CN111709272B - Fingerprint acquisition method, identity authentication method and electronic device based on small-area fingerprint - Google Patents

Fingerprint acquisition method, identity authentication method and electronic device based on small-area fingerprint Download PDF

Info

Publication number
CN111709272B
CN111709272B CN202010339306.5A CN202010339306A CN111709272B CN 111709272 B CN111709272 B CN 111709272B CN 202010339306 A CN202010339306 A CN 202010339306A CN 111709272 B CN111709272 B CN 111709272B
Authority
CN
China
Prior art keywords
fingerprint
small
fingerprints
area
full
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010339306.5A
Other languages
Chinese (zh)
Other versions
CN111709272A (en
Inventor
汪秋云
姜政伟
李小萌
方舟
王栋
赵丽花
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guowang Xiongan Finance Technology Group Co ltd
State Grid Corp of China SGCC
Institute of Information Engineering of CAS
Information and Telecommunication Branch of State Grid Zhejiang Electric Power Co Ltd
Original Assignee
Guowang Xiongan Finance Technology Group Co ltd
State Grid Corp of China SGCC
Institute of Information Engineering of CAS
Information and Telecommunication Branch of State Grid Zhejiang Electric Power 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 Guowang Xiongan Finance Technology Group Co ltd, State Grid Corp of China SGCC, Institute of Information Engineering of CAS, Information and Telecommunication Branch of State Grid Zhejiang Electric Power Co Ltd filed Critical Guowang Xiongan Finance Technology Group Co ltd
Priority to CN202010339306.5A priority Critical patent/CN111709272B/en
Publication of CN111709272A publication Critical patent/CN111709272A/en
Application granted granted Critical
Publication of CN111709272B publication Critical patent/CN111709272B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
    • G06V10/464—Salient features, e.g. scale invariant feature transforms [SIFT] using a plurality of salient features, e.g. bag-of-words [BoW] representations
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Human Computer Interaction (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Collating Specific Patterns (AREA)

Abstract

The invention provides a fingerprint acquisition method, an identity authentication method and an electronic device based on a small-area fingerprint. The invention starts from the full fingerprint, selects the optimal part of the whole full fingerprint as much as possible as the authentication evidence, and has simple processing process and high processing speed.

Description

Fingerprint acquisition method, identity authentication method and electronic device based on small-area fingerprint
Technical Field
The present invention relates to the field of computer terminal security, and in particular, to a fingerprint acquisition method, an identity authentication method, and an electronic device based on a small-area fingerprint.
Background
Fingerprint authentication is a very long-history authentication technology, and can be traced back to tangsheng in China at the earliest time. The fingerprints, knuckle prints or palmprint are all found on many documents, contracts and heritage of Tang dynasty, which are liberated in China, and are taken as important means for identifying individuals. The custom of using finger-matrix and palm-matrix as authentication on the document is kept in the past generation. Ancient army in our country had "skip book", i.e. registered soldier fingerprints for inspection. This shows that fingerprints can be correctly classified according to morphology and structure at that time, and the classification characteristics and knowledge can be applied to social practice. The record of the fingerprint case breaking in China can also trace back the Qin generation more than two thousand years ago. The feasibility of fingerprints in identity authentication is undoubted.
Conventional fingerprint acquisition methods can be classified into two types, physical methods, i.e., using powder, magnetic powder or laser to visualize and record fingerprints, and chemical methods, i.e., using chemicals to acquire fingerprints through special images and fluorescence generated by chemical reactions.
With the development of computer technology, active collection and recognition of fingerprints become more and more convenient, such as optical recognition technology has been widely used, and fingerprint-based identity authentication is also applied to device locks of mobile devices such as entrance guard card punching, unlocking, mobile phones and the like, and even authentication during account registration of banks.
As the fingerprint identification device is smaller, many mobile devices such as mobile phones are added with fingerprint identification function, and identity authentication based on fingerprint identification becomes the preferred identity authentication mode for many applications. At present, support for fingerprint authentication is already realized for WeChat payment, payment bank payment and the like. For android devices, the addition of a Trusted Execution Environment (TEE) also provides hardware support for user fingerprint identification and protection. But different fingerprint identification devices have different identification modes, the collected fingerprints have different precision, and the identification algorithms have larger difference, so that the prior art has loopholes with different degrees.
Chinese patent application CN2017109201495 discloses a fingerprint image matching method based on selective extension, which uses minutiae and direction field information to match small fingerprint images, but uses mutually overlapped fingerprint image blocks to form a dc matrix, thereby increasing algorithm difficulty and affecting accuracy.
Researchers from universities in new york have successfully made "passfingerprints" using GAN, which can achieve a cracking rate of up to 76.67% for the device, and such passfingerprints occur mainly because the device must have a certain fault tolerance rate, and if the fault tolerance rate is too low, even the slightest deviation of the user-entered fingerprint will lead to recognition errors, while too high a fault tolerance rate is impractical.
Because the user's fingerprint will remain on the surface of some smooth objects, the security coefficient of the fingerprint is not even as high as 4-6 digit passcode for some scenes where a higher security level is required.
At present, a great deal of information of all fingerprints is lost in a processing mode of a great deal of existing small-area fingerprint technologies, so that the uniqueness of the small-area fingerprints is difficult to guarantee after the processing is finished. In the prior art, the distribution characteristics of the feature points on the small-area fingerprint are not considered, so that the data acquired on part of the fingerprints is possibly lack of effectiveness, and the user feature information is less, so that the identification accuracy is reduced, and the safety is reduced.
Disclosure of Invention
Aiming at the current situation and the existing problems, the invention provides a fingerprint acquisition method, an identity authentication method and an electronic device based on a small-area fingerprint, which are applicable to application scenes such as: single device authentication with fewer users, such as cell phones, personal computers; or each user can only verify on a specific few devices, such as a scientific research laboratory, etc., so that the full fingerprint information can be utilized to the greatest extent, and the processing speed of fingerprint verification is increased.
A fingerprint collection method based on a small-area fingerprint comprises the following steps:
1) Sequentially collecting a plurality of full fingerprints of a user, acquiring data of all characteristic points in the full fingerprints for each full fingerprint, and making an inscription matrix which takes the center point of the full fingerprint as the center and contains most of the characteristic points;
2) Convolving the inscription matrix, taking the corresponding position of each convolution result as each small-area fingerprint, selecting part or all of the small-area fingerprints, and calculating the distance between each selected small-area fingerprint and the center point of the full fingerprint;
3) And taking all feature point data in the selected small-area fingerprint, the distance between the selected small-area fingerprint and the center point of the full fingerprint, the number of the full fingerprints, the sequence of acquiring the full fingerprints and the user identification as the user fingerprint information.
Further, the ORB algorithm is used to acquire all feature point data in the full fingerprint.
Further, the feature point data includes position and type information of the feature points; the positions of the feature points are calculated according to a two-dimensional coordinate system taking the center point of the full fingerprint as the center.
Further, the inscription matrix is divided into a plurality of sub-matrices of the same shape and size, and convolved with a set receptive field and step size.
Further, a partial small area fingerprint is selected by:
1) Sorting all the small-area fingerprints from more to less according to the number of the characteristic points in each small-area fingerprint;
2) Calculating the Euclidean distance average value of each feature point in the small-area fingerprints with the same feature point number and other features in the small-area fingerprints, and sorting the small-area fingerprints with the same feature point number from large to small;
3) The first few small area fingerprints are sorted as part of the small area fingerprints.
Further, the Euclidean distance average value of each characteristic point in the selected small-area fingerprint and the full fingerprint center point is calculated, and the distance between the selected small-area fingerprint and the full fingerprint center point is obtained.
An identity authentication method based on a small-area fingerprint comprises the following steps:
1) Sequentially acquiring a plurality of full fingerprints of a user to be authenticated, searching user identifications corresponding to the same full fingerprints in the user fingerprint information according to the acquired number of the full fingerprints of the user to be authenticated, acquiring the full fingerprint sequence, selecting all characteristic point data in the small-area fingerprint and selecting the distance between the small-area fingerprint and the center point of the full fingerprint;
2) According to the sequence of collecting the full fingerprints, selecting the distance between the small-area fingerprints and the center point of the full fingerprints and acquiring the sequence of the full fingerprints of the user to be authenticated, matching all characteristic point data in the selected small-area fingerprints with the full fingerprints of the user to be authenticated, and judging whether the full fingerprints of the user to be authenticated are successfully matched according to the number of the successfully matched selected small-area fingerprints;
3) If the user to be authenticated successfully matches the full fingerprint, the user to be authenticated is judged to pass the identity authentication, and the login is carried out according to the user identification.
Further, if the number of the selected small-area fingerprints successfully matched is larger than or equal to the set number, the corresponding full fingerprints are successfully matched; if the number of the successfully matched selected small-area fingerprints is smaller than the set number, the corresponding full fingerprint matching fails.
A storage medium having a computer program stored therein, wherein the computer program performs the steps of the above method.
An electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the above method.
Compared with the prior art, the method provided by the invention has the following advantages and effects:
the invention starts from the full fingerprint, selects the optimal part of the whole full fingerprint as much as possible as the authentication evidence, and has simple processing process and high processing speed.
Drawings
FIG. 1 is an overall flow chart of a small area fingerprint based authentication method.
Fig. 2 is a schematic diagram of a fingerprint acquisition process.
Fig. 3 is a schematic diagram of a convolution process.
Fig. 4 is a schematic diagram of a fingerprint authentication process.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail by means of specific examples and accompanying drawings. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The overall flow of the present invention is shown in figure 1.
The invention firstly collects fingerprints based on small-area fingerprints and establishes a small-area fingerprint information database, as shown in figure 2.
When a user inputs a fingerprint, firstly, the center point of the fingerprint is positioned, the rectangular boundary of the fingerprint is determined, the rectangular area is divided into 4*4 areas, fingerprint feature points in the rectangle are convolved by 2 x 2 receptive fields and step sizes (1, 1), and the fingerprint of the user is sampled.
When the fingerprints are recorded, the user is required to record a plurality of fingerprints, the number of times is set by the user, and the fingerprints input each time can be different or the same. The order of entry is also required if it is different at the time of fingerprint verification. The recommended number of entries is 4-6, up to 8, and 3 different fingerprints are recommended.
Each entered full fingerprint corresponds to 6 small-area fingerprints, and the database is required to store the small-area fingerprints and the position information, the number, the sequence and the user identification of the small-area fingerprints relative to the center of the fingerprints.
The fingerprint acquisition steps are as follows:
in the first step, the user's full fingerprint is collected, and the number and order are determined by the user, where the number is denoted fn.
And secondly, taking out a full fingerprint input by a user, identifying a fingerprint center point, taking the fingerprint center point as a reference point, and identifying all characteristic points on the fingerprint by using a ORB (Oriented Brief) algorithm. The ORB algorithm is a more general image feature recognition algorithm.
In the third step, the feature points in the fingerprint are generally concentrated in an inverted U-shaped region, and an inscribed rectangle of the fingerprint is made in the region with the center point identified in the second step as the center, so that 90% of the feature points can be included.
Fourth, dividing the rectangle into 4 equal parts, and dividing the rectangle according to the standard to obtain 4*4 small rectangular areas with the same size. The receptive fields with the size of 2 x 2 rectangular areas are used, and are convolved according to the step length of (1, 1), so that 9 convolution results are obtained. As shown in fig. 3, R0, R1, R2, B0, B1, B2, G0, G1, G2 total 9 convolution results.
And fifthly, counting the distribution characteristics of the feature points in the 9 convolution results, firstly sequencing according to the number of the feature points, and calculating the Euclidean distance average value M of each feature point in the convolution result and other feature points in the convolution result for the same number of the feature points, wherein the average value is large. The position information of each sample relative to the center is recorded. Namely:
has r feature points, { N 0 ，N 1 ，N 2 ，…N r-1 }
Figure BDA0002467806060000041
Where d (x, y) is the Euclidean distance before two points, nn and Np represent two different feature points, respectively, n being unequal to p. And screening out small-area fingerprints with scattered characteristic points according to the index, so that the fault tolerance of the system can be improved. The first 6 small area fingerprints are selected and recorded with respect to their location information relative to the center point.
Repeating the second step to the fifth step until all fingerprints are processed completely.
Sixth, grouping the small-area fingerprint information, wherein each group is respectively 6: < small area fingerprint 1 data, location >, < small area fingerprint data, location > … < small area fingerprint 6 data, location >, one tag information is stored for each group, and can be set to be blank for single user authentication. The small-area fingerprint data refer to the position and type information of all feature points on the small-area fingerprint, and the position is given by an ORB algorithm, and the position refers to the position information of the whole small-area fingerprint relative to a fingerprint center reference point.
The user's fingerprint data of multiple pairs is stored in the database.
After the user fingerprint data is collected, processed and stored, the identity of the user can be verified based on the small-area fingerprint data of the user, when the fingerprint verification is performed, the verification module can receive 8 pieces of full fingerprint information input by the user at most, then the verification is performed according to the fingerprint information stored in the database, and if the input number of the user is not matched with the corresponding storage number or a certain small-area fingerprint group is not successfully matched, the verification fails. If and only if all succeeds, the verification is successful.
The authentication step is as shown in fig. 4:
the first step, the full fingerprint of the user is obtained according to the user input, the number and the input sequence are determined by the user input, and the number is marked as fn. There is no limitation in this regard.
And secondly, identifying the fingerprint center of the full fingerprint input by each user, and identifying all feature points by using an ORB algorithm.
And thirdly, traversing fingerprint data of all users in the database, taking out pre-stored fingerprint data of the users, and skipping matching if the number fn of fingerprints input by the users is not equal to the number of fingerprints pre-stored by the current users.
Fourth, if the number is equal, traversing each group of small area fingerprint data of the pre-stored user fingerprint data, starting from the first group, trying to match, if the matching fails, returning to the third step again, and selecting the next user to try to match. Since the data and the position relative to the center of each small area fingerprint in each group are recorded at the time of acquisition, the fingerprint to be verified does not need to be convolutionally sampled again. And during matching, sampling is performed on the fingerprint to be verified according to the center directly according to the position of the pre-stored small-area fingerprint data.
And fifthly, calculating matching scores of 6 small-area fingerprints pre-stored in each group and the sampled small-area fingerprints input from a user by using a Brute-Force Hamming Distance algorithm, wherein the algorithm is proposed by Macleod doctor in Telecommunications Engineer's Reference Book in 1993, and represents the number of different characters of two equal-length character strings at corresponding positions, and in this example, the two character strings are finally given by an ORB algorithm as a description for one feature point. The threshold is set to 30 (the optimal threshold observed by experiments), when the score is higher than 30, the current small-area fingerprint pair is not matched, when a group with more than 1 pair of small-area fingerprints is not matched, the fingerprint of the user to be verified is not matched with the prestored user, and the next user is tried. If each group of small-area fingerprints are successfully matched, the authentication process is finished, and the authentication is successful.
The ORB algorithm combined with the Brute-Force Hamming Distance algorithm has the advantages that the feature extraction speed is high, the matching result is reliable compared with other similar algorithms, and the reliability and the performance are both considered. While fault tolerance may be achieved by adjusting the threshold. The threshold value is the average Hamming Distance (Hamming Distance) between each matched feature, and the description of the feature point output is used as the output parameter for calculating the Hamming Distance during calculation.
And sixthly, if the fingerprint input by the user does not have a group of fingerprints prestored in the database and corresponds to the database, the authentication fails. If the pre-stored fingerprint data in the database are matched with the input, the authentication is successful.
The above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and those skilled in the art may modify or substitute the technical solution of the present invention without departing from the spirit and scope of the present invention, and the protection scope of the present invention shall be defined by the claims.

Claims (9)

1. A fingerprint collection method based on a small-area fingerprint comprises the following steps:
1) Sequentially collecting a plurality of full fingerprints of a user, acquiring data of all characteristic points in the full fingerprints for each full fingerprint, and making an inscription matrix which takes the center point of the full fingerprint as the center and contains most of the characteristic points;
2) Convolving the inscription matrix, taking the corresponding position of each convolution result as each small-area fingerprint, selecting partial small-area fingerprints, and calculating the distance between each selected small-area fingerprint and the center point of the full fingerprint; wherein, select partial small area fingerprint, include:
2.1 According to the number of the characteristic points in each small-area fingerprint, sequencing all the small-area fingerprints from more to less;
2.2 Calculating the Euclidean distance average value of each feature point in the small-area fingerprints with the same feature point number and other features in the small-area fingerprints, and sorting the small-area fingerprints with the same feature point number from large to small;
2.3 A plurality of small-area fingerprints before sorting are used as partial small-area fingerprints;
3) And taking all feature point data in the selected small-area fingerprint, the distance between the selected small-area fingerprint and the center point of the full fingerprint, the number of the full fingerprints, the sequence of acquiring the full fingerprints and the user identification as the user fingerprint information.
2. The method of claim 1, wherein the ORB algorithm is used to obtain all feature point data in the full fingerprint.
3. The method of claim 1, wherein the feature point data includes location and type information of feature points; the positions of the feature points are calculated according to a two-dimensional coordinate system taking the center point of the full fingerprint as the center.
4. The method of claim 1, wherein the inscription matrix is partitioned into a number of sub-matrices of the same shape and size, the inscription matrix being convolved using a set receptive field and step size.
5. The method of claim 1, wherein the euclidean distance average of each feature point in the selected small area fingerprint and the full fingerprint center point is calculated to obtain the distance between the selected small area fingerprint and the full fingerprint center point.
6. An identity authentication method based on a small-area fingerprint comprises the following steps:
1) Sequentially acquiring a plurality of full fingerprints of a user to be authenticated, searching user identifications corresponding to the same full fingerprint number in user fingerprint information obtained by the method according to any one of claims 1-5 according to the acquired full fingerprint number of the user to be authenticated, acquiring the full fingerprint sequence, selecting all feature point data in the small-area fingerprint and selecting the distance between the small-area fingerprint and the center point of the full fingerprint;
2) According to the sequence of collecting the full fingerprints, selecting the distance between the small-area fingerprints and the center point of the full fingerprints and acquiring the sequence of the full fingerprints of the user to be authenticated, matching all characteristic point data in the selected small-area fingerprints with the full fingerprints of the user to be authenticated, and judging whether the full fingerprints of the user to be authenticated are successfully matched according to the number of the successfully-matched selected small-area fingerprints;
3) If the user to be authenticated successfully matches the full fingerprint, judging that the user to be authenticated passes identity authentication.
7. The method of claim 6, wherein if the number of the selected small-area fingerprints successfully matched is greater than or equal to a set number, then the full fingerprints of the user to be authenticated are successfully matched; if the number of the successfully matched selected small-area fingerprints is smaller than the set number, the full fingerprint matching of the user to be authenticated fails.
8. A storage medium having a computer program stored therein, wherein the computer program is arranged to perform the method of any of claims 1-7 when run.
9. An electronic device comprising a memory, in which a computer program is stored, and a processor arranged to run the computer program to perform the method of any of claims 1-7.
CN202010339306.5A 2020-04-26 2020-04-26 Fingerprint acquisition method, identity authentication method and electronic device based on small-area fingerprint Active CN111709272B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010339306.5A CN111709272B (en) 2020-04-26 2020-04-26 Fingerprint acquisition method, identity authentication method and electronic device based on small-area fingerprint

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010339306.5A CN111709272B (en) 2020-04-26 2020-04-26 Fingerprint acquisition method, identity authentication method and electronic device based on small-area fingerprint

Publications (2)

Publication Number Publication Date
CN111709272A CN111709272A (en) 2020-09-25
CN111709272B true CN111709272B (en) 2023-05-16

Family

ID=72536365

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010339306.5A Active CN111709272B (en) 2020-04-26 2020-04-26 Fingerprint acquisition method, identity authentication method and electronic device based on small-area fingerprint

Country Status (1)

Country Link
CN (1) CN111709272B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104021374A (en) * 2014-05-28 2014-09-03 上海思立微电子科技有限公司 Fingerprint sensor array
CN107392082A (en) * 2017-04-06 2017-11-24 杭州景联文科技有限公司 A kind of small area fingerprint comparison method based on deep learning
CN108520225A (en) * 2018-03-30 2018-09-11 南京信息工程大学 A kind of fingerprint detection sorting technique based on spatial alternation convolutional neural networks

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3679953B2 (en) * 1999-09-14 2005-08-03 富士通株式会社 Personal authentication system using biometric information
KR102027112B1 (en) * 2016-07-05 2019-10-01 주식회사 슈프리마 Method and apparatus for fingerprint recognition

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104021374A (en) * 2014-05-28 2014-09-03 上海思立微电子科技有限公司 Fingerprint sensor array
CN107392082A (en) * 2017-04-06 2017-11-24 杭州景联文科技有限公司 A kind of small area fingerprint comparison method based on deep learning
CN108520225A (en) * 2018-03-30 2018-09-11 南京信息工程大学 A kind of fingerprint detection sorting technique based on spatial alternation convolutional neural networks

Also Published As

Publication number Publication date
CN111709272A (en) 2020-09-25

Similar Documents

Publication Publication Date Title
Louloudis et al. ICDAR 2011 writer identification contest
US8977648B2 (en) Fast and robust classification algorithm for vein recognition using infrared images
JP2010286937A (en) Biometric authentication method, client terminal used for biometric authentication, and authentication server
Hemalatha A systematic review on Fingerprint based Biometric Authentication System
JP5710748B2 (en) Biometric authentication system
US8914313B2 (en) Confidence based vein image recognition and authentication
Okokpujie et al. Comparative analysis of fingerprint preprocessing algorithms for electronic voting processes
US9436780B2 (en) Constructing incremental tree model for vein image recognition and authentication
CN113128504A (en) OCR recognition result error correction method and device based on verification rule
CN111709272B (en) Fingerprint acquisition method, identity authentication method and electronic device based on small-area fingerprint
CN111259894A (en) Certificate information identification method and device and computer equipment
Pradeep et al. An efficient machine learning approach for fingerprint authentication using artificial neural networks
WO2018096052A1 (en) A quick match algorithm for biometric data
JP2002297549A (en) Individual identification system and program
Sandhya et al. Revocable iris templates using partial sort and randomised look-up table mapping
EP3093793A1 (en) Fingerprint identification method and device using same
Kumar et al. An efficient gravitational search decision forest approach for fingerprint recognition
Sharma et al. Fingerprint matching Using Minutiae Extraction Techniques
Palys et al. Statistical analysis in signature recognition system based on Levenshtein distance
Butt et al. Correlation-resistant fuzzy vault for fingerprints
Kavati et al. Efficient biometric indexing and retrieval techniques for large-Scale systems
Hummel et al. Authentication Using Biometrics: How to Prove Who You Are
Mahesh et al. Biometric System: Unimodal Versus Multibiometric Fusion and Its Current Applications
Jain et al. A Non-Invertible Cancellable Fingerprint Template for Low-Quality Fingerprints
Multani et al. Computational Methods for Analysing Biometric Systems

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant