CN101482921A - Fingerprint identification method - Google Patents
Fingerprint identification method Download PDFInfo
- Publication number
- CN101482921A CN101482921A CNA2008102340642A CN200810234064A CN101482921A CN 101482921 A CN101482921 A CN 101482921A CN A2008102340642 A CNA2008102340642 A CN A2008102340642A CN 200810234064 A CN200810234064 A CN 200810234064A CN 101482921 A CN101482921 A CN 101482921A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- image
- characteristic
- data
- template
- 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.)
- Pending
Links
Images
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The invention relates to a fingerprint identification method which comprises: (1) reading fingerprint: reading an image of somatic fingerprint through a fingerprint reading device, and processing the image to make the fingerprint clear; (2) extracting feature: establishing future data of the fingerprint image, and converting the fingerprint image into the future data to form a templet; (3) extracting the stored fingerprint data: extracting the fingerprint data templet in a pre-stored fingerprint database; (4) comparing: comparing the read fingerprint feature data templet with the fingerprint data in the fingerprint database, calculating the similarity degree, and finally obtaining a matching result of the two fingerprints. The method of the invention has the advantages of low misclassification rate, cross-hardware platform, strong recognition capability, etc., has the phony finger recognition performance, can satisfy various novel embedded fingerprint recognition platform softwares with different application demands, and thereby forming the common technology base to industrialize and commercialize products with various categories and varieties which aim at different user demands.
Description
Technical field
The present invention relates to a kind of safety recognizing method, specifically relate to a kind of fingerprint identification method.
Background technology
Enter 21 century, reasonable growth momentum has also appearred in domestic fingerprint recognition market.At the fingerprint recognition traditional market, all keep ratio growth rate faster as fingerprint attendance, fingerprint gate lock, fingerprint gate lock and fingerprint safe etc.The enterprise that has the fingerprint recognition core technology carries out the fingerprint identification technology application innovation audaciously, makes fingerprint recognition market present in riotous profusion more colorful situation.Wherein, it with Zhejiang Weier Technology Co., Ltd. representative; the enterprise that has the fingerprint recognition core technology; fingerprint identification technology is generalized to fields such as finance, traffic, ecommerce; and form the application of scale rapidly; promoting the development of whole fingerprint recognition industry, is the maximum bright spot of fingerprint recognition application innovation in recent years.The wherein the most representative application that is the fingerprint recognition technology at financial field and field of traffic.For example, along with Zhejiang Weier Technology Co., Ltd. have patent of invention, and endeavour the bank cashier identity fingerprint recognition system promoted always and popularize in an all-round way in China Construction Bank and use, promoted the application of fingerprint identification technology in the financial field.And field of traffic fingerprint recognition market is developed and guided to the driver training finger print management system of Zhejiang Weier Technology Co., Ltd. exploitation in Zhejiang Province and the popularization in the whole nation.
Fingerprint technique is in the successful Application of high-end industries such as finance, traffic, not only enlarged fingerprint technique and used scale, most importantly promoted the understanding of the public to fingerprint identification technology, and distance between the fingerprint identification technology and the public furthers.Can expect that fingerprint identification technology will progressively be walked out traditional application, the fingerprint identification technology application innovation will be that following fingerprint identification technology is used topmost growth point.
The application of fingerprint identification technology will be fingerprint technology new growth point in safety-security area is used, and the coming years, some following applications will obtain development at a high speed:
(1) fingerprint technique is in Application in E-Commerce
Popularizing of internet, shopping online, online transaction, online payment, net fun popular, the safety problem in the ecommerce has been subjected to widely and has paid close attention to, and also the application for fingerprint identification technology provides reasonable development space.Using access control problem and identity validation problem in the fingerprint identification technology solution E-business applications, will be next step fingerprint identification technology priority application in e-commerce system.
(2) fingerprint technique is the emphasis application industry of security product in financial fields such as the application bank of financial fields such as bank, security, security always.
In the financial field, along with the all-round popularization of bank cashier identity fingerprint Verification System is used, especially China Construction Bank promotes teller's fingerprint identity validation system at full row, with the application that advances fingerprint identification technology at the financial industry other field.
Aspect bank's internal control and inner management, except that present already used bank cashier identity authorization system, fingerprint is escorted system, fingerprint two sect control system, fingerprint national treasury gate control system will progressively be admitted and obtain uses; In the application facet towards bank client, fingerprint identification technology will progressively be applied to the authenticating user identification of links such as savings, ATM automated teller machine withdrawal; The fingerprint POS machine will progressively replace traditional POS that swipes the card, and the fingerprint payment will progressively replace the payment of swiping the card, and fingerprint USBKey digital certificate will progressively replace traditional USBKey digital certificate.In enterprise network goes to bank, also will introduce the authentication that fingerprint identification technology carries out operating personnel.
(3) application of fingerprint technique field of traffic
Fingerprint technique will be by also more single driver training finger print management system at present in the application of field of traffic, progressively expands to automobile travel recorder based on fingerprint, demonstrate,proves management, the management based on the special car of fingerprint, a plurality of applications such as driver identity finger print identifying in the traffic logistics system based on the working qualification of fingerprint technique.
(4) application of fingerprint technique in electronic government affairs system, the enterprises office automation system
The electronic government affairs system and the enterprises office automation system also will be the major fields that the fingerprint recognition technology is used.Aspect system's access control, turnover network system, turnover computer system, turnover electronic government affairs system or the office automation system all can adopt the fingerprint identity validation mode; Aspect identity validation, will use the fingerprint E-seal to carry out identity validation.
But existing fingerprint identification technology has misclassification rate does, can not stride the defective that hardware platform uses, recognition speed is slow, recognition capability is not strong, does not have the prosthetic finger recognition function simultaneously.
Summary of the invention
For solving the deficiencies in the prior art, the object of the present invention is to provide a kind of new fingerprint identification method, the accuracy rate of fingerprint recognition is improved, the speed of being parted by death improves, recognition capability is strengthened.
For achieving the above object, the present invention is achieved by the following technical solutions:
A kind of fingerprint identification method is characterized in that may further comprise the steps:
(1), reads fingerprint: read the image of somatic fingerprint by the fingerprint fetch equipment, get after the finger print image, the original fingerprint image is carried out preliminary processing, make fingerprint clear;
(2), extract feature: set up the characteristic of fingerprint image, convert fingerprint image to characteristic, form a template;
(3), extract the finger print data of being preserved: data template takes the fingerprint in the fingerprint database that stores in advance;
(4), comparison: the fingerprint characteristic data template that read and the finger print data in the fingerprint database are compared,, the template of two fingerprints is compared, calculate their similarity degree, finally obtain the matching result of two fingerprints by relatively fuzzy.
Aforesaid fingerprint identification method is characterized in that converting fingerprint image to characteristic described in the step 2, is unidirectional conversion, can not convert fingerprint to from characteristic.
Aforesaid fingerprint identification method, it is characterized in that in the step 2, when carrying out fingerprint image to the conversion of characteristic, find the bifurcated of fingerprint lines, the coordinate position that stops or loop from fingerprint, each coordinate position has the uniqueness characteristic more than 7 kinds, and these features are formed a template.
Aforesaid fingerprint identification method is characterized in that the directional information of described coordinate position and this coordinate position is combined, and forms a template jointly.
Aforesaid fingerprint identification method is characterized in that whole fingerprint image is handled.
The invention has the beneficial effects as follows: the present invention have misclassification rate low, stride hardware platform, recognition speed height, recognition capability strong, possess advantage such as prosthetic finger recognition performance, and can satisfy the novel embedded fingerprint recognition flatbed software of different application demand, and as the common technology basis, industrialization and commercialization are at multi-class, the multi-assortment production of different user demands.
Description of drawings
Fig. 1 is the process flow diagram of fingerprint identification method of the present invention;
Fig. 2 is the process flow diagram of application examples of the present invention.
Embodiment
Below in conjunction with accompanying drawing the present invention is done concrete introduction:
Fig. 1 is the process flow diagram of fingerprint identification method of the present invention; Fig. 2 is the process flow diagram of application examples of the present invention.
As shown in the figure, fingerprint identification method of the present invention relates generally to four functions: read finger print image, extract feature, extract the finger print data and the comparison of being preserved.
At the beginning, read the image of somatic fingerprint by the fingerprint fetch equipment, get after the finger print image, carry out preliminary processing to the original fingerprint image, make it more clear.
Next, identification of fingerprint software is set up the numeral of fingerprint---characteristic, this is a kind of unidirectional conversion, can convert characteristic to from fingerprint but can not be converted into fingerprint from characteristic, and two pieces of different fingerprints can not produce identical characteristic.Software finds from fingerprint and is called as " node " data point (minutiae), just the bifurcated of those fingerprint lines, stop or the coordinate position at the place that loops, these points have uniqueness characteristic more than seven kinds simultaneously.Because on average have 70 nodes on the finger usually, so this method can produce about 490 data.
Simultaneously, can node and directional information combination results more data, these directional informations have shown the relation between each node, can also handle the view picture fingerprint image.In a word, these data are commonly referred to template, save as the record of 1K size.
At last,, the template of two fingerprints is compared, calculate their similarity degree, finally obtain the matching result of two fingerprints by the method for system ambiguous comparison.
The concrete following characteristics of the present invention:
1, the built-in Linux that adopts open source code is supported most of hardware platforms as the bottom operation platform, finishes the embedded platformization of fingerprint recognition kernel software.Can form a series of fingerprint recognition application product through very simple secondary development on this platform.
2, at child in domestic. applications and old man's a fingerprint recognition difficult problem, the present invention has proposed the deformation model of registration pattern innovatively, has effectively solved the inferior quality fingerprint image of a large amount of existence and the deformation problems of fingerprint.
3, in the domestic. applications, not high to quantity and rate request, and the demand that identification percent of pass and accuracy of system identification are had higher requirements, the present invention comprehensively adopts artificial intelligence and small echo and mathematical tool such as fractal first, and the mode that adopts unique point and pattern recognition to combine solves this difficult problem.
4, adopt open System Design, can load multiple algorithm for recognizing fingerprint, integrated a large amount of international standard fingerprint databases adopt international biological characteristic interface standard BioAPI1.0, are the basic software platforms that a cover is used for algorithm for recognizing fingerprint and relative application software exploitation.
The present invention have misclassification rate low, stride hardware platform, recognition speed height, recognition capability strong, possess gordian technique such as prosthetic finger recognition performance, and can satisfy the novel embedded fingerprint recognition flatbed software of different application demand, and as the common technology basis, industrialization and commercialization are at multi-class, the multi-assortment production of different user demands:
A, professional fingerprint access control series: mainly contain the fingerprint recognition interlock door system, the fingerprint recognition national treasury door system that are applied in financial industry; And be applied in the prison fingerprint entrance guard system of army and judicial industry and army's armament depot fingerprint entrance guard system etc.
B, home intelligence product line: based on the home intelligence product (fingerprint recognition home intelligence terminal) of fingerprint recognition, on the basis of embedded fingerprint identification kernel software, Smart Home functions such as extending and send that fingerprint opens the door, burglar alarm, flash appeal, estate management, three tables are made a copy for belongs to market vacancy product.
The foregoing description does not limit the present invention in any form, and the technical scheme that mode obtained that all employings are equal to replacement or equivalent transformation all drops in protection scope of the present invention.
Claims (5)
1, fingerprint identification method is characterized in that may further comprise the steps:
(1), reads fingerprint: read the image of somatic fingerprint by the fingerprint fetch equipment, get after the finger print image, the original fingerprint image is carried out preliminary processing, make fingerprint clear;
(2), extract feature: set up the characteristic of fingerprint image, convert fingerprint image to characteristic, form a template;
(3), extract the finger print data of being preserved: data template takes the fingerprint in the fingerprint database that stores in advance;
(4), comparison: the fingerprint characteristic data template that read and the finger print data in the fingerprint database are compared,, the template of two fingerprints is compared, calculate their similarity degree, finally obtain the matching result of two fingerprints by relatively fuzzy.
2, fingerprint identification method according to claim 1 is characterized in that converting fingerprint image to characteristic described in the step 2, is unidirectional conversion, can not convert fingerprint to from characteristic.
3, fingerprint identification method according to claim 1, it is characterized in that in the step 2, when carrying out fingerprint image to the conversion of characteristic, find the bifurcated of fingerprint lines, the coordinate position that stops or loop from fingerprint, each coordinate position has the uniqueness characteristic more than 7 kinds, and these features are formed a template.
4, fingerprint identification method according to claim 3 is characterized in that the directional information of described coordinate position and this coordinate position is combined, and forms a template jointly.
5, according to claim 3 or 4 described fingerprint identification methods, it is characterized in that whole fingerprint image is handled.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2008102340642A CN101482921A (en) | 2008-11-20 | 2008-11-20 | Fingerprint identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2008102340642A CN101482921A (en) | 2008-11-20 | 2008-11-20 | Fingerprint identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101482921A true CN101482921A (en) | 2009-07-15 |
Family
ID=40880022
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2008102340642A Pending CN101482921A (en) | 2008-11-20 | 2008-11-20 | Fingerprint identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101482921A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101807246A (en) * | 2010-03-17 | 2010-08-18 | 上海大学 | Multi-character vivo identification method and device |
| CN102004903A (en) * | 2010-11-17 | 2011-04-06 | 深圳市中控生物识别技术有限公司 | Anti-counterfeiting fingerprint identification device and fingerprint identification method |
| WO2011082604A1 (en) * | 2010-01-07 | 2011-07-14 | 华为终端有限公司 | Method, equipment and mobile terminal for fingerprint identification |
| CN102446271A (en) * | 2010-10-08 | 2012-05-09 | 金佶科技股份有限公司 | Sectional type image identification method and regional type identification device thereof |
| CN102685124A (en) * | 2012-05-07 | 2012-09-19 | 成都国腾实业集团有限公司 | Cloud-terminal user recognizer |
| CN104798311A (en) * | 2013-10-18 | 2015-07-22 | Lg电子株式会社 | Mobile terminal and control method thereof |
| CN105589446A (en) * | 2016-01-22 | 2016-05-18 | 潘玲玉 | Detection and alarm system for status in KTV room |
-
2008
- 2008-11-20 CN CNA2008102340642A patent/CN101482921A/en active Pending
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011082604A1 (en) * | 2010-01-07 | 2011-07-14 | 华为终端有限公司 | Method, equipment and mobile terminal for fingerprint identification |
| CN101807246A (en) * | 2010-03-17 | 2010-08-18 | 上海大学 | Multi-character vivo identification method and device |
| CN102446271A (en) * | 2010-10-08 | 2012-05-09 | 金佶科技股份有限公司 | Sectional type image identification method and regional type identification device thereof |
| CN102004903A (en) * | 2010-11-17 | 2011-04-06 | 深圳市中控生物识别技术有限公司 | Anti-counterfeiting fingerprint identification device and fingerprint identification method |
| CN102004903B (en) * | 2010-11-17 | 2013-07-10 | 深圳市中控生物识别技术有限公司 | Anti-counterfeiting fingerprint identification device and fingerprint identification method |
| CN102685124A (en) * | 2012-05-07 | 2012-09-19 | 成都国腾实业集团有限公司 | Cloud-terminal user recognizer |
| CN104798311A (en) * | 2013-10-18 | 2015-07-22 | Lg电子株式会社 | Mobile terminal and control method thereof |
| US10444890B2 (en) | 2013-10-18 | 2019-10-15 | Lg Electronics Inc. | Mobile terminal and control method thereof |
| CN105589446A (en) * | 2016-01-22 | 2016-05-18 | 潘玲玉 | Detection and alarm system for status in KTV room |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101482921A (en) | Fingerprint identification method | |
| CN108229427B (en) | Identity security verification method and system based on identity document and face recognition | |
| Coetzer et al. | Offline signature verification using the discrete radon transform and a hidden Markov model | |
| CN100385449C (en) | Method and system for automatic recognizing idnetity document of leaving and entering a country as well as fingerprint of biological living body | |
| Frias-Martinez et al. | Support vector machines versus multi-layer perceptrons for efficient off-line signature recognition | |
| CN103077459A (en) | Method for carrying out living body authentication and payment by fusing multi-biometric features of user | |
| CN102904885B (en) | Compound authentication method of multi-identity authentication information feature | |
| CN100458829C (en) | Identify authentication system and method employing wireless RF card and fingerprint recognition | |
| CN102831403B (en) | A kind of recognition methods based on fingerprint feature point | |
| CN103886283A (en) | Method for fusing multi-biometric image information for mobile user and application thereof | |
| CN103218621B (en) | The recognition methods of multiple dimensioned vehicle in a kind of life outdoor videos monitoring | |
| CN105528572A (en) | Fingerprint identification method | |
| Malik et al. | A signature verification framework for digital pen applications | |
| CN101145198A (en) | Certainty coding method and system in fingerprint identification | |
| Liu et al. | Fingerprint pore matching using deep features | |
| CN103440480A (en) | Non-contact palmprint recognition method based on palmprint image registration | |
| CN101178767A (en) | Recognizing layer amalgamation for human face and iris mixed recognition | |
| Garhawal et al. | A study on handwritten signature verification approaches | |
| Tan et al. | A robust two step approach for fingerprint identification | |
| Ng et al. | Adjacent orientation vector based fingerprint minutiae matching system | |
| CN102354367A (en) | Fingerprint identification card and fingerprint identification method running on card | |
| CN103593660A (en) | Palm print recognition method based on cross gradient encoding of image with stable characteristics | |
| CN105488473A (en) | Multi-feature fusion-based massive fingerprint coding and comparing method | |
| CN201984530U (en) | Automatic networking verification system for blank client identities | |
| Tan et al. | Fingerprint verification using genetic algorithms |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20090715 |