images taken at the time of successful authentication in operation are registered. For this reason, it is not necessary to give the user special instructions for registration, and a highly convenient authentication system can be realized.
  • FIG. 8 is a flowchart of the registration process of the first embodiment.
  • step 201 when the user presents a finger in the opening 3, in step 202, the authentication unit 516 of the server 502 executes an authentication process (for example, an authentication process shown in FIG. 6).
  • step 203 if it is determined in step 202 that authentication has failed, the process returns to step 202.
  • the authentication unit 516 can register the blood vessel image captured at the authentication success based on the blood vessel image acquired at the authentication success or the position and posture at which the finger is presented. Determine the quality. For example, a blood vessel contrast value representing the sharpness of the blood vessel may be calculated from the blood vessel image, and if the contrast value is equal to or greater than a predetermined position value, it may be determined that the blood vessel is clearly captured . In addition, if the amount of blood vessels in the photographed blood vessel image is equal to or more than a predetermined threshold value, it may be determined that the quality can be registered.
  • the blood vessel image based on the brightness (brightness) of the blood vessel image, it may be determined that the blood vessel image that is neither too bright nor too dark is of a registrable quality. Also, based on the result of the authentication process in step 201 (similarity to the data of the person and similarity to the data of others), it is determined that the quality is such that blood vessel images with low false acceptance rate and low false rejection rate can be registered. You may Furthermore, the determination may be made by combining a plurality of conditions described above.
  • step 205 if it is evaluated in step 204 that the quality of the blood vessel image can be registered, the process proceeds to step 206. If the quality can not be registered, the process returns to step 202.
  • step 206 the category creation unit 515 of the server 502 determines whether data is already registered in the category n corresponding to the position and posture of the finger when the certifier has succeeded in the authentication. If the data is already registered in category n, the process proceeds to step 207. If the data is not registered, the category creating unit 515 of the server 502 additionally registers the successfully authenticated blood vessel image in the registration data of category n (step 210), end the registration process (step 211).
  • the category creation unit 515 compares the feature amount of the blood vessel image already registered in the category n with the feature amount of the blood vessel image captured at the time of successful authentication, and determines whether to update the registration. Specifically, when the blood vessel image is not registered in the category n, the feature amount of the photographed blood vessel image is registered. If the quality of the taken blood vessel image is better than the quality of the blood vessel image registered in the category n, the feature amount of the taken blood vessel image is registered and the registration data is updated. Since the registration data is updated according to the seasonality of the living body (for example, expansion and contraction of blood vessels of the finger due to a change in air temperature) by updating the registration data, authentication can be performed with high accuracy.
  • step 208 if the determination result in step 207 is "do not update”, the process returns to step 202 (step 209). On the other hand, if the determination result in step 207 is "update”, in step 210, the category creation unit 515 updates the registration data with the blood vessel image captured at the time of successful authentication, and ends the registration processing in step 211.
  • the category selecting unit 514 acquires the biometric information for authentication based on the auxiliary information including the information on the position and orientation of the living body acquired at the imaging timing of the blood vessel image.
  • the category corresponding to is selected, and the authentication unit 516 compares the registered biometric information of the selected category with the biometric information for authentication, and executes the authentication process. Therefore, high-reliability and high-speed authentication can be performed.
  • biometric information database 518 associates and records the biometric information for authentication with the category corresponding to the biometric information for authentication, it is easy to select a category and it is possible to collate the spine information at high speed.
  • the living body in Example 1 is a finger, and since the living body is small, the position fluctuates greatly, but the posture also fluctuates.
  • the hand since the hand is flat, it is easy to present it horizontally, but since the finger is cylindrical, it may be presented while being rotated about the longitudinal direction of the finger. Therefore, in the first embodiment, in the authentication in which the finger is presented in a non-contact manner, authentication can be performed with higher accuracy than in the related art by selecting a category in consideration of not only positional variations but also posture variations.
  • Example 2 In the present embodiment, as in the first embodiment, biometric information and authentication registered in a category selected from a plurality of categories are performed, but in the case where it is possible to limit the presentation position and presentation posture of the living body in actual operation In the above, a configuration for realizing high-accuracy authentication will be described.
  • FIG. 9 is a diagram for explaining the configuration of the blood vessel image capturing apparatus 2 of the second embodiment.
  • a finger presentation unit 20 for presenting the finger 1 by the user is provided in the opening 3 and the user brings the finger into contact with the finger presentation unit 20 during authentication and registration. It can be presented to restrict the position and posture of the finger. Therefore, in actual operation, it can be expected that many users present fingers at the same position (basic position) and the same posture (basic posture). However, when the number of times of use increases, the frequency at which the finger is presented in a state deviated from the basic position and the basic posture increases, and the frequency of authentication failure increases.
  • the blood vessel feature of the finger blood vessel image obtained by photographing the finger presented in the basic position and the basic posture is registered in the storage device 11 as basic registration data, and at least one of the basic position and the basic posture deviates and is presented. Multiple categories are created to correspond to the blood vessel image of the finger.
  • the blood vessel feature extracted from the blood vessel image of the finger presented by the user is collated with the basic registration data, and further, the registered data of the category according to the position and posture of the presented finger and the extracted blood vessel feature Can be collated, and the result of collation with a plurality of registered data can be integrated to realize highly accurate authentication even when the finger is presented deviating from the basic position and the basic posture.
  • two collations with the basic registration data and with the registration data of the category corresponding to the position and posture of the finger at the time of authentication are performed twice, so collation with the registration data of all categories is performed. It is possible to realize highly accurate authentication with less number of times.
  • only the registered data of the category corresponding to the position and posture of the finger at the time of authentication may be collated.
  • FIG. 10 is a flowchart of the authentication process of the second embodiment.
  • the control unit 6 detects a finger in step 302, and the light source 10 uses near-infrared light as a finger to capture a blood vessel image.
  • the control value (light quantity) of the initial light source 10 to be irradiated is determined.
  • the imaging unit 4 captures a near infrared image of the presented finger.
  • step 304 the control unit 6 detects the position and posture of the finger using the captured near-infrared image.
  • step 305 the control unit 6 determines whether a finger is detected, and if the finger is not detected, the process returns to step 302. On the other hand, if a finger is detected, the light amount for controlling the light source 10 in step 306 based on the detected position and posture of the finger and the luminance information of the photographed finger blood vessel image etc. Decide. The determined light amount is used to capture the next near-infrared image after it is determined in step 317 that the authentication has timed out, and the blood vessels of the finger are clearly captured.
  • step 307 the control unit 6 executes a normalization process to correct the magnification and distortion depending on the position and posture of the finger in the photographed blood vessel image.
  • control unit 6 extracts blood vessel characteristics from the finger blood vessel image after normalization processing.
  • the extracted feature amount is transmitted to the server 502.
  • step 309 the authentication unit 516 of the server 502 collates the extracted blood vessel feature with the basic registration data which is the blood vessel feature of the finger blood vessel image photographed in the state where the finger is presented at the basic position in the basic posture. Then, the matching score 1 is calculated.
  • step 310 the authentication unit 516 compares the calculated matching score 1 with the predetermined threshold value TH1. If the matching score is larger than the threshold value TH1, the post-authentication success process is executed (step 311). The process ends (step 312). On the other hand, if the matching score is less than or equal to the threshold TH1, the category selection unit 514 of the server 502 determines the category according to the detected finger position and posture in step 313, and detects the detected finger position and posture Select the category n corresponding to.
  • step 314 the authentication unit 516 collates the blood vessel feature registered in the selected category n with the blood vessel feature extracted in step 308 to calculate a matching score 2.
  • step 315 the authentication unit 516 compares the calculated matching score 2 with the predetermined threshold value TH2. If the matching score is larger than the threshold value TH2, the post-authentication success process is executed (step 316), and the authentication process is performed. The process ends (step 312). On the other hand, if the verification score is less than or equal to the threshold value TH2, in step 317, the server 502 determines an authentication timeout. If the predetermined time-out time has not elapsed from the start of the authentication (for example, the imaging of an image), the process returns to step 303 to newly capture a near-infrared image and repeat the authentication process. At this time, a near infrared image is taken under the condition (light quantity) determined in step 306. On the other hand, if the predetermined time-out time has elapsed, the authentication processing is ended as an authentication failure (step 312).
  • FIG. 11 is a diagram for explaining a category classification method based on information other than the position and the posture of the finger.
  • the categories are classified based on the presented position and posture of the finger.
  • the difference between the time of registration and authentication depends on the difference between the case where the blood vessels are clearly seen and the case where the blood vessels look unclear due to the expansion or contraction of the blood vessels. It may become large and the authentication accuracy may decline. Therefore, although the photographed finger blood vessel image is registered in the category according to the position and posture of the finger at the time of authentication, as shown in FIG. 11, the degree of coincidence with the basic registration data and registered data of the category based on the position and posture. Is low, the blood vessel image is classified into another category of blurring, and a finger blood vessel image taken at the time of authentication is registered as registration data of the same category.
  • the process of determining the category based on the comparison result with the registered data, and performing verification by comparing the registered data (biometric information) of the determined category may be the same as that of the flowchart of FIG.
  • the difference in blood vessel volume of the finger blood vessel image is calculated by comparison with the basic registration data in step 309, and fluctuations in biological information such as the calculated blood vessel volume difference
  • the category can be determined based on it.
  • the category is determined based on the blood vessel volume of the blood vessel image at the time of authentication as well as the difference between the blood vessel volume of the blood vessel image at the time of registration and authentication, authentication can be performed with high accuracy even when the fluctuation of the blood vessel volume is large. .
  • the category selecting unit 514 corresponds to the category corresponding to the biometric information for authentication based on the information on the position and posture of the living body and the information on the definition of the blood vessel image. It is possible to cope with the fluctuation of the living body due to long-term use. For example, it can follow the condition of the living body and seasonal factors.
  • Example 3 In the first embodiment and the second embodiment, a category for registering biometric information is selected from a plurality of existing categories, but in the present embodiment, the position and posture of the finger pointed by the user at the time of successful authentication are selected. A configuration will be described in which authentication is performed with high accuracy by registering biometric information in a newly created category according to the variation.
  • the authentication process in this embodiment can perform the same process as the flowchart of FIG. 6 of the first embodiment and the flowchart of FIG. 10 of the second embodiment.
  • a new category is created based on the difference between the position and posture of the finger at the time of authentication and the position and posture of the finger at the time of registration, and the authentication succeeds to the category corresponding to the position and posture of the finger at the time of authentication Register blood vessel characteristics at the time.
  • a new category may be created based on the difference in definition of blood vessels between authentication and registration.
  • FIG. 12 is a flowchart of the registration process of the third embodiment.
  • the authentication unit 516 of the server 502 executes an authentication process (for example, the authentication process shown in FIG. 6 and FIG. 10) in step 202.
  • step 403 if it is determined in step 402 that the authentication has failed, the process returns to step 402.
  • the authentication unit 516 can register the blood vessel image captured at the authentication success based on the blood vessel image acquired at the authentication success or the position and posture at which the finger is presented. Determine the quality. For example, a blood vessel contrast value that indicates the sharpness of the blood vessel is calculated from the blood vessel image, and it is determined whether the blood vessel sharpness is of sufficient quality as a registered image used for authentication. Alternatively, the quality may be determined based on the brightness (brightness) of the blood vessel image.
  • step 405 if it is evaluated in step 404 that the quality of the blood vessel image can be registered, the process proceeds to step 406. If the quality can not be registered, the process returns to step 402.
  • the category creation unit 515 of the server 502 calculates the degree of difference between the blood vessel image captured at the time of successful authentication and the blood vessel image registered in the category already defined in the authentication process of step 402. For example, it can be calculated based on the difference between the position or posture at which the finger was presented at the time of successful authentication and the position or posture at which the finger was presented at the time of registration. Also, the degree of difference of the blood vessel image may be calculated using the authentication result. For example, if it is determined that the authentication is successful near the threshold, it is better to register the blood vessel image of the finger presented at the time of authentication in another category.
  • step 407 the category creation unit 515 determines the degree of difference, and if the degree of difference calculated in step 406 is equal to or less than a predetermined threshold TH3, the process returns to step 402. On the other hand, if the calculated degree of difference is larger than the threshold TH3, in step 408, the blood vessel image at the time of authentication is stored in the storage device 11 to be a candidate of an image registered in a new category.
  • the category creation unit 515 determines whether to create a new category. If the degree of similarity of the blood vessel image presented in multiple authentications is high, the user tends to present the blood vessel image captured at the time of authentication. Therefore, if the degree of similarity between the plurality of blood vessel images presented by the user and stored in the storage device 11 is high, a new category is generated. Note that the number of blood vessel images having a high degree of similarity stored in the storage device 11 may be set as a condition for generating a new category. For example, when blood vessel images having a predetermined degree of similarity are stored in the storage device 11 by a predetermined number, a new category may be generated.
  • step 410 if the category is not generated in step 409, the process returns to step 402.
  • the category creating unit 515 is newly created among the plurality of blood vessel images which are candidates registered in the new category and stored in the storage device 11.
  • An image representing a category is selected as additional registration data. For example, among the blood vessel images of the registration candidate, an image having a good quality score may be selected as a representative image.
  • the similarities of blood vessel images of a plurality of registered candidates may be calculated, and an image having a high degree of similarity with another candidate image (at the center of the similar range) may be selected as a representative image.
  • step 412 the category creating unit 515 registers the blood vessel image selected in step 413 in the new category created in step 409, and ends the registration process in step 413.
  • a new category is generated and not only the authenticated biometric information is registered, but as in Example 1, the authenticated biometric information is additionally registered in the already existing category, or the registered biometric information May be updated.
  • the category creating unit 515 acquires the case where the degree of difference between the registered biometric information and the biometric information for authentication is larger than a predetermined value as a result of comparison by the authenticating unit. Since the category corresponding to the auxiliary information is created, the biometric system can be operated with high accuracy without investigating the habits and bias of the user in advance. In addition, since the system learns the habits and biases of the user, the time and effort for management can be reduced.
  • Example 4 in this embodiment, as in the first embodiment, biometric information and authentication registered in a category selected from a plurality of categories are performed, but high in finger blood vessel authentication in which authentication is performed by simultaneously presenting a plurality of fingers.
  • the configuration for authenticating to accuracy is described.
  • the biometric authentication system of the fourth embodiment the same components and functions as those of the above-described embodiment are denoted by the same reference numerals, and the description thereof will be omitted. Also, any of the features of the first to third embodiments may be applied to the fourth embodiment.
  • FIG. 13 is a view showing an example of the blood vessel image photographing apparatus 2 for photographing blood vessel images of a plurality of fingers presented simultaneously.
  • the CPU 7 executes a program stored in the memory 8, and when a plurality of fingers (hands) 1 are presented on the opening 3, the blood vessel image of the plurality of fingers is photographed.
  • the light source 10 is controlled to emit near infrared light to the presented plurality of fingers.
  • the imaging unit 4 arranged below the opening 3 receives the light irradiated and scattered by the finger and receives a blood vessel image.
  • the control unit 6 takes in the photographed blood vessel image and stores it in the memory 8.
  • the CPU 7 collates the feature of the image stored in the memory 8 with the feature of the image stored in advance in the storage device 11 to perform authentication.
  • the distance sensor 12 is provided in the vicinity of the imaging unit 4.
  • the distance sensor 12 is, for example, a distance image camera, and captures a distance image including information on the distance to the presented hand. By using the distance sensor 12, the position and posture of the plurality of presented fingers 1 can be accurately detected.
  • the blood vessel image photographing apparatus 2 shown in FIG. 13 has a high degree of freedom in the position and posture of the finger to be presented, and it is assumed that the finger is presented in various positions and postures when used by many people. If the variation of the position and orientation of the hand presented is large, that is, the difference between the position and orientation of the hand at registration and the position and orientation of the finger at authentication is large, the authentication accuracy decreases. Therefore, as in the first embodiment, blood vessel images are registered in a plurality of categories created according to the position and posture of the finger, and registered data of the category according to the position and posture of the finger presented at the time of authentication are selected. By matching the features of the photographed blood vessel image with the selected registration data, highly accurate authentication is realized. By creating the category according to the position and posture of the finger so that the difference between the categories becomes large, even if the variation of the position and posture of the finger to be presented is large, authentication can be performed with high accuracy.
  • FIG. 14A to 14C are diagrams for explaining an example of the finger presentation position and posture change in the blood vessel image capturing apparatus 2 shown in FIG.
  • FIG. 14A shows an example of the position and posture at which the finger is presented, which is recommended at the time of registration, and the palm is placed on the opening 3 (a transparent member constituting the opening 3).
  • a category corresponding to the position (basic position) or posture (basic posture) at which the finger is presented is defined as a basic category.
  • the blood vessel imaging device 2 shown in FIG. 13 can be authenticated either in a state in which the finger is in contact with the device or in a non-contact state in which the finger is away from the device. Therefore, as shown in FIG. It is good to create a category by finger blood vessel image in.
  • toe may be shown in the state which the hand rotated on the plane of the opening part 3.
  • FIG. 14C it is preferable to create a category from a finger blood vessel image in which the hand is rotated.
  • a category may be created with a finger blood vessel image captured in a state such as bending of the finger and curling of the finger.
  • a category may be created by combining the positions and orientations of a plurality of fingers.
  • the categories may be created in the non-contact state (FIG. 14B) and in the state where the hand is rotated (FIG. 14C).
  • the position and the posture may be determined for each presented finger, the category corresponding to the position and the posture of each finger may be selected, and the registered data may be collated.
  • the finger blood vessel image is photographed multiple times at the time of registration, the similarity between the photographed blood vessel images is calculated, and the calculated similarity is high (similarity range
  • a finger blood vessel image at the center of the image as registration data, a finger blood vessel image having high reproducibility at the time of authentication can be registered, and high-accuracy authentication can be realized.
  • the user presents the finger to the blood vessel image photographing apparatus 2 multiple times at the time of registration, and after registration of the finger blood vessel image is completed, the blood vessel image photographing apparatus 2 used for registration is used. It is possible to perform authentication processing and check if it is correctly registered. A finger blood vessel image that has succeeded in authentication at the time of authentication processing for this registration confirmation may be additionally registered.
  • the blood vessel image is registered in the category corresponding to the position and posture of the finger at the first registration, and at the time of authentication for registration confirmation, the finger is presented with the position and posture of the finger corresponding to a category different from that at the first registration.
  • the finger blood vessel image can be registered in different categories at the time of registration and at the time of additional registration.
  • the user can register blood vessel images in a plurality of categories only by one registration process and the registration confirmation process, so that both high convenience and high authentication accuracy can be achieved.
  • a finger blood vessel image taken in a state where the finger is in contact with the transparent member constituting the opening 3 is registered, and at the time of authentication processing for registration confirmation, the finger is released from the opening 3
  • the finger blood vessel image taken in the non-contact state is additionally registered, and the state in which the finger is in contact with the transparent member constituting the opening 3 and the non-contact in which the finger is released from the opening 3
  • Finger blood vessel images of two categories of states can be registered. In this way, by registering in the two categories of the contact state and the non-contact state, high authentication accuracy is realized when performing authentication in a non-contact state in which many users release their finger from the device in actual operation. it can.
  • the light source 10 for irradiating the living body with light is provided above the living body, and an imaging unit for capturing a blood vessel image by the light emitted from the light source 10 and transmitted through the living body Since 4 is provided below the living body, when a plurality of fingers (hands) are presented, the plurality of fingers can be photographed simultaneously, and a category can be selected for each finger and collated with registered data.
  • a walk-through type biometric authentication system can be constructed, and highly convenient biometric authentication can be provided.
  • Example 5 In this embodiment, as in the first embodiment, biometric information and authentication registered in a category selected from a plurality of categories are performed, but the environment around recognition is recognized and the environment around the recognition is recognized. Create categories and register biometric information. At the time of authentication, a configuration will be described in which authentication is performed with high accuracy by authentication collating with biometric information registered in a category corresponding to the surrounding environment.
  • the same components and functions as those of the above-described embodiment are denoted by the same reference numerals, and the description thereof will be omitted. Also, any of the features of the first to third embodiments may be applied to the fifth embodiment.
  • the authentication process and the registration process can be performed in the same manner as the first to third embodiments described above.
  • it recognizes surrounding environment such as ambient light of a region other than the living body in the captured image, and biological information registered in the category corresponding to the recognized surrounding environment, and presented biological information To authenticate the user.
  • surrounding environment such as ambient light of a region other than the living body in the captured image
  • biological information registered in the category corresponding to the recognized surrounding environment and presented biological information To authenticate the user.
  • luminance information of the near-infrared image at the timing before or after authentication or at the time of authentication is used to recognize the surrounding environment such as ambient light of an area other than the living body in the captured image. If there is a large difference between the recognized ambient environment and the ambient environment at the time of registration, a category different from the category (ambient environment category) corresponding to the ambient environment at the time of registration is newly created. If the authentication is successful and the ambient environment category at the time of authentication is different from the ambient environment category at the time of registration, biometric information acquired at the time of authentication is registered in a new ambient environment category.
  • the category selecting unit 514 corresponds to the biometric information for authentication based on the background information extracted from the area other than the living body in the captured image. Since the category is selected, authentication can be performed with high accuracy in a biometric authentication system using reflected light. In addition, since biometric information is registered in different categories depending on the environment of the place where authentication is performed, authentication can be performed with high accuracy. For example, by applying to a smartphone or a tablet terminal, highly accurate biometric authentication can be performed without providing a biometric sensor for detecting a fingerprint.
  • biometric authentication system In the biometric authentication system according to the fifth embodiment, high-accuracy authentication can be performed with light of various altitudes and wavelengths, and therefore, it is not necessary to provide a light source dedicated to biometric authentication.
  • the present invention is not limited to the embodiments described above, and includes various modifications and equivalent configurations within the scope of the appended claims.
  • the embodiments described above are described in detail to explain the present invention in an easy-to-understand manner, and the present invention is not necessarily limited to those having all the configurations described.
  • part of the configuration of one embodiment may be replaced with the configuration of another embodiment.
  • the configuration of another embodiment may be added to the configuration of one embodiment.
  • another configuration may be added, deleted, or replaced.
  • each configuration, function, processing unit, processing means, etc. described above may be realized by hardware, for example, by designing part or all of them with an integrated circuit, etc., and the processor realizes the respective functions. It may be realized by software by interpreting and executing the program to
  • Information such as a program, a table, and a file for realizing each function can be stored in a memory, a hard disk, a storage device such as a solid state drive (SSD), or a recording medium such as an IC card, an SD card, or a DVD.
  • SSD solid state drive
  • control lines and information lines indicate what is considered to be necessary for explanation, and not all control lines and information lines necessary for mounting are shown. In practice, it can be considered that almost all configurations are mutually connected.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Computer Security & Cryptography (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Hardware Design (AREA)
  • Software Systems (AREA)
  • Vascular Medicine (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Collating Specific Patterns (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Image Input (AREA)
PCT/JP2018/033656 2017-12-27 2018-09-11 生体認証システム Ceased WO2019130670A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201880048838.4A CN110945520B (zh) 2017-12-27 2018-09-11 生物体认证系统
US16/640,663 US11113493B2 (en) 2017-12-27 2018-09-11 Biometric authentication system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2017-252194 2017-12-27
JP2017252194A JP6751072B2 (ja) 2017-12-27 2017-12-27 生体認証システム

Publications (1)

Publication Number Publication Date
WO2019130670A1 true WO2019130670A1 (ja) 2019-07-04

Family

ID=67066989

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/033656 Ceased WO2019130670A1 (ja) 2017-12-27 2018-09-11 生体認証システム

Country Status (4)

Country Link
US (1) US11113493B2 (https=)
JP (1) JP6751072B2 (https=)
CN (1) CN110945520B (https=)
WO (1) WO2019130670A1 (https=)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10346852B2 (en) 2016-02-19 2019-07-09 Alitheon, Inc. Preserving authentication under item change
US10740767B2 (en) 2016-06-28 2020-08-11 Alitheon, Inc. Centralized databases storing digital fingerprints of objects for collaborative authentication
KR20190098795A (ko) * 2018-01-30 2019-08-23 엘지전자 주식회사 차량 단말기 및 그것을 포함하는 운송 시스템의 제어방법
WO2020070590A1 (ja) * 2018-10-05 2020-04-09 株式会社半導体エネルギー研究所 認証システム、認証システムを用いた解錠履歴の記録方法
US10963670B2 (en) 2019-02-06 2021-03-30 Alitheon, Inc. Object change detection and measurement using digital fingerprints
EP3734506A1 (en) * 2019-05-02 2020-11-04 Alitheon, Inc. Automated authentication region localization and capture
EP3736717A1 (en) 2019-05-10 2020-11-11 Alitheon, Inc. Loop chain digital fingerprint method and system
US11238146B2 (en) 2019-10-17 2022-02-01 Alitheon, Inc. Securing composite objects using digital fingerprints
JP7399727B2 (ja) * 2020-01-30 2023-12-18 株式会社東芝 認証デバイスおよび認証システム
JP7668159B2 (ja) * 2021-05-27 2025-04-24 株式会社日立製作所 人特定システム
CN115438703B (zh) * 2022-10-24 2023-04-07 广州河东科技有限公司 一种智能家居生物识别系统及识别方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010079448A (ja) * 2008-09-24 2010-04-08 Hitachi Software Eng Co Ltd 指静脈認証システム
JP2010250466A (ja) * 2009-04-14 2010-11-04 Hitachi Ltd 個人認証装置
US20110304720A1 (en) * 2010-06-10 2011-12-15 The Hong Kong Polytechnic University Method and apparatus for personal identification using finger imaging
JP2014016822A (ja) * 2012-07-09 2014-01-30 Canon Inc 画像処理装置及びその制御方法、プログラム
JP2015106386A (ja) * 2013-12-02 2015-06-08 富士通株式会社 生体情報抽出装置、生体情報抽出方法、および生体情報抽出プログラム
WO2017004464A1 (en) * 2015-06-30 2017-01-05 Nec Corporation Of America Facial recognition system

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5110983B2 (ja) * 2007-06-29 2012-12-26 日立オムロンターミナルソリューションズ株式会社 生体認証処理システム
EP2444933B1 (en) * 2009-06-17 2019-07-10 Fujitsu Limited Biometric authentication device, biometric authentication method and computer program for biometric authentication
WO2011030441A1 (ja) * 2009-09-11 2011-03-17 富士通株式会社 生体認証装置、生体認証システム、及び生体認証方法
US9076027B2 (en) * 2009-11-17 2015-07-07 Hitachi Industry & Control Colutions, Ltd. Authentication system using biometric information and authentication device
JP5249273B2 (ja) * 2010-03-25 2013-07-31 パナソニック株式会社 生体情報計測システム
JP5809792B2 (ja) * 2010-11-04 2015-11-11 株式会社日立製作所 生体認証装置および方法
JP5690556B2 (ja) * 2010-11-12 2015-03-25 株式会社 日立産業制御ソリューションズ 個人認証装置
JP5919944B2 (ja) * 2012-03-27 2016-05-18 富士通株式会社 非接触生体認証装置
CN103500337B (zh) * 2013-09-30 2018-10-09 上海合合信息科技发展有限公司 用于智能无线通信终端的识别四边形边框的方法及装置
CN103996055B (zh) * 2014-06-13 2017-06-09 上海珉智信息科技有限公司 基于影像档案电子资料识别系统中分类器的识别方法
EP3392824A4 (en) * 2015-12-18 2019-10-23 Hitachi, Ltd. DEVICE AND SYSTEM FOR BIOMETRIC AUTHENTICATION
CN105895096A (zh) * 2016-03-30 2016-08-24 乐视控股（北京）有限公司 一种身份识别与语音交互操作的方法及装置
CN106775346A (zh) * 2016-11-23 2017-05-31 广州日滨科技发展有限公司 一种手指图像识别的方法及装置
CN107463608A (zh) * 2017-06-20 2017-12-12 上海汇尔通信息技术有限公司 一种基于人脸识别的信息推送方法及系统
CN107358232B (zh) * 2017-06-28 2020-12-29 中山大学新华学院 基于插件的发票识别方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010079448A (ja) * 2008-09-24 2010-04-08 Hitachi Software Eng Co Ltd 指静脈認証システム
JP2010250466A (ja) * 2009-04-14 2010-11-04 Hitachi Ltd 個人認証装置
US20110304720A1 (en) * 2010-06-10 2011-12-15 The Hong Kong Polytechnic University Method and apparatus for personal identification using finger imaging
JP2014016822A (ja) * 2012-07-09 2014-01-30 Canon Inc 画像処理装置及びその制御方法、プログラム
JP2015106386A (ja) * 2013-12-02 2015-06-08 富士通株式会社 生体情報抽出装置、生体情報抽出方法、および生体情報抽出プログラム
WO2017004464A1 (en) * 2015-06-30 2017-01-05 Nec Corporation Of America Facial recognition system

Also Published As

Publication number Publication date
US11113493B2 (en) 2021-09-07
US20200356751A1 (en) 2020-11-12
CN110945520A (zh) 2020-03-31
JP2019117579A (ja) 2019-07-18
CN110945520B (zh) 2023-12-19
JP6751072B2 (ja) 2020-09-02

Similar Documents

Publication Publication Date Title
JP6751072B2 (ja) 生体認証システム
US12223760B2 (en) Systems and methods for performing fingerprint based user authentication using imagery captured using mobile devices
JP5671607B2 (ja) 生体認証装置、生体認証システム、および生体認証方法
CN110326001B (zh) 使用利用移动设备捕捉的图像执行基于指纹的用户认证的系统和方法
US9361507B1 (en) Systems and methods for performing fingerprint based user authentication using imagery captured using mobile devices
KR100944172B1 (ko) 생체 인증 방법 및 생체 인증 시스템
JP6089610B2 (ja) 生体認証装置、生体認証方法及び生体認証用コンピュータプログラム
JP2023150898A (ja) 認証システム及び認証方法
JP6798285B2 (ja) 生体認証装置、生体認証方法及びプログラム
HK40069201B (zh) 执行指纹识别的方法和系统
HK1246928A1 (en) Systems and methods for performing fingerprint based user authentication using imagery captured using mobile devices
HK1246928B (en) Systems and methods for performing fingerprint based user authentication using imagery captured using mobile devices

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18893644

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18893644

Country of ref document: EP

Kind code of ref document: A1