WO2020022597A1 - Apparatus for controlling fingerprint registration and fingerprint authentication, and method of driving the same - Google Patents

Apparatus for controlling fingerprint registration and fingerprint authentication, and method of driving the same Download PDF

Info

Publication number
WO2020022597A1
WO2020022597A1 PCT/KR2019/000985 KR2019000985W WO2020022597A1 WO 2020022597 A1 WO2020022597 A1 WO 2020022597A1 KR 2019000985 W KR2019000985 W KR 2019000985W WO 2020022597 A1 WO2020022597 A1 WO 2020022597A1
Authority
WO
WIPO (PCT)
Prior art keywords
fingerprint
minutiae information
information
minutiae
registration
Prior art date
Application number
PCT/KR2019/000985
Other languages
French (fr)
Inventor
Seung Jin Lee
Sangrok Lee
Sung Il Hong
Original Assignee
Btbl Co., 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 Btbl Co., Ltd filed Critical Btbl Co., Ltd
Publication of WO2020022597A1 publication Critical patent/WO2020022597A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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
    • G06V40/1347—Preprocessing; Feature extraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06V40/1365—Matching; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06V40/1365—Matching; Classification
    • G06V40/1371—Matching features related to minutiae or pores
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/08—Key distribution or management, e.g. generation, sharing or updating, of cryptographic keys or passwords
    • H04L9/0894—Escrow, recovery or storing of secret information, e.g. secret key escrow or cryptographic key storage
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/14—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols using a plurality of keys or algorithms
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
    • H04L9/3226—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using a predetermined code, e.g. password, passphrase or PIN
    • H04L9/3231—Biological data, e.g. fingerprint, voice or retina
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2221/00—Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F2221/21—Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F2221/2117—User registration

Definitions

  • the present invention relates to a fingerprint recognition technology, and more particularly, to an apparatus for controlling fingerprint registration and fingerprint authentication, which as a fingerprint image is scanned by a fingerprint sensor, generates N' th fingerprint minutiae (features) information by using integrated fingerprint minutiae information including only non-redundant fingerprint minutiae information from fingerprint minutiae information that has been extracted N times, registers the N' th fingerprint minutiae information for one identifier (ID), calculates a similarity between fingerprint minutiae information extracted from a fingerprint image scanned for authentication and the N' th fingerprint minutiae information, and if the similarity is larger than a predetermined specific value, authenticates the scanned fingerprint image, and a method of driving the apparatus.
  • N' th fingerprint minutiae features
  • Fingerprint recognition which has widely been used in the field of biometrics, started at the time when N Grew found out that humans have different fingerprints in the UK in 1684, and was first used for commercial purposes in a Wall Street sticks firm in the US in 1968.
  • a person's fingerprints are kept unchanged until the end of the person's life. Even though a fingerprint is scratched in view of an external factor, the fingerprint is soon recovered to the original shape, and the probability of a person having an identical fingerprint to that of another person is only 1/1,000,000,000.
  • Fingerprint recognition is a user identification technique of electronically reading a user's finger on the basis of the above fingerprint property, comparing the reading with pre-input data, and thus identifying the user by the comparison. While fingerprint recognition has been applied to the fields of identification, control of physical access to a safe and an entrance control system, crime investigation to find criminals, etc., fingerprint recognition has also been used as a security system for security and authentication in electronic transactions since the 1990s.
  • fingerprint sensors have been getting smaller and more integrated, and have found their applications in a wide range such as electronic transactions.
  • fingerprint recognition has also been adopted for portable phones, personal digital assistant (PDA) terminals, etc.
  • fingerprint recognition techniques are divided into image-based fingerprint recognition and feature-based fingerprint recognition.
  • Feature-based fingerprint recognition is widely used, including minutiae extraction and matching.
  • the spatial characteristics of extracted minutiae are used by applying many image processing techniques such as flattening, separation of foreground and background, binarization, and thinning.
  • feature-based fingerprint recognition methods compare a fingerprint for authentication with a registered fingerprint by using minutiae, mostly checking the similarity between corresponding minutiae.
  • a fingerprint recognition algorithm adopted in a smartphone equipped with a fingerprint sensor or an existing fingerprint sensor-related product separately performs fingerprint registration and fingerprint authentication.
  • fingerprint registration the fingerprint of the same finger is scanned at least four times up to ten times in order to reduce a false rejection ratio (FRR), and the minutiae of the extracted fingerprints are registered for one ID.
  • FRR false rejection ratio
  • the fingerprints of two or more different fingers may problematically be registered for one ID.
  • registration of the fingerprints of another person's plural fingers for one ID may cause the fatal problem that an unauthorized user can be authenticated.
  • an apparatus for controlling fingerprint registration and fingerprint authentication, and a method of driving the same have been devised in view of the above problems, and an aspect of the present invention is to enable successful registration of only a fingerprint of an authorized user, and thus allow only the authorized user to use a smartphone, a laptop computer, or other devices which have a fingerprint sensor therein, during fingerprint registration and authentication on the smartphone, the laptop computer, or the other devices by generating N' th fingerprint minutiae information, using integrated fingerprint minutiae information including only non-redundant fingerprint minutiae information from fingerprint minutiae information extracted N times along with scanning of a fingerprint image by the fingerprint sensor, registering the N' th fingerprint minutiae information for one ID, calculating a similarity between fingerprint minutiae information extracted from a scanned fingerprint image and the N' th minutiae information, and authenticating the scanned fingerprint image, if the similarity is larger than a predetermined specific value.
  • the present invention includes the following constructions.
  • an apparatus for controlling fingerprint registration and fingerprint authentication includes a similarity check and computation unit configured to perform fingerprint registration in conjunction with fingerprint authentication through a fingerprint sensor, without separating the fingerprint registration from the fingerprint authentication, and to calculate a similarity between first fingerprint minutiae information extracted from a first fingerprint image scanned a first time and N th fingerprint minutiae information extracted from an N th fingerprint image scanned an N th time, during fingerprint registration of a selected one of fingers, and a fingerprint registration and authentication controller configured to, if the calculated similarity between the first fingerprint minutiae information and the N th fingerprint minutiae information is larger than a predetermined specific value, generate N' th fingerprint minutiae information by detecting minutiae information unique to the N th fingerprint minutiae information, and reflecting the detected minutiae information in the first fingerprint minutiae information, and to register the N' th fingerprint minutiae information for one identifier (ID), instead of the first fingerprint minutiae information.
  • ID identifier
  • the similarity check and computation unit is configured to calculate a similarity between the N' th fingerprint minutiae information, instead of the first fingerprint minutiae information, and (N+1) th fingerprint minutiae information extracted from an (N+1) th fingerprint image scanned an (N+1) th time.
  • a method of controlling an apparatus for controlling fingerprint registration and fingerprint authentication includes performing fingerprint registration in conjunction with fingerprint authentication through a fingerprint sensor, without separating the fingerprint registration from the fingerprint authentication by a similarity check and computation unit, calculating a similarity between first fingerprint minutiae information extracted from a first fingerprint image scanned a first time and N th fingerprint minutiae information extracted from an N th fingerprint image scanned an N th time, during fingerprint registration of a selected one of fingers, by the similarity check and computation unit, generating N' th fingerprint minutiae information by detecting minutiae information unique to the N th fingerprint minutiae information, and reflecting the detected minutiae information in the first fingerprint minutiae information, by a fingerprint registration and authentication controller, if the calculated similarity between the first fingerprint minutiae information and the N th fingerprint minutiae information is larger than a predetermined specific value, and registering the N 'th fingerprint minutiae information for one identifier (ID), instead of the
  • the apparatus for controlling fingerprint registration and fingerprint authentication, and the method of driving the same have a first effect of enabling successful recognition of only a fingerprint of an authorized user, and thus allow only the authorized user to use a smartphone, a laptop computer, or other devices which have a fingerprint sensor therein, during fingerprint registration and authentication on the smartphone, the laptop computer, or the other devices by generating N' th fingerprint minutiae information, using integrated fingerprint minutiae information including only non-redundant fingerprint minutiae information from fingerprint minutiae information extracted N times along with scanning of a fingerprint image by the fingerprint sensor, registering the N' th fingerprint minutiae information for one ID, calculating a similarity between fingerprint minutiae information extracted from a scanned fingerprint image and the N' th minutiae information, and authenticating the scanned fingerprint image, if the similarity is larger than a predetermined specific value.
  • the present invention has a second effect of overcoming the shortcoming that since correlations between scanned fingerprints are generally not checked during registration of fingerprint minutiae extracted from fingerprint images of the same finger scanned at least four times up to ten times, two or more different fingerprints can be registered for one ID.
  • the present invention has a third effect of eliminating the problem that possible registration of fingerprints of two or more other persons for one ID leads to malicious system use of an unauthorized person in a system that enhances security by fingerprint recognition.
  • FIG. 1 is a block diagram illustrating an apparatus for controlling fingerprint registration and fingerprint authentication according to an embodiment of the present invention.
  • FIG. 2 is a flowchart illustrating a method of driving an apparatus for controlling fingerprint registration and fingerprint authentication according to an embodiment of the present invention.
  • FIG. 3 is a view referred to for describing a conventional fingerprint registration and authentication method.
  • FIG. 4 is a view referred to for describing a method of storing fingerprint minutiae information by calculating similarities among a plurality of fingerprint images during conventional fingerprint registration.
  • FIG. 5 is a view referred to for describing a problem encountered with registration of a fingerprint image by calculating similarities among fingerprint images during conventional fingerprint registration.
  • FIG. 6 is another view referred to for describing a problem encountered with registration of a fingerprint image by calculating similarities among fingerprint images during conventional fingerprint registration.
  • FIG. 7 is a detailed flowchart illustrating an operation of registering a fingerprint image in the method of driving an apparatus for controlling fingerprint registration and fingerprint authentication according to an embodiment of the present invention.
  • FIG. 8 is another detailed flowchart illustrating an operation of registering a fingerprint image in the method of driving an apparatus for controlling fingerprint registration and fingerprint authentication according to another embodiment of the present invention.
  • FIG. 9 is another detailed flowchart illustrating an operation of registering a fingerprint image in the method of driving an apparatus for controlling fingerprint registration and fingerprint authentication according to another embodiment of the present invention.
  • FIG. 10 is another detailed flowchart illustrating an operation of registering a fingerprint image in the method of driving an apparatus for controlling fingerprint registration and fingerprint authentication according to another embodiment of the present invention.
  • FIG. 1 is a block diagram illustrating an apparatus for controlling fingerprint registration and fingerprint authentication according to an embodiment of the present invention.
  • an apparatus 1000 for controlling fingerprint registration and fingerprint authentication generates N' th fingerprint minutiae information, using integrated fingerprint minutiae information including only non-redundant fingerprint minutiae information from fingerprint minutiae information extracted N times, registers the N' th fingerprint minutiae information for one identifier (ID), calculates a similarity between fingerprint minutiae information extracted from a fingerprint image scanned for authentication and the N' th fingerprint minutiae information, and if the similarity is larger than a predetermined specific value, authenticates the scanned fingerprint image.
  • the apparatus 1000 for controlling fingerprint registration and fingerprint authentication includes a similarity check and computation unit 100, a data set storage 200, and a fingerprint registration and authentication controller 300.
  • a scanned image is flattened, information such as the positions and directions of an ending that defines the end of a ridge line flow, and a bifurcation defined as a point in the ridge where the line is separated into two branches, the type of a minutia, and so on is extracted by subjecting the flattened image to various image processes including foreground and background separation, binarization, and thinning.
  • minutiae data having the following four parameters is extracted:
  • x represents an x-axis coordinate
  • y represents a y-axis coordinate
  • ⁇ represents the direction of a minutia
  • T represents the type of the minutia, which is set to 0 to indicate ending, and to 1 to indicate bifurcation.
  • the similarity check and computation unit 100 may check the similarity between two fingerprints by using a clique model made up of the radius of a circle circumscribed around three adjacent minutiae, the maximum ⁇ of the included angles of three vertices, an included angle ⁇ in a clockwise direction from ⁇ , the directions ⁇ a, ⁇ b and ⁇ c of the respective minutiae, and the types of Ta, Tb and Tc of the respective minutiae, in an extracted minutiae set.
  • the similarity check and computation unit 100 makes up lists in which clique data are appropriately ordered on the basis of the radius of a circumscribed circle, a maximum included angle, or the like by using minutiae of two fingerprints to be compared, and searches the two lists for matching cliques.
  • the similarity check and computation unit 100 may obtain two superimposed fingerprints by calculating rotation and shift amounts between two images by the matching cliques, and shifting the two fingerprints to the same coordinate system, detect corresponding minutiae in the superimposed fingerprints, and subject the detected minutiae to matching, thereby calculating the similarity.
  • the apparatus 1000 for controlling fingerprint registration and fingerprint authentication performs registration in conjunction with authentication through a fingerprint sensor, without separating the registration from the authentication.
  • fingerprint registration the similarity between first fingerprint minutiae information extracted from an initial scanned fingerprint image and second fingerprint minutiae information extracted from a second scanned fingerprint image. If the similarity is larger than a predetermined specific value, minutiae information unique to the second fingerprint minutiae information is detected and reflected in the first fingerprint minutiae information, thus producing 2' nd fingerprint minutiae information.
  • the 2' nd fingerprint minutiae information is registered for one ID.
  • the apparatus 1000 for controlling fingerprint registration and fingerprint authentication calculates the similarity between N' th fingerprint minutiae information and (N+1) th fingerprint minutiae information of a newly scanned (N+1) th fingerprint image during fingerprint registration.
  • the apparatus 1000 for controlling fingerprint registration and fingerprint authentication detects minutiae information unique to the (N+1) th fingerprint minutiae information and reflects the unique minutiae information in the N' th fingerprint minutiae information, thus producing (N+1)' th fingerprint minutiae information.
  • the apparatus 1000 for controlling fingerprint registration and fingerprint authentication newly registers an improved data set including the (N+1)' th fingerprint minutiae information for the same ID, instead of the N' th fingerprint minutiae information.
  • the pre-registered (N' th ) fingerprint minutiae information is replaced with the (N+1)' th fingerprint minutiae information, and stored in the improved data set.
  • the fingerprint minutiae information of a fingerprint image to be authenticated matches pre-registered fingerprint minutiae information due to the similarity between the fingerprint minutiae information equal to or larger than a predetermined ratio, only non-redundant fingerprint minutiae information of the new fingerprint minutiae information with respect to a plurality of pieces of pre-registered minutiae information is additionally registered for a matching ID.
  • the apparatus 1000 for controlling fingerprint registration and fingerprint authentication compares the first fingerprint minutiae information or the pre-registered N' th fingerprint minutiae information in the improved data set with fingerprint minutiae information extracted from a new scanned image. If the similarity between the fingerprint minutiae information is equal to or less than a predetermined specific value, or equal to or larger than a predetermined specific value, the apparatus 1000 for controlling fingerprint registration and fingerprint authentication eliminates the fingerprint minutiae of the new scanned image. If the similarity is too low, this may mean different fingerprint images, and if the similarity is too high, most minutiae are identical and thus not many minutiae need to be added.
  • the apparatus 1000 for controlling fingerprint registration and fingerprint authentication reflects and stores a new scanned fingerprint image with a similarity within a predetermined range, and non-redundant fingerprint minutiae of fingerprint minutiae information extracted from the new scanned fingerprint image in the improved data set, and registers the minutiae information for one ID.
  • the apparatus 1000 for controlling fingerprint registration and fingerprint authentication performs the foregoing operations by means of components described below.
  • the similarity check and computation unit 100 performs fingerprint registration in conjunction with fingerprint authentication through the fingerprint sensor, without separating the fingerprint registration from the fingerprint authentication. During fingerprint registration of a selected one of fingers, the similarity check and computation unit 100 calculates the similarity between first fingerprint minutiae information extracted from a first fingerprint image scanned initially and N th fingerprint minutiae information extracted from an N th fingerprint image scanned an N th time.
  • the data set storage 200 initially stores the first fingerprint minutiae information for one ID, replaces the first fingerprint minutiae information with N' th fingerprint minutiae information obtained through N modifications, and stores the N' th fingerprint minutiae information for the same ID.
  • the similarity check and computation unit 100 calculates the similarity between the N' th fingerprint minutiae information, instead of the first fingerprint minutiae information extracted from the first fingerprint image, and (N+1) th fingerprint minutiae information extracted from an (N+1) th scanned fingerprint image.
  • the fingerprint registration and authentication controller 300 detects minutiae information unique to the N th fingerprint minutiae information, and reflects the unique minutiae information in the first fingerprint image, thereby producing the N' th fingerprint minutiae information.
  • the fingerprint registration and authentication controller 300 registers the N' th fingerprint minutiae information for the one ID, instead of the first fingerprint minutiae information.
  • the fingerprint registration and authentication controller 300 performs fingerprint authentication, using the stored the N' th fingerprint minutiae information.
  • the fingerprint registration and authentication controller 300 may reinforce the security of personal information by encrypting fingerprint minutiae information by an encryption algorithm such as advanced encryption standard (AES), data encryption standard (DES), SEED, ARIA, or the like, storing the encrypted fingerprint minutiae information, decrypting the stored fingerprint minutiae information by the encryption algorithm such as AES, DES, SEED, ARIA, or the like, and using the decrypted fingerprint minutiae information.
  • AES advanced encryption standard
  • DES data encryption standard
  • SEED SEED
  • ARIA advanced encryption standard
  • the similarity check and computation unit 100 compares the fingerprint minutiae of the two fingerprint areas.
  • a similarity is a ratio between the number of matching minutiae and the number of non-matching minutiae during comparison between the minutiae of two fingerprints.
  • a mere exemplary threshold value such as a similarity of 60% or 70% may be set or changed appropriately under circumstances.
  • FIG. 2 is a flowchart illustrating a method of driving an apparatus for controlling fingerprint registration and fingerprint authentication according to an embodiment of the present invention.
  • an improved data set which has been obtained by removing redundant minutiae information in a source data set including fingerprint minutiae information extracted from the scanned fingerprint images, or at least one piece of fingerprint minutiae information, is registered for one ID.
  • a similarity check and computation unit performs fingerprint registration in conjunction with fingerprint authentication through a fingerprint sensor without separating the fingerprint registration from the fingerprint authentication (S100).
  • the similarity check and computation unit calculates the similarity between first fingerprint minutiae information extracted from an initially scanned first fingerprint image and N th fingerprint minutiae information extracted from an N th scanned fingerprint image (S200 and S300).
  • a fingerprint registration and authentication controller If the similarity between the first fingerprint minutiae information and the N th fingerprint minutiae information is larger than a predetermined specific value, a fingerprint registration and authentication controller generates N' th fingerprint minutiae information by detecting minutiae information unique to the N th fingerprint minutiae information, and reflecting the detected minutiae information in the first fingerprint minutiae information (S400).
  • the fingerprint registration and authentication controller registers the N' th fingerprint minutiae information for one ID, instead of the first fingerprint image and the first fingerprint minutiae information (S500).
  • the similarity check and computation unit calculates the similarity between the N' th fingerprint information extracted from the N' th fingerprint image (instead of the first fingerprint minutiae information extracted from the first fingerprint image) and (N+1) th fingerprint minutiae information of the afore-mentioned (N+1) th fingerprint image.
  • the fingerprint registration and authentication controller performs fingerprint authentication, using the N' th fingerprint minutiae information.
  • FIGS. 3 and 4 illustrate conventional technologies relating to fingerprint registration and fingerprint authentication.
  • fingerprint minutiae are registered for one ID.
  • Fingerprint minutiae stored in the resulting database are compared with fingerprint minutiae extracted from a scanned image, to thereby determine whether the minutiae of the two fingerprints are identical.
  • an integrated fingerprint minutiae set is generated by using fingerprint images with high similarities from among a plurality of fingerprint images through fingerprint authentication.
  • the integrated fingerprint minutiae set is stored for one ID, and used for fingerprint authentication. More specifically, fingerprint minutiae sets are extracted from a plurality of scanned fingerprint images, and similarities between the fingerprint minutiae sets are calculated.
  • a single integrated fingerprint minutiae set is produced by removing redundant fingerprint minutiae in fingerprint minutiae sets with similarities within a predetermined range, and stored for one ID.
  • the method of producing one integrated fingerprint minutia set simply by selecting only fingerprint images with similarities within a predetermined range, and storing the integrated fingerprint minutia set has limitations in its effectiveness in perfectly preventing a malicious user from registering fingerprint images of a plurality of fingers for one ID, and using the ID.
  • the conventional fingerprint registration and authentication method for calculating similarities between multiple images and accordingly registering fingerprints can prevent a malicious user from registering fingerprint images of a plurality of fingers for one ID in the case illustrated in FIG. 5.
  • a first fingerprint image among fingerprint images is obtained by scanning finger A, and second to fourth fingerprint images are obtained by scanning finger B, as illustrated in FIG. 5.
  • an average similarity S3 between the third fingerprint and the other fingerprints is 50.6%
  • an average similarity S4 between the fourth fingerprint and the other fingerprints is 51.3%. If a fingerprint with an average similarity equal to or less than 10% is to be removed, the fingerprint image of finger A is removed, and fingerprint minutiae are extracted only from the fingerprint images of finger B. Then, an integrated data set is configured by removing redundant minutiae in the extracted fingerprint minutiae. Thus, only the fingerprint images of one finger may be registered, thereby preventing a malicious user from registering fingerprint images of a plurality of fingers for one ID. However, despite the advantage of preventing registration of fingerprints of a plurality of fingers, this method cannot select and register a specific one of the fingerprint images of finger A and finger B.
  • the conventional fingerprint registration and authentication method for calculating similarities among multiple fingerprint images and accordingly registering fingerprints cannot prevent a malicious user from registering fingerprint images of a plurality of fingers for one ID in the case illustrated in FIG. 6.
  • first and third fingerprint images among fingerprint images are obtained by scanning finger A, and second and fourth fingerprint images are obtained by scanning finger B. If fingerprint minutiae are extracted from the respective fingerprint images and similarities among the fingerprint minutiae are calculated, the similarities are all close. Therefore, it is difficult to selectively remove fingerprints with similarities equal to or less than a specific value or equal to or larger than a specific value.
  • the first fingerprint image has an average similarity S1 of 25.6%.
  • FIG. 7 is a detailed flowchart illustrating a fingerprint registration and fingerprint authentication method according to an embodiment of the present invention.
  • fingerprint registration the image quality state of an initially scanned first fingerprint image is checked. If the image quality state is good, first fingerprint minutiae information is extracted from the first fingerprint image, and stored for one ID in a database.
  • a second fingerprint image is scanned, and the image quality state of the second fingerprint image is checked. If the image quality state is good, second fingerprint minutiae information is extracted from the second fingerprint image. The similarity between the extracted second fingerprint minutiae information and the minutiae information stored in the database is calculated. If the similarity is larger than a predetermined specific value (60%), minutiae information unique to the second fingerprint minutiae information is detected and reflected in the first fingerprint minutiae information, thereby producing 2' nd fingerprint minutiae information. The 2' nd fingerprint minutiae information is stored for the same ID in the database.
  • the similarity between third fingerprint minutiae information extracted from a third fingerprint image and the 2' nd fingerprint minutiae information is calculated. If the similarity is larger than the predetermined specific value (60%), minutiae information unique to the third fingerprint minutiae information is detected and reflected in the 2' nd fingerprint minutiae information, thereby producing 3' rd fingerprint minutiae information.
  • the 3' rd fingerprint minutiae information is stored for the same ID in the database.
  • N' th fingerprint minutiae information generated finally by repeating the above operation N times is stored for the same ID in the database, thereby completing the fingerprint registration.
  • a fingerprint image is scanned, and the image quality state of the fingerprint image is checked. If the image quality state is good, fingerprint minutiae information is extracted from the fingerprint image, and the similarity between the extracted fingerprint minutiae information and the fingerprint minutiae information stored in the database. If the similarity is larger than a predetermined specific value (70%), it is determined that the fingerprints match.
  • FIG. 8 is a flowchart illustrating a fingerprint registration and authentication method according to another embodiment of the present invention.
  • the image quality state of an initially scanned first fingerprint image is checked. If the image quality state is good, first fingerprint minutiae information is extracted from the first fingerprint image.
  • a second fingerprint image is scanned, and the image quality state of the second fingerprint image is checked. If the image quality state is good, second fingerprint minutiae information is extracted from the second fingerprint image. The similarity between the extracted second fingerprint minutiae information and the first minutiae information is calculated. If the similarity is larger than a predetermined specific value (60%), minutiae information unique to the second fingerprint minutiae information is detected and reflected in the first fingerprint minutiae information, thereby producing 2' nd fingerprint minutiae information. The 2' nd fingerprint minutiae information is stored for one ID in a database.
  • a third fingerprint image is scanned, and the image quality state of the third fingerprint image is checked. If the image quality state is good, third fingerprint minutiae information is extracted from the third fingerprint image. The similarity between the extracted fingerprint minutiae information and the first fingerprint minutiae information is calculated. If the similarity is larger than the predetermined specific value (60%), minutiae information unique to the third fingerprint minutiae information is detected and reflected in the 2' nd fingerprint minutiae information, thereby producing 3' rd fingerprint minutiae information. The 3' rd fingerprint minutiae information is stored for the same ID in the database.
  • N' th fingerprint minutiae information generated finally by repeating the above operation N times is stored for the same ID in the database, thereby completing the fingerprint registration.
  • a fingerprint image is scanned, and the image quality state of the fingerprint image is checked. If the image quality state is good, fingerprint minutiae information is extracted from the fingerprint image, and the similarity between the extracted fingerprint minutiae information and the fingerprint minutiae information stored in the database is calculated. If the similarity is larger than a predetermined specific value (70%), it is determined that the fingerprints match.
  • FIG. 9 is a flowchart illustrating a fingerprint registration and authentication method according to another embodiment of the present invention.
  • the image quality state of an initially scanned first fingerprint image is checked. If the image quality state is good, first fingerprint minutiae information is extracted from the first fingerprint image, and stored for one ID in a database.
  • a second fingerprint image is scanned, and the image quality state of the second fingerprint image is checked. If the image quality state is good, second fingerprint minutiae information is extracted from the second fingerprint image. The similarity between the second fingerprint minutiae information and the minutiae information stored in the database is calculated. If the similarity is larger than a predetermined specific value (60%), minutiae information unique to the second fingerprint minutiae information is detected and reflected in the first fingerprint minutiae information, thereby producing 2' nd fingerprint minutiae information. The 2' nd fingerprint minutiae information is stored for the same ID in the database.
  • the similarity between third fingerprint minutiae information extracted by scanning a third fingerprint and the 2' nd fingerprint minutiae information is calculated. If the similarity is larger than the predetermined specific value (60%), minutiae information unique to the third fingerprint minutiae information is detected and reflected in the 2' nd fingerprint minutiae information, thereby producing 3' rd fingerprint minutiae information.
  • the 3' rd fingerprint minutiae information is stored for the same ID in the database.
  • N' th fingerprint minutiae information generated finally by repeating the above operation N times is stored for the same ID in the database, thereby completing the fingerprint registration.
  • a fingerprint image is scanned, and the image quality state of the fingerprint image is checked. If the image quality state is good, fingerprint minutiae information is extracted from the fingerprint image, and the similarity between the extracted fingerprint minutiae information and the fingerprint minutiae information stored in the database is calculated. If the similarity is larger than a predetermined specific value (70%), it is determined that the fingerprints match.
  • minutiae information unique to the fingerprint minutiae extracted from the fingerprint image scanned for fingerprint authentication is detected and reflected in the fingerprint minutiae information stored in the database, thereby generating new fingerprint minutiae information.
  • the new fingerprint minutiae information is stored for the same ID in the database.
  • FIG. 10 is a flowchart illustrating a fingerprint registration and authentication method according to another embodiment of the present invention.
  • the image quality state of an initially scanned first fingerprint image is checked. If the image quality state is good, first fingerprint minutiae information is extracted from the first fingerprint image.
  • a second fingerprint image is scanned, and the image quality state of the second fingerprint image is checked. If the image quality state is good, second fingerprint minutiae information is extracted from the second fingerprint image. The similarity between the second fingerprint minutiae information and the first fingerprint minutiae information is calculated. If the similarity is larger than a predetermined specific value (60%), minutiae information unique to the second fingerprint minutiae information is detected and reflected in the first fingerprint minutiae information, thereby producing 2' nd fingerprint minutiae information. The 2' nd fingerprint minutiae information is stored for one ID in the database.
  • a third fingerprint image is scanned, and the image quality state of the third fingerprint image is checked. If the image quality state is good, third fingerprint minutiae information is extracted from the third fingerprint image. The similarity between the third fingerprint minutiae information and the first fingerprint minutiae information is calculated. If the similarity is larger than the predetermined specific value (60%), minutiae information unique to the third fingerprint minutiae information is detected and reflected in the 2' nd fingerprint minutiae information, thereby producing 3' rd fingerprint minutiae information. The 3' rd fingerprint minutiae information is stored for the same ID in the database.
  • N' th fingerprint minutiae information generated finally by repeating the above operation N times is stored for the same ID in the database, thereby completing the fingerprint registration.
  • a fingerprint image is scanned, and the image quality state of the image is checked. If the image quality state is good, fingerprint minutiae information is extracted from the fingerprint image, and the similarity between the extracted fingerprint minutiae information and fingerprint minutiae information stored in the database is calculated. If the similarity is larger than a predetermined specific value (70%), it is determined that the fingerprints match.
  • minutiae information unique to the fingerprint minutiae information extracted from the fingerprint image scanned for fingerprint authentication is detected and reflected in the fingerprint minutiae information stored in the database, thereby generating new fingerprint minutiae information.
  • the new fingerprint minutiae information is stored for the same ID in the database. Since minutiae information unique to minutiae information extracted for fingerprint authentication is also detected and reflected for the same ID during fingerprint authentication, more complete fingerprint minutiae information can be configured.
  • the present invention performs registration in conjunction with authentication through a fingerprint sensor, without separating them. Therefore, during fingerprint registration, the similarity of minutiae extracted from an N th scanned fingerprint image to fingerprint minutiae extracted from an initially scanned fingerprint image is calculated. If the similarity between the two fingerprints is equal to or larger than a specific value, redundant minutiae of the minutiae extracted from the two fingerprints are removed, and then the resulting minutiae are registered for one ID.
  • the present invention extracts minutiae sets from a plurality of scanned fingerprint images, and separately stores the minutiae sets for one ID. Or the present invention stores one integrated minutiae set by removing redundant minutiae in the plurality of fingerprint images.
  • the similarity of minutiae of a new scanned fingerprint to minutiae extracted from an initially scanned fingerprint or one integrated minutiae set is additionally registered.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Biomedical Technology (AREA)
  • Software Systems (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Collating Specific Patterns (AREA)

Abstract

A fingerprint registration and authentication technique is disclosed. In an apparatus for controlling fingerprint registration and fingerprint authentication, and a method of driving the same according to an embodiment of the present invention, as a fingerprint image is scanned by a fingerprint sensor, N' th fingerprint minutiae information is generated, using integrated fingerprint minutiae information including only non-redundant fingerprint minutiae information from fingerprint minutiae information extracted N times, and registered for one ID. A similarity between fingerprint minutiae information extracted from a scanned fingerprint image and the N' th minutiae information is calculated. If the similarity is larger than a predetermined specific value, the scanned fingerprint image is authenticated. Therefore, the problem that a malicious user can register two or more different fingerprints for one ID is solved, thereby enabling only an authorized user to use a smartphone, a laptop computer, or other devices which have a fingerprint sensor therein.

Description

APPARATUS FOR CONTROLLING FINGERPRINT REGISTRATION AND FINGERPRINT AUTHENTICATION, AND METHOD OF DRIVING THE SAME
The present invention relates to a fingerprint recognition technology, and more particularly, to an apparatus for controlling fingerprint registration and fingerprint authentication, which as a fingerprint image is scanned by a fingerprint sensor, generates N' th fingerprint minutiae (features) information by using integrated fingerprint minutiae information including only non-redundant fingerprint minutiae information from fingerprint minutiae information that has been extracted N times, registers the N' th fingerprint minutiae information for one identifier (ID), calculates a similarity between fingerprint minutiae information extracted from a fingerprint image scanned for authentication and the N' th fingerprint minutiae information, and if the similarity is larger than a predetermined specific value, authenticates the scanned fingerprint image, and a method of driving the apparatus.
Fingerprint recognition, which has widely been used in the field of biometrics, started at the time when N Grew found out that humans have different fingerprints in the UK in 1684, and was first used for commercial purposes in a Wall Street sticks firm in the US in 1968.
A person's fingerprints are kept unchanged until the end of the person's life. Even though a fingerprint is scratched in view of an external factor, the fingerprint is soon recovered to the original shape, and the probability of a person having an identical fingerprint to that of another person is only 1/1,000,000,000.
Fingerprint recognition is a user identification technique of electronically reading a user's finger on the basis of the above fingerprint property, comparing the reading with pre-input data, and thus identifying the user by the comparison. While fingerprint recognition has been applied to the fields of identification, control of physical access to a safe and an entrance control system, crime investigation to find criminals, etc., fingerprint recognition has also been used as a security system for security and authentication in electronic transactions since the 1990s.
Owing to advanced research on fingerprint recognition techniques, fingerprint sensors have been getting smaller and more integrated, and have found their applications in a wide range such as electronic transactions. Of recent, fingerprint recognition has also been adopted for portable phones, personal digital assistant (PDA) terminals, etc.
In general, fingerprint recognition techniques are divided into image-based fingerprint recognition and feature-based fingerprint recognition. Feature-based fingerprint recognition is widely used, including minutiae extraction and matching. The spatial characteristics of extracted minutiae are used by applying many image processing techniques such as flattening, separation of foreground and background, binarization, and thinning.
That is, feature-based fingerprint recognition methods compare a fingerprint for authentication with a registered fingerprint by using minutiae, mostly checking the similarity between corresponding minutiae.
A fingerprint recognition algorithm adopted in a smartphone equipped with a fingerprint sensor or an existing fingerprint sensor-related product separately performs fingerprint registration and fingerprint authentication. During fingerprint registration, the fingerprint of the same finger is scanned at least four times up to ten times in order to reduce a false rejection ratio (FRR), and the minutiae of the extracted fingerprints are registered for one ID. In general, since the correlation between scanned fingerprints is not checked, the fingerprints of two or more different fingers may problematically be registered for one ID. Although it does not matter that the same person registers the fingerprints of his or her different fingers for one ID, registration of the fingerprints of another person's plural fingers for one ID may cause the fatal problem that an unauthorized user can be authenticated.
Prior Art Documents
Patent Documents
Korean Patent No. 10-1783816-0000
Korean Patent No. 10-0497226-0000
Korean Publication Patent No. 10-2011-0048121
Korean Patent No. 10-1632912-0000
Therefore, an apparatus for controlling fingerprint registration and fingerprint authentication, and a method of driving the same according to embodiments of the present invention have been devised in view of the above problems, and an aspect of the present invention is to enable successful registration of only a fingerprint of an authorized user, and thus allow only the authorized user to use a smartphone, a laptop computer, or other devices which have a fingerprint sensor therein, during fingerprint registration and authentication on the smartphone, the laptop computer, or the other devices by generating N' th fingerprint minutiae information, using integrated fingerprint minutiae information including only non-redundant fingerprint minutiae information from fingerprint minutiae information extracted N times along with scanning of a fingerprint image by the fingerprint sensor, registering the N' th fingerprint minutiae information for one ID, calculating a similarity between fingerprint minutiae information extracted from a scanned fingerprint image and the N' th minutiae information, and authenticating the scanned fingerprint image, if the similarity is larger than a predetermined specific value.
It is another aspect of the present invention to overcome the shortcoming that since correlations between scanned fingerprints are generally not checked during registration of fingerprint minutiae extracted from fingerprint images of the same finger scanned at least four times up to ten times, two or more different fingerprints are registered for one ID.
It is another aspect of the present invention to eliminate the problem that possible registration of fingerprints of two or more other persons for one ID leads to malicious system use of an unauthorized person in a system that enhances security by fingerprint recognition.
In order to achieve these objects, the present invention includes the following constructions.
In accordance with an aspect of the present invention, an apparatus for controlling fingerprint registration and fingerprint authentication includes a similarity check and computation unit configured to perform fingerprint registration in conjunction with fingerprint authentication through a fingerprint sensor, without separating the fingerprint registration from the fingerprint authentication, and to calculate a similarity between first fingerprint minutiae information extracted from a first fingerprint image scanned a first time and N th fingerprint minutiae information extracted from an N th fingerprint image scanned an N th time, during fingerprint registration of a selected one of fingers, and a fingerprint registration and authentication controller configured to, if the calculated similarity between the first fingerprint minutiae information and the N th fingerprint minutiae information is larger than a predetermined specific value, generate N' th fingerprint minutiae information by detecting minutiae information unique to the N th fingerprint minutiae information, and reflecting the detected minutiae information in the first fingerprint minutiae information, and to register the N' th fingerprint minutiae information for one identifier (ID), instead of the first fingerprint minutiae information. The similarity check and computation unit is configured to calculate a similarity between the N' th fingerprint minutiae information, instead of the first fingerprint minutiae information, and (N+1) th fingerprint minutiae information extracted from an (N+1) th fingerprint image scanned an (N+1) th time.
In accordance with another aspect of the present invention, a method of controlling an apparatus for controlling fingerprint registration and fingerprint authentication includes performing fingerprint registration in conjunction with fingerprint authentication through a fingerprint sensor, without separating the fingerprint registration from the fingerprint authentication by a similarity check and computation unit, calculating a similarity between first fingerprint minutiae information extracted from a first fingerprint image scanned a first time and N th fingerprint minutiae information extracted from an N th fingerprint image scanned an N th time, during fingerprint registration of a selected one of fingers, by the similarity check and computation unit, generating N' th fingerprint minutiae information by detecting minutiae information unique to the N th fingerprint minutiae information, and reflecting the detected minutiae information in the first fingerprint minutiae information, by a fingerprint registration and authentication controller, if the calculated similarity between the first fingerprint minutiae information and the N th fingerprint minutiae information is larger than a predetermined specific value, and registering the N 'th fingerprint minutiae information for one identifier (ID), instead of the first fingerprint minutiae information by the fingerprint registration and authentication controller.
The apparatus for controlling fingerprint registration and fingerprint authentication, and the method of driving the same according to the embodiments of the present invention have a first effect of enabling successful recognition of only a fingerprint of an authorized user, and thus allow only the authorized user to use a smartphone, a laptop computer, or other devices which have a fingerprint sensor therein, during fingerprint registration and authentication on the smartphone, the laptop computer, or the other devices by generating N' th fingerprint minutiae information, using integrated fingerprint minutiae information including only non-redundant fingerprint minutiae information from fingerprint minutiae information extracted N times along with scanning of a fingerprint image by the fingerprint sensor, registering the N' th fingerprint minutiae information for one ID, calculating a similarity between fingerprint minutiae information extracted from a scanned fingerprint image and the N' th minutiae information, and authenticating the scanned fingerprint image, if the similarity is larger than a predetermined specific value.
Further, the present invention has a second effect of overcoming the shortcoming that since correlations between scanned fingerprints are generally not checked during registration of fingerprint minutiae extracted from fingerprint images of the same finger scanned at least four times up to ten times, two or more different fingerprints can be registered for one ID.
Further, the present invention has a third effect of eliminating the problem that possible registration of fingerprints of two or more other persons for one ID leads to malicious system use of an unauthorized person in a system that enhances security by fingerprint recognition.
FIG. 1 is a block diagram illustrating an apparatus for controlling fingerprint registration and fingerprint authentication according to an embodiment of the present invention.
FIG. 2 is a flowchart illustrating a method of driving an apparatus for controlling fingerprint registration and fingerprint authentication according to an embodiment of the present invention.
FIG. 3 is a view referred to for describing a conventional fingerprint registration and authentication method.
FIG. 4 is a view referred to for describing a method of storing fingerprint minutiae information by calculating similarities among a plurality of fingerprint images during conventional fingerprint registration.
FIG. 5 is a view referred to for describing a problem encountered with registration of a fingerprint image by calculating similarities among fingerprint images during conventional fingerprint registration.
FIG. 6 is another view referred to for describing a problem encountered with registration of a fingerprint image by calculating similarities among fingerprint images during conventional fingerprint registration.
FIG. 7 is a detailed flowchart illustrating an operation of registering a fingerprint image in the method of driving an apparatus for controlling fingerprint registration and fingerprint authentication according to an embodiment of the present invention.
FIG. 8 is another detailed flowchart illustrating an operation of registering a fingerprint image in the method of driving an apparatus for controlling fingerprint registration and fingerprint authentication according to another embodiment of the present invention.
FIG. 9 is another detailed flowchart illustrating an operation of registering a fingerprint image in the method of driving an apparatus for controlling fingerprint registration and fingerprint authentication according to another embodiment of the present invention.
FIG. 10 is another detailed flowchart illustrating an operation of registering a fingerprint image in the method of driving an apparatus for controlling fingerprint registration and fingerprint authentication according to another embodiment of the present invention.
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings.
FIG. 1 is a block diagram illustrating an apparatus for controlling fingerprint registration and fingerprint authentication according to an embodiment of the present invention.
Referring to FIG. 1, as a fingerprint image is scanned by a fingerprint sensor, an apparatus 1000 for controlling fingerprint registration and fingerprint authentication generates N' th fingerprint minutiae information, using integrated fingerprint minutiae information including only non-redundant fingerprint minutiae information from fingerprint minutiae information extracted N times, registers the N' th fingerprint minutiae information for one identifier (ID), calculates a similarity between fingerprint minutiae information extracted from a fingerprint image scanned for authentication and the N' th fingerprint minutiae information, and if the similarity is larger than a predetermined specific value, authenticates the scanned fingerprint image. The apparatus 1000 for controlling fingerprint registration and fingerprint authentication includes a similarity check and computation unit 100, a data set storage 200, and a fingerprint registration and authentication controller 300.
During fingerprint minutiae extraction performed in the apparatus 1000 for controlling fingerprint registration and fingerprint authentication according to the embodiment of the present invention, after a scanned image is flattened, information such as the positions and directions of an ending that defines the end of a ridge line flow, and a bifurcation defined as a point in the ridge where the line is separated into two branches, the type of a minutia, and so on is extracted by subjecting the flattened image to various image processes including foreground and background separation, binarization, and thinning. As a result, minutiae data having the following four parameters is extracted:
m = (x, y, θ, T)
where x represents an x-axis coordinate, y represents a y-axis coordinate, θ represents the direction of a minutia, and T represents the type of the minutia, which is set to 0 to indicate ending, and to 1 to indicate bifurcation.
In the apparatus 1000 for controlling fingerprint registration and fingerprint authentication, the similarity check and computation unit 100 may check the similarity between two fingerprints by using a clique model made up of the radius of a circle circumscribed around three adjacent minutiae, the maximum α of the included angles of three vertices, an included angle β in a clockwise direction from α, the directions θa, θb and θc of the respective minutiae, and the types of Ta, Tb and Tc of the respective minutiae, in an extracted minutiae set.
The similarity check and computation unit 100 makes up lists in which clique data are appropriately ordered on the basis of the radius of a circumscribed circle, a maximum included angle, or the like by using minutiae of two fingerprints to be compared, and searches the two lists for matching cliques.
The similarity check and computation unit 100 may obtain two superimposed fingerprints by calculating rotation and shift amounts between two images by the matching cliques, and shifting the two fingerprints to the same coordinate system, detect corresponding minutiae in the superimposed fingerprints, and subject the detected minutiae to matching, thereby calculating the similarity.
The apparatus 1000 for controlling fingerprint registration and fingerprint authentication according to the embodiment of the present invention performs registration in conjunction with authentication through a fingerprint sensor, without separating the registration from the authentication. During fingerprint registration, the similarity between first fingerprint minutiae information extracted from an initial scanned fingerprint image and second fingerprint minutiae information extracted from a second scanned fingerprint image. If the similarity is larger than a predetermined specific value, minutiae information unique to the second fingerprint minutiae information is detected and reflected in the first fingerprint minutiae information, thus producing 2' nd fingerprint minutiae information. The 2' nd fingerprint minutiae information is registered for one ID.
Further, the apparatus 1000 for controlling fingerprint registration and fingerprint authentication calculates the similarity between N' th fingerprint minutiae information and (N+1) th fingerprint minutiae information of a newly scanned (N+1) th fingerprint image during fingerprint registration.
If the similarity is larger than the predetermined specific value, the apparatus 1000 for controlling fingerprint registration and fingerprint authentication detects minutiae information unique to the (N+1) th fingerprint minutiae information and reflects the unique minutiae information in the N' th fingerprint minutiae information, thus producing (N+1)' th fingerprint minutiae information. The apparatus 1000 for controlling fingerprint registration and fingerprint authentication newly registers an improved data set including the (N+1)' th fingerprint minutiae information for the same ID, instead of the N' th fingerprint minutiae information.
In other words, the pre-registered (N' th) fingerprint minutiae information is replaced with the (N+1)' th fingerprint minutiae information, and stored in the improved data set.
Further, during the fingerprint registration, if the fingerprint minutiae information of a fingerprint image to be authenticated matches pre-registered fingerprint minutiae information due to the similarity between the fingerprint minutiae information equal to or larger than a predetermined ratio, only non-redundant fingerprint minutiae information of the new fingerprint minutiae information with respect to a plurality of pieces of pre-registered minutiae information is additionally registered for a matching ID.
According to another embodiment of the present invention, the apparatus 1000 for controlling fingerprint registration and fingerprint authentication compares the first fingerprint minutiae information or the pre-registered N' th fingerprint minutiae information in the improved data set with fingerprint minutiae information extracted from a new scanned image. If the similarity between the fingerprint minutiae information is equal to or less than a predetermined specific value, or equal to or larger than a predetermined specific value, the apparatus 1000 for controlling fingerprint registration and fingerprint authentication eliminates the fingerprint minutiae of the new scanned image. If the similarity is too low, this may mean different fingerprint images, and if the similarity is too high, most minutiae are identical and thus not many minutiae need to be added.
Herein, the apparatus 1000 for controlling fingerprint registration and fingerprint authentication reflects and stores a new scanned fingerprint image with a similarity within a predetermined range, and non-redundant fingerprint minutiae of fingerprint minutiae information extracted from the new scanned fingerprint image in the improved data set, and registers the minutiae information for one ID.
More specifically, the apparatus 1000 for controlling fingerprint registration and fingerprint authentication performs the foregoing operations by means of components described below.
The similarity check and computation unit 100 performs fingerprint registration in conjunction with fingerprint authentication through the fingerprint sensor, without separating the fingerprint registration from the fingerprint authentication. During fingerprint registration of a selected one of fingers, the similarity check and computation unit 100 calculates the similarity between first fingerprint minutiae information extracted from a first fingerprint image scanned initially and N th fingerprint minutiae information extracted from an N th fingerprint image scanned an N th time.
The data set storage 200 initially stores the first fingerprint minutiae information for one ID, replaces the first fingerprint minutiae information with N' th fingerprint minutiae information obtained through N modifications, and stores the N' th fingerprint minutiae information for the same ID.
Subsequently, the similarity check and computation unit 100 calculates the similarity between the N' th fingerprint minutiae information, instead of the first fingerprint minutiae information extracted from the first fingerprint image, and (N+1) th fingerprint minutiae information extracted from an (N+1) th scanned fingerprint image.
If the similarity between the first fingerprint minutiae information and the N th fingerprint minutiae information is larger than a predetermined specific value, the fingerprint registration and authentication controller 300 detects minutiae information unique to the N th fingerprint minutiae information, and reflects the unique minutiae information in the first fingerprint image, thereby producing the N' th fingerprint minutiae information. The fingerprint registration and authentication controller 300 registers the N' th fingerprint minutiae information for the one ID, instead of the first fingerprint minutiae information.
The fingerprint registration and authentication controller 300 performs fingerprint authentication, using the stored the N' th fingerprint minutiae information.
During fingerprint registration, the fingerprint registration and authentication controller 300 may reinforce the security of personal information by encrypting fingerprint minutiae information by an encryption algorithm such as advanced encryption standard (AES), data encryption standard (DES), SEED, ARIA, or the like, storing the encrypted fingerprint minutiae information, decrypting the stored fingerprint minutiae information by the encryption algorithm such as AES, DES, SEED, ARIA, or the like, and using the decrypted fingerprint minutiae information.
After matching between a fingerprint area including fingerprint minutiae and a fingerprint area including fingerprint minutiae information in the data set storage 200, the similarity check and computation unit 100 compares the fingerprint minutiae of the two fingerprint areas.
A similarity is a ratio between the number of matching minutiae and the number of non-matching minutiae during comparison between the minutiae of two fingerprints. A mere exemplary threshold value such as a similarity of 60% or 70% may be set or changed appropriately under circumstances.
FIG. 2 is a flowchart illustrating a method of driving an apparatus for controlling fingerprint registration and fingerprint authentication according to an embodiment of the present invention.
Referring to FIG. 2, in the method of driving an apparatus for controlling fingerprint registration and fingerprint authentication, as a plurality of fingerprint images are scanned by means of a fingerprint sensor, an improved data set, which has been obtained by removing redundant minutiae information in a source data set including fingerprint minutiae information extracted from the scanned fingerprint images, or at least one piece of fingerprint minutiae information, is registered for one ID.
First, a similarity check and computation unit performs fingerprint registration in conjunction with fingerprint authentication through a fingerprint sensor without separating the fingerprint registration from the fingerprint authentication (S100).
During fingerprint registration of a selected one of fingers, the similarity check and computation unit calculates the similarity between first fingerprint minutiae information extracted from an initially scanned first fingerprint image and N th fingerprint minutiae information extracted from an N th scanned fingerprint image (S200 and S300).
If the similarity between the first fingerprint minutiae information and the N th fingerprint minutiae information is larger than a predetermined specific value, a fingerprint registration and authentication controller generates N' th fingerprint minutiae information by detecting minutiae information unique to the N th fingerprint minutiae information, and reflecting the detected minutiae information in the first fingerprint minutiae information (S400).
The fingerprint registration and authentication controller registers the N' th fingerprint minutiae information for one ID, instead of the first fingerprint image and the first fingerprint minutiae information (S500).
In a subsequent additional operation, the similarity check and computation unit calculates the similarity between the N' th fingerprint information extracted from the N' th fingerprint image (instead of the first fingerprint minutiae information extracted from the first fingerprint image) and (N+1) th fingerprint minutiae information of the afore-mentioned (N+1) th fingerprint image.
The fingerprint registration and authentication controller performs fingerprint authentication, using the N' th fingerprint minutiae information.
FIGS. 3 and 4 illustrate conventional technologies relating to fingerprint registration and fingerprint authentication. In FIG. 3, with fingerprint registration separated from fingerprint authentication, fingerprint minutiae are registered for one ID. Fingerprint minutiae stored in the resulting database are compared with fingerprint minutiae extracted from a scanned image, to thereby determine whether the minutiae of the two fingerprints are identical.
In FIG. 4, during fingerprint registration, an integrated fingerprint minutiae set is generated by using fingerprint images with high similarities from among a plurality of fingerprint images through fingerprint authentication. The integrated fingerprint minutiae set is stored for one ID, and used for fingerprint authentication. More specifically, fingerprint minutiae sets are extracted from a plurality of scanned fingerprint images, and similarities between the fingerprint minutiae sets are calculated. A single integrated fingerprint minutiae set is produced by removing redundant fingerprint minutiae in fingerprint minutiae sets with similarities within a predetermined range, and stored for one ID. However, the method of producing one integrated fingerprint minutia set simply by selecting only fingerprint images with similarities within a predetermined range, and storing the integrated fingerprint minutia set has limitations in its effectiveness in perfectly preventing a malicious user from registering fingerprint images of a plurality of fingers for one ID, and using the ID.
In an example, it may be noted that the conventional fingerprint registration and authentication method for calculating similarities between multiple images and accordingly registering fingerprints can prevent a malicious user from registering fingerprint images of a plurality of fingers for one ID in the case illustrated in FIG. 5.
That is, a first fingerprint image among fingerprint images is obtained by scanning finger A, and second to fourth fingerprint images are obtained by scanning finger B, as illustrated in FIG. 5.
In a method of driving an apparatus for controlling fingerprint registration and fingerprint authentication, the minutiae of the respective fingerprints are extracted, and similarities among the minutiae are calculated. Then, the similarities between the first fingerprint image obtained by scanning finger A and the second to fourth fingerprint images obtained by scanning finger B are very low (S12=3%, S13=5%, and S14=2%), leading to an average similarity S1 of 3.3% between the first fingerprint and the other fingerprints.
While the similarities between the second fingerprint image obtained by scanning finger B and the third and fourth fingerprint images obtained by scanning finger B are high (S23=70% and S24=75%), the similarity between the second fingerprint image and the first fingerprint image obtained by scanning finger A is very low (S21=3%), and thus an average similarity (S2) between the second fingerprint and the other fingerprints is 49.3%.
Similarly, an average similarity S3 between the third fingerprint and the other fingerprints is 50.6%, and an average similarity S4 between the fourth fingerprint and the other fingerprints is 51.3%. If a fingerprint with an average similarity equal to or less than 10% is to be removed, the fingerprint image of finger A is removed, and fingerprint minutiae are extracted only from the fingerprint images of finger B. Then, an integrated data set is configured by removing redundant minutiae in the extracted fingerprint minutiae. Thus, only the fingerprint images of one finger may be registered, thereby preventing a malicious user from registering fingerprint images of a plurality of fingers for one ID. However, despite the advantage of preventing registration of fingerprints of a plurality of fingers, this method cannot select and register a specific one of the fingerprint images of finger A and finger B.
In another example, however, the conventional fingerprint registration and authentication method for calculating similarities among multiple fingerprint images and accordingly registering fingerprints cannot prevent a malicious user from registering fingerprint images of a plurality of fingers for one ID in the case illustrated in FIG. 6.
As illustrated in FIG. 6, first and third fingerprint images among fingerprint images are obtained by scanning finger A, and second and fourth fingerprint images are obtained by scanning finger B. If fingerprint minutiae are extracted from the respective fingerprint images and similarities among the fingerprint minutiae are calculated, the similarities are all close. Therefore, it is difficult to selectively remove fingerprints with similarities equal to or less than a specific value or equal to or larger than a specific value.
More specifically, if minutiae are extracted from the first to fourth fingerprints and similarities among the minutiae are calculated, the similarities between the first fingerprint image obtained by scanning finger A and the second and fourth fingerprint images obtained by scanning finger B are very low (S12=3% and S14=2%), and the similarity between the first fingerprint image and the third fingerprint image obtained by scanning finger A is high (S13=72%). Thus, the first fingerprint image has an average similarity S1 of 25.6%.
While the similarity between the second image obtained by scanning finger B and the fourth image obtained by scanning finger B is high (S24=75%), the similarities between the second image and the first and third images obtained by scanning finger A are very low (S21=3% and S23=5%). Thus, an average similarity S2 between the second fingerprint and the other fingerprints is 27.6%. Similarly, an average similarity S3 between the third fingerprint and the other fingerprints is 27%, and an average similarity S4 between the fourth fingerprint and the other fingerprints is 27%.
Even though a fingerprint with an average similarity equal to or less than 10% is supposed to be removed, there is no fingerprint to be removed. Thus, it is possible to remove a redundant fingerprint minutiae set from four fingerprint data sets extracted from the four fingerprint images obtained by scanning fingers A and B, and register the resulting fingerprint minutiae sets for one ID. As a result, a malicious user's registration of fingerprint images of a plurality of fingers for one ID cannot be prevented.
FIG. 7 is a detailed flowchart illustrating a fingerprint registration and fingerprint authentication method according to an embodiment of the present invention. During fingerprint registration, the image quality state of an initially scanned first fingerprint image is checked. If the image quality state is good, first fingerprint minutiae information is extracted from the first fingerprint image, and stored for one ID in a database.
Subsequently, a second fingerprint image is scanned, and the image quality state of the second fingerprint image is checked. If the image quality state is good, second fingerprint minutiae information is extracted from the second fingerprint image. The similarity between the extracted second fingerprint minutiae information and the minutiae information stored in the database is calculated. If the similarity is larger than a predetermined specific value (60%), minutiae information unique to the second fingerprint minutiae information is detected and reflected in the first fingerprint minutiae information, thereby producing 2' nd fingerprint minutiae information. The 2' nd fingerprint minutiae information is stored for the same ID in the database.
Subsequently, the similarity between third fingerprint minutiae information extracted from a third fingerprint image and the 2' nd fingerprint minutiae information is calculated. If the similarity is larger than the predetermined specific value (60%), minutiae information unique to the third fingerprint minutiae information is detected and reflected in the 2' nd fingerprint minutiae information, thereby producing 3' rd fingerprint minutiae information. The 3' rd fingerprint minutiae information is stored for the same ID in the database.
N' th fingerprint minutiae information generated finally by repeating the above operation N times is stored for the same ID in the database, thereby completing the fingerprint registration. During fingerprint authentication, a fingerprint image is scanned, and the image quality state of the fingerprint image is checked. If the image quality state is good, fingerprint minutiae information is extracted from the fingerprint image, and the similarity between the extracted fingerprint minutiae information and the fingerprint minutiae information stored in the database. If the similarity is larger than a predetermined specific value (70%), it is determined that the fingerprints match.
FIG. 8 is a flowchart illustrating a fingerprint registration and authentication method according to another embodiment of the present invention.
During fingerprint registration, the image quality state of an initially scanned first fingerprint image is checked. If the image quality state is good, first fingerprint minutiae information is extracted from the first fingerprint image.
Subsequently, a second fingerprint image is scanned, and the image quality state of the second fingerprint image is checked. If the image quality state is good, second fingerprint minutiae information is extracted from the second fingerprint image. The similarity between the extracted second fingerprint minutiae information and the first minutiae information is calculated. If the similarity is larger than a predetermined specific value (60%), minutiae information unique to the second fingerprint minutiae information is detected and reflected in the first fingerprint minutiae information, thereby producing 2' nd fingerprint minutiae information. The 2' nd fingerprint minutiae information is stored for one ID in a database.
Subsequently, a third fingerprint image is scanned, and the image quality state of the third fingerprint image is checked. If the image quality state is good, third fingerprint minutiae information is extracted from the third fingerprint image. The similarity between the extracted fingerprint minutiae information and the first fingerprint minutiae information is calculated. If the similarity is larger than the predetermined specific value (60%), minutiae information unique to the third fingerprint minutiae information is detected and reflected in the 2' nd fingerprint minutiae information, thereby producing 3' rd fingerprint minutiae information. The 3' rd fingerprint minutiae information is stored for the same ID in the database.
N' th fingerprint minutiae information generated finally by repeating the above operation N times is stored for the same ID in the database, thereby completing the fingerprint registration. During fingerprint authentication, a fingerprint image is scanned, and the image quality state of the fingerprint image is checked. If the image quality state is good, fingerprint minutiae information is extracted from the fingerprint image, and the similarity between the extracted fingerprint minutiae information and the fingerprint minutiae information stored in the database is calculated. If the similarity is larger than a predetermined specific value (70%), it is determined that the fingerprints match.
FIG. 9 is a flowchart illustrating a fingerprint registration and authentication method according to another embodiment of the present invention.
During fingerprint registration, the image quality state of an initially scanned first fingerprint image is checked. If the image quality state is good, first fingerprint minutiae information is extracted from the first fingerprint image, and stored for one ID in a database.
Subsequently, a second fingerprint image is scanned, and the image quality state of the second fingerprint image is checked. If the image quality state is good, second fingerprint minutiae information is extracted from the second fingerprint image. The similarity between the second fingerprint minutiae information and the minutiae information stored in the database is calculated. If the similarity is larger than a predetermined specific value (60%), minutiae information unique to the second fingerprint minutiae information is detected and reflected in the first fingerprint minutiae information, thereby producing 2' nd fingerprint minutiae information. The 2' nd fingerprint minutiae information is stored for the same ID in the database.
Subsequently, the similarity between third fingerprint minutiae information extracted by scanning a third fingerprint and the 2' nd fingerprint minutiae information is calculated. If the similarity is larger than the predetermined specific value (60%), minutiae information unique to the third fingerprint minutiae information is detected and reflected in the 2' nd fingerprint minutiae information, thereby producing 3' rd fingerprint minutiae information. The 3' rd fingerprint minutiae information is stored for the same ID in the database.
N' th fingerprint minutiae information generated finally by repeating the above operation N times is stored for the same ID in the database, thereby completing the fingerprint registration.
During fingerprint authentication, a fingerprint image is scanned, and the image quality state of the fingerprint image is checked. If the image quality state is good, fingerprint minutiae information is extracted from the fingerprint image, and the similarity between the extracted fingerprint minutiae information and the fingerprint minutiae information stored in the database is calculated. If the similarity is larger than a predetermined specific value (70%), it is determined that the fingerprints match.
If the fingerprints match, minutiae information unique to the fingerprint minutiae extracted from the fingerprint image scanned for fingerprint authentication is detected and reflected in the fingerprint minutiae information stored in the database, thereby generating new fingerprint minutiae information. The new fingerprint minutiae information is stored for the same ID in the database.
Since minutiae information unique to minutiae information extracted for fingerprint authentication is also detected and reflected for the same ID during fingerprint authentication, more complete fingerprint minutiae information can be configured.
FIG. 10 is a flowchart illustrating a fingerprint registration and authentication method according to another embodiment of the present invention.
During fingerprint registration, the image quality state of an initially scanned first fingerprint image is checked. If the image quality state is good, first fingerprint minutiae information is extracted from the first fingerprint image.
Subsequently, a second fingerprint image is scanned, and the image quality state of the second fingerprint image is checked. If the image quality state is good, second fingerprint minutiae information is extracted from the second fingerprint image. The similarity between the second fingerprint minutiae information and the first fingerprint minutiae information is calculated. If the similarity is larger than a predetermined specific value (60%), minutiae information unique to the second fingerprint minutiae information is detected and reflected in the first fingerprint minutiae information, thereby producing 2' nd fingerprint minutiae information. The 2' nd fingerprint minutiae information is stored for one ID in the database.
Subsequently, a third fingerprint image is scanned, and the image quality state of the third fingerprint image is checked. If the image quality state is good, third fingerprint minutiae information is extracted from the third fingerprint image. The similarity between the third fingerprint minutiae information and the first fingerprint minutiae information is calculated. If the similarity is larger than the predetermined specific value (60%), minutiae information unique to the third fingerprint minutiae information is detected and reflected in the 2' nd fingerprint minutiae information, thereby producing 3' rd fingerprint minutiae information. The 3' rd fingerprint minutiae information is stored for the same ID in the database.
N' th fingerprint minutiae information generated finally by repeating the above operation N times is stored for the same ID in the database, thereby completing the fingerprint registration. During fingerprint authentication, a fingerprint image is scanned, and the image quality state of the image is checked. If the image quality state is good, fingerprint minutiae information is extracted from the fingerprint image, and the similarity between the extracted fingerprint minutiae information and fingerprint minutiae information stored in the database is calculated. If the similarity is larger than a predetermined specific value (70%), it is determined that the fingerprints match.
If the fingerprints match, minutiae information unique to the fingerprint minutiae information extracted from the fingerprint image scanned for fingerprint authentication is detected and reflected in the fingerprint minutiae information stored in the database, thereby generating new fingerprint minutiae information. The new fingerprint minutiae information is stored for the same ID in the database. Since minutiae information unique to minutiae information extracted for fingerprint authentication is also detected and reflected for the same ID during fingerprint authentication, more complete fingerprint minutiae information can be configured.
That is, in order to solve the problem, which is consistently encountered with commercialized fingerprint sensor-related products, that a malicious user can register two or more different fingerprints for one ID, the present invention performs registration in conjunction with authentication through a fingerprint sensor, without separating them. Therefore, during fingerprint registration, the similarity of minutiae extracted from an N th scanned fingerprint image to fingerprint minutiae extracted from an initially scanned fingerprint image is calculated. If the similarity between the two fingerprints is equal to or larger than a specific value, redundant minutiae of the minutiae extracted from the two fingerprints are removed, and then the resulting minutiae are registered for one ID.
Further, the present invention extracts minutiae sets from a plurality of scanned fingerprint images, and separately stores the minutiae sets for one ID. Or the present invention stores one integrated minutiae set by removing redundant minutiae in the plurality of fingerprint images.
Further when a fingerprint is scanned two or more times and then stored, the similarity of minutiae of a new scanned fingerprint to minutiae extracted from an initially scanned fingerprint or one integrated minutiae set. If the similarity is equal to or larger than a specific value, the fingerprint is additionally registered.
Further, if the similarity between a fingerprint to be authenticated and a pre-registered fingerprint is equal to or larger than a predetermined ratio, and thus the fingerprints match, new minutiae different from pre-registered minutiae are additionally registered for an existing ID, even during fingerprint authentication in the present invention. Therefore, a more and more complete fingerprint minutiae set is produced along with use.
Although the preferred embodiments of the present invention have been described for illustrative purposes, those skilled in the art will appreciate that various modifications, additions and substitutions are possible, without departing from the scope and spirit of the invention as disclosed in the accompanying claims.
List of Reference Numerals
1000 Apparatus for controlling fingerprint registration and fingerprint
authentication
100 Similarity check and computation unit
200 Data set storage
300 Fingerprint registration and authentication controller

Claims (10)

  1. An apparatus for controlling fingerprint registration and fingerprint authentication, the apparatus comprising:
    a similarity check and computation unit configured to perform fingerprint registration in conjunction with fingerprint authentication through a fingerprint sensor, without separating the fingerprint registration from the fingerprint authentication, and to calculate a similarity between first fingerprint minutiae information extracted from a first fingerprint image scanned a first time and N th fingerprint minutiae information extracted from an N th fingerprint image scanned an N th time, during fingerprint registration of a selected one of fingers; and
    a fingerprint registration and authentication controller configured to, if the calculated similarity between the first fingerprint minutiae information and the N th fingerprint minutiae information is larger than a predetermined specific value, generate N' th fingerprint minutiae information by detecting minutiae information unique to the N th fingerprint minutiae information, and reflecting the detected minutiae information in the first fingerprint minutiae information, and to register the N' th fingerprint minutiae information for one identifier (ID), instead of the first fingerprint minutiae information,
    wherein the similarity check and computation unit is configured to calculate a similarity between the N' th fingerprint minutiae information, instead of the first fingerprint minutiae information, and (N+1) th fingerprint minutiae information extracted from an (N+1) th fingerprint image scanned an (N+1) th time.
  2. The apparatus according to claim 1, further comprising a data set storage configured to store the first fingerprint minutiae information or the N' th fingerprint minutiae information for the one ID.
  3. The apparatus according to claim 2, wherein the data set storage is configured to enhance the security of personal information by encrypting the fingerprint minutiae information by an encryption algorithm such as advanced encryption standard (AES), data encryption standard (DES), SEED, ARIA, or the like, storing the encrypted fingerprint minutiae information, decrypting the stored encrypted fingerprint minutiae information by the encryption algorithm such as AES, DES, SEED, ARIA, or the like, and using the decrypted minutiae information.
  4. The apparatus according to claim 2, wherein after the N' th fingerprint minutiae information obtained through N modifications is integrated by removing redundant minutiae information in N pieces of fingerprint minutiae information, the data set storage is configured to store the integrated data set for the one ID.
  5. The apparatus according to claim 1, wherein if the similarity between the N' th fingerprint minutiae information and the (N+1) th fingerprint minutiae information extracted from the (N+1) th fingerprint image scanned the (N+1) th time is larger than the specific value, the fingerprint registration and authentication controller is configured to perform the fingerprint authentication by using (N+1)' th fingerprint minutiae information in which unique minutiae information detected the (N+1) th time is reflected.
  6. A method of controlling an apparatus for controlling fingerprint registration and fingerprint authentication, the method comprising:
    performing fingerprint registration in conjunction with fingerprint authentication through a fingerprint sensor, without separating the fingerprint registration from the fingerprint authentication by a similarity check and computation unit;
    calculating a similarity between first fingerprint minutiae information extracted from a first fingerprint image scanned a first time and N th fingerprint minutiae information extracted from an N th fingerprint image scanned an N th time, during fingerprint registration of a selected one of fingers, by the similarity check and computation unit;
    if the calculated similarity between the first fingerprint minutiae information and the N th fingerprint minutiae information is larger than a predetermined specific value, generating N' th fingerprint minutiae information by detecting minutiae information unique to the N th fingerprint minutiae information, and reflecting the detected minutiae information in the first fingerprint minutiae information, by a fingerprint registration and authentication controller; and
    registering the N' th fingerprint minutiae information for one identifier (ID), instead of the first fingerprint minutiae information by the fingerprint registration and authentication controller.
  7. The method according to claim 6, further comprising calculating a similarity between the N' th fingerprint minutiae information, instead of the first fingerprint minutiae information, and (N+1) th fingerprint minutiae information extracted from an (N+1) th fingerprint image scanned an (N+1) th time by the similarity check and computation unit.
  8. The method according to claim 6, further comprising storing the first fingerprint minutiae information or the N' th fingerprint minutiae information for the one ID in a data set storage.
  9. The method according to claim 8, wherein the data set storage enhances the security of personal information by encrypting the fingerprint minutiae information by an encryption algorithm such as advanced encryption standard (AES), data encryption standard (DES), SEED, ARIA, or the like, storing the encrypted fingerprint minutiae information, decrypting the stored encrypted fingerprint minutiae information by the encryption algorithm such as AES, DES, SEED, ARIA, or the like, and using the decrypted minutiae information.
  10. The method according to claim 6, further comprising, if the similarity between the N' th fingerprint minutiae information and the (N+1) th fingerprint minutiae information extracted from the (N+1) th fingerprint image scanned the (N+1) th time is larger than the specific value, performing the fingerprint authentication by using (N+1)' th fingerprint minutiae information in which unique minutiae information detected the (N+1) th time is reflected, by the fingerprint registration and authentication controller.
PCT/KR2019/000985 2018-07-27 2019-01-23 Apparatus for controlling fingerprint registration and fingerprint authentication, and method of driving the same WO2020022597A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020180088106A KR101977539B1 (en) 2018-07-27 2018-07-27 Fingerprint registration and fingerprint authentication control device and Drive method of the same
KR10-2018-0088106 2018-07-27

Publications (1)

Publication Number Publication Date
WO2020022597A1 true WO2020022597A1 (en) 2020-01-30

Family

ID=67775470

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2019/000985 WO2020022597A1 (en) 2018-07-27 2019-01-23 Apparatus for controlling fingerprint registration and fingerprint authentication, and method of driving the same

Country Status (2)

Country Link
KR (1) KR101977539B1 (en)
WO (1) WO2020022597A1 (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20220008625A (en) 2020-07-14 2022-01-21 김창일 User authentication system
KR20220117540A (en) * 2021-02-17 2022-08-24 삼성전자주식회사 Electronic device having fingerprint sensor and method for updating fingerprint information thereof

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10187987A (en) * 1996-12-26 1998-07-21 Sony Corp Image collating device
JP2001357371A (en) * 2000-06-13 2001-12-26 Sony Corp Hardware token with fingerprint collating function
JP2003030660A (en) * 2001-07-17 2003-01-31 Canon Inc Fingerprint collation device and fingerprint collation method
KR20080076204A (en) * 2007-02-15 2008-08-20 (주)휴제닉스 Portable fingerprint recognition and identificaion apparatus and method using the same
KR20170043404A (en) * 2015-10-13 2017-04-21 삼성전자주식회사 Electronic device and method for authenticating finger print

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100497226B1 (en) 2003-03-03 2005-06-23 학교법인 인하학원 Extraction and matching method of ridge number in finger identification system
KR20110048121A (en) 2009-11-02 2011-05-11 에스케이텔레콤 주식회사 Terminal and method for providing user interface using fingerprint identification
KR101632912B1 (en) 2014-09-26 2016-06-24 창신정보통신(주) Method for User Authentication using Fingerprint Recognition
KR101783816B1 (en) 2016-04-04 2017-10-12 중앙대학교 산학협력단 System and method for fingerprint authentication

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10187987A (en) * 1996-12-26 1998-07-21 Sony Corp Image collating device
JP2001357371A (en) * 2000-06-13 2001-12-26 Sony Corp Hardware token with fingerprint collating function
JP2003030660A (en) * 2001-07-17 2003-01-31 Canon Inc Fingerprint collation device and fingerprint collation method
KR20080076204A (en) * 2007-02-15 2008-08-20 (주)휴제닉스 Portable fingerprint recognition and identificaion apparatus and method using the same
KR20170043404A (en) * 2015-10-13 2017-04-21 삼성전자주식회사 Electronic device and method for authenticating finger print

Also Published As

Publication number Publication date
KR101977539B1 (en) 2019-08-28

Similar Documents

Publication Publication Date Title
WO2020022704A1 (en) Method for training and testing obfuscation network capable of processing data to be concealed for privacy, and training device and testing device using the same
US7039224B2 (en) Method and device for preventing false acceptance of latent fingerprint images
WO2013100699A1 (en) Method, apparatus, and computer-readable recording medium for authenticating a user
EP1990770B1 (en) Face authentication device, face authentication method, and program
JP5326527B2 (en) Authentication apparatus and authentication method
WO2022019693A1 (en) Decentralized identifier (did)-based non-face-to-face user authentication method using non-face-to-face user authentication verifiable credential (vc), and authentication support server using same
WO2013048160A1 (en) Face recognition method, apparatus, and computer-readable recording medium for executing the method
WO2015199501A1 (en) User authentication method and system using variable keypad and biometric identification
WO2017099427A1 (en) Convergent biometric authentication method based on finger joint and finger vein, and apparatus therefor
WO2015056979A1 (en) Security card having fingerprint authentication, processing system and processing method therefor
WO2020022597A1 (en) Apparatus for controlling fingerprint registration and fingerprint authentication, and method of driving the same
US11281922B2 (en) Face recognition system, method for establishing data of face recognition, and face recognizing method thereof
WO2022086147A1 (en) Method for training and testing user learning network to be used for recognizing obfuscated data created by obfuscating original data to protect personal information and user learning device and testing device using the same
WO2016108562A1 (en) Coding and recognition system of fingerprint information, and operation method therefor
WO1998025227A1 (en) Biometric security encryption system
Kalra et al. A survey on multimodal biometric
WO2021066252A1 (en) Biometrics-based vehicle control device and vehicle control method using same
WO2023096444A1 (en) Learning method and learning device for training obfuscation network capable of obfuscating original data for privacy and testing method and testing device using the same
KR20000030122A (en) user identification method using multi-biometric information and system thereof
Abdelouahed et al. A comparative study of anti-spoofing detection based on deep learning
WO2021060670A1 (en) Device and method for user authentication using security card
JPH0433065A (en) Fingerprint collating device
WO2023277210A1 (en) Smart door lock based on revocable biometric technology
JP2004355377A (en) Face image collation system and its method for distributing face image data
Oyetola et al. Secured biometrics-crypto authentication system over computer network

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: 19840096

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 06.07.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19840096

Country of ref document: EP

Kind code of ref document: A1