CN105808747A - Method for quickly searching and comparing fingerprint data by using multidimensional technology - Google Patents
Method for quickly searching and comparing fingerprint data by using multidimensional technology Download PDFInfo
- Publication number
- CN105808747A CN105808747A CN201610142400.5A CN201610142400A CN105808747A CN 105808747 A CN105808747 A CN 105808747A CN 201610142400 A CN201610142400 A CN 201610142400A CN 105808747 A CN105808747 A CN 105808747A
- Authority
- CN
- China
- Prior art keywords
- multidimensional
- finger print
- print data
- technology
- fingerprint data
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2228—Indexing structures
- G06F16/2264—Multidimensional index structures
Abstract
The invention discloses a method for quickly searching and comparing fingerprint data by using a multidimensional technology, and relates to the fingerprint verification technology. A fingerprint data storage, query and verification method in a multidimensional way is adopted, which mainly comprises three aspects: storing multidimensional fingerprint data, searching the multidimensional fingerprint data, and verifying the multidimensional fingerprint data. According to the method for quickly searching and comparing the fingerprint data by using the multidimensional technology provided by the invention, the fingerprint data volume can be reduced, and the storage capacity and network transmission speed can be reduced; the index way is more flexible, the index efficiency is higher, and the result is more precise; the verification speed is substantially improved and the verification result is more accurate, so that the retrieval work of large-scale fingerprint data can be greatly optimized.
Description
Technical field
The present invention relates to fingerprint authentication technology, particularly relate to a kind of method using multidimensional technology to carry out quick finger print data inquiry and contrast.
Background technology
Along with the fast development of Internet technology, traditional ID/ key verification means are difficult to ensure the personal secrets of user.Therefore, under the promotion of a lot of emerging safety certification patterns, fingerprint is increased gradually as the Related product of verification means, and uses the user of this kind of method of calibration to also begin to substantial increase.
In these verification authentication means, some adopts locally stored mode to store the/finger print data of verified users, but also has the finger print data of the form centralized management user needing to use the network storage greatly, as: police personal information database etc..Adopting in the data base of concentrated management in this part, encountered greatest problem is exactly the check problem of data.Particularly interconnect in internet data strange land, under the major premise of intercommunication, how to retrieve hundreds of millions of finger print datas effectively and rapidly and just become insoluble huge difficult problem in relevant industries.
Although under existing finger prints processing pattern, there is the method being much indexed with fingerprint image characteristics data, retrieve and verifying, but these methods exist the coarse problem of check results mostly.Particularly in the quick retrieval system that some are comparatively succinct for the characteristic indexed, in order to one-sidedness pursue the lifting of inquiry velocity, the design of a lot of related algorithms all deliberately simplifies the identification feature quantity of finger print data, so that the probability of misrecognized is significantly increased, eventually reduce experience and the product quality of product.
Summary of the invention
The present invention is directed to current needs and the weak point of prior art development, it is provided that a kind of method using multidimensional technology to carry out quick finger print data inquiry and contrast.
A kind of method using multidimensional technology to carry out quick finger print data inquiry and contrast of the present invention, the technical scheme solving the employing of above-mentioned technical problem is as follows: the multidimensional technology of described use carries out the method for quick finger print data inquiry and contrast, the finger print data adopting multidimensional mode stores, inquires about and method of calibration, it mainly includes three aspects: store multidimensional finger print data, retrieve multidimensional finger print data, and verify multidimensional finger print data.
Preferably, the multidimensional finger print data of described storage, refer to use binary code storage finger print data.
Preferably, if the pixel of each lines process is 1 in fingerprint image, blank space is 0, finger print data is substituted in data space coordinate system, each spatial value is initialized as the binary data stream being made up of 0 and 1, then the texture structure of fingerprint image may finally be converted to 0010110111 ... binary data so intuitively.
Preferably, the multidimensional finger print data of described retrieval, refer to retrieval multidimensional characteristic coordinate data.
Preferably, quick indexing, the relevant fingerprint in location are come by the mode of definition coordinates regional.
Preferably, the multidimensional finger print data of described verification, refer to the feature verification being accurate to each grain details.
A kind of method using multidimensional technology to carry out quick finger print data inquiry and contrast of the present invention, compared with prior art have the beneficial effect that when the present invention proposes a kind of solution extensive finger print data process, processing speed is effective ways comparatively slowly, adopt the storage of multidimensional fingerprint and identification technology, reduce finger print data volume, reduce memory capacity and network transfer speeds；Indexed mode is more flexible, and index efficiency is higher, and result is more accurate；Verification speed is greatly improved, and check results is more accurate；So that the retrieval work of large-scale finger print data is greatly optimized.
The multidimensional technology of use of the present invention carries out the method for quick finger print data inquiry and contrast, it is mainly used to optimize internet safety identification, personal security's information retrieval, and the storage in police finger print information storehouse, inquiry and verifying work, time that associative operation need wait is greatly reduced under the premise not promoting hardware resource, significantly promote the retrieval rate of Related product, the cost thus realizing economizing on resources, improves the purpose of Consumer's Experience.
Figure of description
Accompanying drawing 1 is multidimensional fingerprint image schematic diagram.
Detailed description of the invention
For making the object, technical solutions and advantages of the present invention clearly understand, below in conjunction with specific embodiment, a kind of method using multidimensional technology to carry out quick finger print data inquiry and contrast of the present invention is further described.
For problems of the prior art, under the premise reducing retrieval data total amount, accomplish not reduce uniqueness and the recall precision of check results, the present invention proposes the method using multidimensional technology to carry out quick finger print data inquiry and contrast, it is mainly used to solve the problem that during high-volume finger print data retrieval, system latency time is long, adopt the storage of multidimensional fingerprint and identification technology, significantly improve the storage of finger print data, retrieval and recognition efficiency, it is mainly used in the proof of identity in bank, internet industry and the relevant verification work etc. of police data base.
It is commonly performed finger print data to process, including three aspects respectively, stores finger print data, retrieval finger print data and verification finger print data.Wherein, described storage finger print data, is that the patterned feature of fingerprint is carried out image conversion storage；Do so finger print data preserves complete, image resolution ratio more high then more clear accurately, but the data that picture format preserves are relatively big, identify comparatively difficulty, are not suitable for high-volume storage.Described retrieval finger print data, refers to the fingerprint characteristic of inquiry and source fingerprint matches；Do so can set up multiple index for finger print data, improves data retrieval speed, but condition code algorithm exists a degree of deviation, it is possible to causes retrieval result wrong.Described verification finger print data, refers to matching relationship and the similarity degree of verification fingerprint lines；So along with the lifting of algorithm complex, it is possible to accurately mate the minutia of each lines, but computational complexity is higher, computing cost is big, is not suitable for using in mega project.
Embodiment:
The present embodiment is used the method that multidimensional technology carries out quick finger print data inquiry and contrast, overcome the defect existed in existing finger print data processing method, it mainly includes three aspects: store multidimensional finger print data, retrieves multidimensional finger print data, and verifies multidimensional finger print data.The method adopts the finger print data storage of multidimensional mode, inquiry and method of calibration, centesimal the retrieval rate of data is improve nearly thousand times data volume being reduced to, it is possible to solve the problem that during high-volume finger print data retrieval, system latency time is longer simultaneously.
In the method for finger print data inquiry and contrast described in the present embodiment, the multidimensional finger print data of described storage, refer to use binary code storage finger print data；As shown in Figure 1, if the pixel of each lines process is 1 in fingerprint image, blank space is 0, finger print data is substituted in data space coordinate system, each spatial value is initialized as the binary data stream being made up of 0 and 1, then the texture structure of fingerprint image may finally be converted to 0010110111 ... binary data so intuitively.Verification and the Main Basis of index finger print information generally it is not intended as so that use the method that most basic binary data directly characterizes fingerprint texture feature to be possibly realized due to the width index of fingerprint texture.After eliminating the unnecessary characteristic information such as picture color information and fingerprint texture width information, one of the finger print data volume of pure binary coding generally percentage only having identical content fingerprint image file.
In the method for finger print data inquiry and contrast described in the present embodiment, the multidimensional finger print data of described retrieval, refer to retrieval multidimensional characteristic coordinate data；From traditional approach, fingerprint texture characteristic is different as the method for search index, the method comes quick indexing, the relevant fingerprint in location by defining the mode of coordinates regional, as: the size carrying out classification fingerprint by adding up the area of fingerprint in effective coverage is indexed, this indexed mode is more flexible, index efficiency is higher, and result is more accurate.
In the method for finger print data inquiry and contrast described in the present embodiment, the multidimensional finger print data of described verification, refer to the feature verification being accurate to each grain details.All fingerprint texture data are done due to any algorithm for recognizing fingerprint a degree of abstract and mathematical operation, and these processes can exist a degree of error all unavoidably so that these methods have all existed recognition result and there is the probability of deviation.In the present embodiment, the result of multidimensional finger print data is one group of binary data, calculates unrelated to the verifying work of these group data with complicated data, also avoids the probability of error produced therefrom.Then the accurate coupling of contrast fingerprint texture structure, not only versus speed is improved, and the result contrasted is also more accurate.
Using the method that multidimensional technology carries out quick finger print data inquiry and contrast described in the present embodiment, its specific implementation process is as follows:
Step 1: start multidimensional finger print data recognizer, reads the finger print data needing to identify；
Step 2: the finger print data under image state is loaded in multi-dimensional data space, and is converted to binary data；
Step 3: taking-up fingerprint character code is set according to user index, and sends data retrieval request；
Step 4: receive retrieval request result.
Detailed description of the invention is only the concrete case of the present invention; the scope of patent protection of the present invention includes but not limited to above-mentioned detailed description of the invention; claims of any present invention of meeting and any person of an ordinary skill in the technical field to its suitably change done or replaces, and all should fall into the scope of patent protection of the present invention.
Claims (6)
1. one kind uses the method that multidimensional technology carries out quick finger print data inquiry and contrast, it is characterized in that, the finger print data adopting multidimensional mode stores, inquires about and method of calibration, it mainly includes three aspects: store multidimensional finger print data, retrieve multidimensional finger print data, and verify multidimensional finger print data.
2. a kind of method using multidimensional technology to carry out quick finger print data inquiry and contrast according to claim 1, it is characterised in that the multidimensional finger print data of described storage, refers to use binary code storage finger print data.
3. a kind of method using multidimensional technology to carry out quick finger print data inquiry and contrast according to claim 2, it is characterized in that, if the pixel of each lines process is 1 in fingerprint image, blank space is 0, finger print data is substituted in data space coordinate system, each spatial value is initialized as the binary data stream being made up of 0 and 1, then the texture structure of fingerprint image may finally be converted to 0010110111 ... binary data so intuitively.
4. a kind of method using multidimensional technology to carry out quick finger print data inquiry and contrast according to claim 3, it is characterised in that the multidimensional finger print data of described retrieval, refers to retrieval multidimensional characteristic coordinate data.
5. a kind of method using multidimensional technology to carry out quick finger print data inquiry and contrast according to claim 4, it is characterised in that come quick indexing, the relevant fingerprint in location by defining the mode of coordinates regional.
6. a kind of method using multidimensional technology to carry out quick finger print data inquiry and contrast according to claim 5, it is characterised in that the multidimensional finger print data of described verification, refers to the feature verification being accurate to each grain details.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610142400.5A CN105808747A (en) | 2016-03-14 | 2016-03-14 | Method for quickly searching and comparing fingerprint data by using multidimensional technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610142400.5A CN105808747A (en) | 2016-03-14 | 2016-03-14 | Method for quickly searching and comparing fingerprint data by using multidimensional technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105808747A true CN105808747A (en) | 2016-07-27 |
Family
ID=56468311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610142400.5A Pending CN105808747A (en) | 2016-03-14 | 2016-03-14 | Method for quickly searching and comparing fingerprint data by using multidimensional technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105808747A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239571A (en) * | 2017-06-28 | 2017-10-10 | 浪潮金融信息技术有限公司 | Index structuring method based on multidimensional data space technology |
| CN108038475A (en) * | 2017-12-29 | 2018-05-15 | 浪潮金融信息技术有限公司 | Facial image recognition method and device, computer-readable storage medium, terminal |
| CN108229378A (en) * | 2017-12-29 | 2018-06-29 | 浪潮金融信息技术有限公司 | Face image data generation method and device, computer storage media, terminal |
| CN108427870A (en) * | 2017-02-15 | 2018-08-21 | 北京京东尚科信息技术有限公司 | Hand gesture unlocking method, device, storage medium and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3959884A (en) * | 1975-07-25 | 1976-06-01 | First Ann Arbor Corporation | Method of classifying fingerprints |
| CN1506903A (en) * | 2002-12-06 | 2004-06-23 | 中国科学院自动化研究所 | Automatic fingerprint distinguishing system and method based on template learning |
| CN101620677B (en) * | 2009-03-11 | 2012-03-21 | 刘鸣宇 | Fingerprint identification method based on triangulation and LOD technology |
| CN103927351A (en) * | 2014-04-10 | 2014-07-16 | 清华大学 | Posture correcting based fingerprint retrieval method and system |
-
2016
- 2016-03-14 CN CN201610142400.5A patent/CN105808747A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3959884A (en) * | 1975-07-25 | 1976-06-01 | First Ann Arbor Corporation | Method of classifying fingerprints |
| CN1506903A (en) * | 2002-12-06 | 2004-06-23 | 中国科学院自动化研究所 | Automatic fingerprint distinguishing system and method based on template learning |
| CN101620677B (en) * | 2009-03-11 | 2012-03-21 | 刘鸣宇 | Fingerprint identification method based on triangulation and LOD technology |
| CN103927351A (en) * | 2014-04-10 | 2014-07-16 | 清华大学 | Posture correcting based fingerprint retrieval method and system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108427870A (en) * | 2017-02-15 | 2018-08-21 | 北京京东尚科信息技术有限公司 | Hand gesture unlocking method, device, storage medium and electronic equipment |
| CN107239571A (en) * | 2017-06-28 | 2017-10-10 | 浪潮金融信息技术有限公司 | Index structuring method based on multidimensional data space technology |
| CN108038475A (en) * | 2017-12-29 | 2018-05-15 | 浪潮金融信息技术有限公司 | Facial image recognition method and device, computer-readable storage medium, terminal |
| CN108229378A (en) * | 2017-12-29 | 2018-06-29 | 浪潮金融信息技术有限公司 | Face image data generation method and device, computer storage media, terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | Local difference binary for ultrafast and distinctive feature description | |
| CN103207898B (en) | A kind of similar face method for quickly retrieving based on local sensitivity Hash | |
| CN106453437B (en) | equipment identification code acquisition method and device | |
| US8995729B2 (en) | Accelerated comparison using scores from coarse and fine matching processes | |
| CN105808747A (en) | Method for quickly searching and comparing fingerprint data by using multidimensional technology | |
| Yue et al. | Hashing based fast palmprint identification for large-scale databases | |
| CN107341178B (en) | Data retrieval method based on self-adaptive binary quantization Hash coding | |
| Psyllos et al. | M-SIFT: A new method for Vehicle Logo Recognition | |
| CN110633289A (en) | License plate number determining method, server and parking management system | |
| Yue et al. | Fast palmprint identification with multiple templates per subject | |
| CN103440480A (en) | Non-contact palmprint recognition method based on palmprint image registration | |
| Zhou et al. | Enhanced locality-sensitive hashing for fingerprint forensics over large multi-sensor databases | |
| Huang et al. | Mobile phone component object detection algorithm based on improved SSD | |
| WO2017000352A1 (en) | Method, apparatus and terminal for fingerprint identification | |
| Bai et al. | An efficient indexing scheme based on k-plet representation for fingerprint database | |
| Conti et al. | An advanced technique for user identification using partial fingerprint | |
| Yue et al. | Consistency analysis on orientation features for fast and accurate palmprint identification | |
| Chen et al. | Orientation field code hashing: A novel method for fast palmprint identification | |
| Ekombo et al. | Application of affine invariant fourier descriptor to shape based image retrieval | |
| Fan et al. | A novel probabilistic model based fingerprint recognition algorithm | |
| CN115527241A (en) | Fingerprint template updating method and device, embedded equipment and storage medium | |
| CN114707174A (en) | Data processing method and device, electronic equipment and storage medium | |
| Jia et al. | A performance evaluation of hashing techniques for 2D and 3D palmprint retrieval and recognition | |
| CN113626469B (en) | Internet of things equipment matching method and device | |
| Yue et al. | Fast palmprint identification using orientation pattern hashing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Wusong Industrial Park, Wuzhong Development District of Suzhou City, Jiangsu province 215100 Wusong Road No. 818 Applicant after: Tide Financial Information Technology Co Ltd Address before: Wuzhong Economic Development Zone in Suzhou City, Jiangsu Province, the River Street 215104 tower rhyme Road No. 178 Building 2 layer 1 Applicant before: Tide (Suzhou) Financial Technology Service Co., Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160727 |