CN105320935A - Multiple-template fingerprint identification method - Google Patents
Multiple-template fingerprint identification method Download PDFInfo
- Publication number
- CN105320935A CN105320935A CN201510451322.2A CN201510451322A CN105320935A CN 105320935 A CN105320935 A CN 105320935A CN 201510451322 A CN201510451322 A CN 201510451322A CN 105320935 A CN105320935 A CN 105320935A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- template
- fingerprint template
- contrast
- storehouse
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention discloses a multiple-template fingerprint identification method. The method comprises steps of fingerprint registration and fingerprint searching and matching. Therefore, according to the multiple-template fingerprint identification method disclosed by the present invention, three templates are prestored in a fingerprint inputting stage and are sequentially stored in the first three spaces of an allocated memory, and then in a searching and matching stage, the three remaining templates are sequentially filled fully, so that while not too much time is taken for fingerprint registration, the module identification rate for a later identity authentication stage is improved.
Description
Technical field
The present invention relates to fingerprint module field, particularly relate to a kind of multi-template fingerprint identification method.
Background technology
People, in the process of social interaction, often need to carry out authentication.Common various authentication means, as key, password password, certificate and IC-card etc., being all the modes by recognizing people with " thing ", indirectly realizing the identity validation to related item possessor.This method accuracy is very low, and security breaches are larger.In actual life, the example of various forged certificate and keepsake is of common occurrence, and password is decrypted or usurps and also often occurs.In order to take precautions against the generation of this kind of event, people need a kind of authentication means of directly recognizing people, and Here it is " human body biological characteristics recognition technology ".The true identity of biological characteristic to everyone that it self has according to everyone is differentiated.These biological characteristics mostly have " people respectively has different ", the feature of " constant throughout one's life " and " carrying with ", ensure that accuracy and the reliability of authentication result.
Fingerprint is the inherent physical trait of people, fingerprint has " stationarity ", can not change because the continuation of people is grown up, fingerprint also has uniqueness, two different people can not have identical fingerprint, since the famous anthropologist's laboratory report that Ge Mideng, Fo Lanxue deliver of Britain in 1888, also do not find identical finger-print card.Because fingerprint obtains easily, and possess the characteristic of " fixing " and " uniquely ", be just used as the instrument of Criminal Investigation by this police commissioner of EdwardHenry as far back as 1897 Christian eras, from then on fingerprint comes into one's own day by day.The sixties in 20th century is that the infotech of representative is progressively risen with robot calculator, and for human research's fingerprint recognition provides thinking and countermeasure, research is exactly that fingerprint automatically extracts and searches for the most widely.Early 1990s, China successfully have developed the automatic system of fingerprint recognition with international most advanced level, and profit not only can reduce a large amount of manual labor in this way, and by setting up fingerprint file database, can increase work efficiency.Along with the progress of science and technology, fingerprint identification technology extend to normal domestic field from police field, such as fingerprint attendance, fingerprint access control, Fingerprint Lock etc.
Due to when gathering fingerprint, the different fingerprint collecting of twice of same finger may be different owing to pointing the position placed on fingerprint acquisition instrument window, make the public domain after two fingerprint overlaps less, thus make the pairing node logarithm of two fingerprints less and produce False Rejects.In addition, the impact of environmental factor, also can make the feature of fingerprint image unstable.In order to process these instability, many Automated Fingerprint Identification Systems are at the multiple template fingerprint of fingerprint register phase acquisition, it is all kept in template base, or one or several template fingerprint adopting certain policy selection wherein representative is stored in template base, but do the time that can increase registration like this, so people need the fingerprint identification method more met the demands.
Summary of the invention
The technical matters that the present invention mainly solves is to provide a kind of multi-template fingerprint identification method, has that reliability is high, discrimination is high, recognition efficiency advantages of higher, simultaneously fingerprint module application and universal on have market outlook widely.
For solving the problems of the technologies described above, the technical scheme that the present invention adopts is:
There is provided a kind of multi-template fingerprint identification method, its step comprises:
(1) fingerprint register: in the flash memory of fingerprint module, predistribution m to be used for the template internal memory of fingerprint template of typing, and the size arranging each fingerprint template is n byte, then the size of preallocated template internal memory is m*n byte, and wherein, m, n are natural number;
This m fingerprint template is arranged to a fingerprint template storehouse;
When typing fingerprint, the sensor on fingerprint module is to each finger collection three fingerprints, and all generate a fingerprint template, namely each finger has generation three fingerprint templates altogether at every turn;
Three fingerprint templates are stored in template internal memory, namely make three fingerprint templates all be stored in fingerprint template storehouse;
Be in n bytes of storage space by first three size that three fingerprint templates are kept in template internal memory successively;
(2) fingerprint search comparison: the similarity threshold that comparison is set, i.e. alignment score;
The fingerprint of the sensor collection finger on fingerprint module, and generate a contrast fingerprint template;
In fingerprint template storehouse, search for fingerprint template, compare with contrast fingerprint template;
When in fingerprint template storehouse, when searching the fingerprint template identical with contrasting fingerprint template, judge the alignment score relation of fingerprint template and the contrast fingerprint template searched;
If contrast fingerprint template and the alignment score of the fingerprint template searched are more than or equal to the alignment score of setting, then judge that contrast fingerprint template and the fingerprint template searched are the fingerprint templates from same finger, namely judge comparison success, no longer store new fingerprint template in fingerprint template storehouse;
If contrast fingerprint template and the alignment score of the fingerprint template searched are less than the alignment score of setting, then judge that comparison is unsuccessful, namely in fingerprint template storehouse, be stored into this contrast fingerprint template.
In a preferred embodiment of the present invention, the size of each fingerprint template is 810 bytes.
In a preferred embodiment of the present invention, when fingerprint search comparison, the fingerprint template in contrast fingerprint template and fingerprint template storehouse is carried out comparison one by one.
In a preferred embodiment of the present invention, when the sensor on fingerprint module gathers fingerprint, first obtain fingerprint image, then after fingerprint image is corrected, generate fingerprint template.
The invention has the beneficial effects as follows: belong to multi-template, the fingerprint template that the fingerprint characteristic of storage stores than single mode version is how a lot, thus can greatly improve Module recognition rate in the authentication stage; Owing to fingerprint template being filled up in the search comparison stage, thus once just six templates can be filled up in the registered fingerprint stage and save a large amount of time.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, below the accompanying drawing used required in describing embodiment is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings, wherein:
Fig. 1 is the schematic flow sheet of the fingerprint register of multi-template fingerprint identification method of the present invention;
Fig. 2 is the schematic flow sheet of the fingerprint search comparison of multi-template fingerprint identification method of the present invention;
Fig. 3 is the framed structure schematic diagram of multi-template fingerprint identification method of the present invention.
Embodiment
Be clearly and completely described to the technical scheme in the embodiment of the present invention below, obviously, described embodiment is only a part of embodiment of the present invention, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making other embodiments all obtained under creative work prerequisite, belong to the scope of protection of the invention.
Refer to Fig. 1-2, the embodiment of the present invention comprises:
A kind of multi-template fingerprint identification method, the method is used in fingerprint identification module, described fingerprint identification module comprises MCU main control chip, cmos sensor, Flash chip, serial/parallel line interface and system equipment, and described MCU main control chip is connected with described system equipment with described cmos sensor, described Flash chip, described serial/parallel line interface respectively.
Described cmos sensor receives the finger print information of user, and described MCU main control chip calculates finger print information according to multi-template fingerprint identification method.
The concrete steps of multi-template fingerprint identification method comprise:
(1) fingerprint register: in the flash memory (FLASH) of fingerprint module, predistribution m to be used for the template internal memory of fingerprint template of typing, and the size arranging each fingerprint template is n byte, then the size of preallocated template internal memory is m*n byte, wherein, m, n are natural number;
This m fingerprint template is arranged to a fingerprint template storehouse;
When typing fingerprint, the sensor on fingerprint module is to each finger collection three fingerprints, and all generate a fingerprint template, namely each finger has generation three fingerprint templates altogether at every turn;
Three fingerprint templates are stored in template internal memory, namely make three fingerprint templates all be stored in fingerprint template storehouse;
Be in n bytes of storage space by first three size that three fingerprint templates are kept in template internal memory successively;
(2) fingerprint search comparison: the similarity threshold that comparison is set, i.e. alignment score;
The fingerprint of the sensor collection finger on fingerprint module, and generate a contrast fingerprint template;
In fingerprint template storehouse, search for fingerprint template, compare with contrast fingerprint template;
When in fingerprint template storehouse, when searching the fingerprint template identical with contrasting fingerprint template, judge the alignment score relation of fingerprint template and the contrast fingerprint template searched;
If contrast fingerprint template and the alignment score of the fingerprint template searched are more than or equal to the alignment score of setting, then judge that contrast fingerprint template and the fingerprint template searched are the fingerprint templates from same finger, namely judge comparison success, no longer store new fingerprint template in fingerprint template storehouse;
If contrast fingerprint template and the alignment score of the fingerprint template searched are less than the alignment score of setting, then judge that comparison is unsuccessful, namely in fingerprint template storehouse, be stored into this contrast fingerprint template.
When sensor on fingerprint module gathers fingerprint, first obtain fingerprint image, then after fingerprint image is corrected, generate fingerprint template.
Specific embodiment one
In the flash memory (FLASH) of fingerprint module, in advance for each finger to be logged distributes the internal memory of six templates, the size of each template is 810 bytes, then each finger is divided into the internal memory of joining 6*810 byte, when template is stored in flash memory (FLASH), a template base will be formed.
When typing fingerprint, finger is pressed three times on the sensor of fingerprint module, each all generations template, symbiosis becomes three templates, preservation flash memory (FLASH) is in the module in its specific internal memory distributed, and after typing completes, the template of each finger is in template base, at this moment each finger just saves three templates in the module, and these three templates are kept in first three 810 byte in the internal memory distributed successively.
Then carry out search comparison, when searching template in template base, at this moment similarity threshold and the alignment score of a comparison will be set, also be similarity score.Finger is put on sensor, if generate template success, then can produces a new template, Here it is contrast fingerprint template.
With the comparison that this contrast fingerprint template and the fingerprint template be stored in fingerprint template storehouse carry out one by one, in the successful situation of search, if in contrast fingerprint template and template base stored in this finger the alignment score of any one fingerprint template be more than or equal to the alignment score set, then think and just do not store comparison success in template to be compared to template base as in its internal memory distributed.
If in contrast fingerprint template and template base stored in the mark of comparison of fingerprint template of this finger be all less than the alignment score of setting, then think that comparison is unsuccessful, just template to be compared is stored in the internal memory of the 4th 810 bytes that flash memory (FLASH) distributes for it.
Add the 5th, the 6th template in the same way.After overtesting proves that six templates are filled with, then carry out search comparison, template discrimination can be improved greatly, discrimination can be improved twice, and also can not consume the oversize time at registration phase.
The beneficial effect of multi-template fingerprint identification method of the present invention is:
1. owing to fingerprint template being filled up in the search comparison stage, thus once just six templates can be filled up in the registered fingerprint stage and save a large amount of time;
2. belong to multi-template, the fingerprint template that the fingerprint characteristic of storage stores than single mode version is how a lot, thus can greatly improve Module recognition rate in the authentication stage.
The foregoing is only embodiments of the invention; not thereby the scope of the claims of the present invention is limited; every utilize description of the present invention to do equivalent structure or equivalent flow process conversion; or be directly or indirectly used in other relevant technical field, be all in like manner included in scope of patent protection of the present invention.
Claims (4)
1. a multi-template fingerprint identification method, is characterized in that, step comprises:
(1) fingerprint register: in the flash memory of fingerprint module, predistribution m to be used for the template internal memory of fingerprint template of typing, and the size arranging each fingerprint template is n byte, then the size of preallocated template internal memory is m*n byte, and wherein, m, n are natural number;
This m fingerprint template is arranged to a fingerprint template storehouse;
When typing fingerprint, the sensor on fingerprint module is to each finger collection three fingerprints, and all generate a fingerprint template, namely each finger has generation three fingerprint templates altogether at every turn;
Three fingerprint templates are stored in template internal memory, namely make three fingerprint templates all be stored in fingerprint template storehouse;
Be in n bytes of storage space by first three size that three fingerprint templates are kept in template internal memory successively;
(2) fingerprint search comparison: the similarity threshold that comparison is set, i.e. alignment score;
The fingerprint of the sensor collection finger on fingerprint module, and generate a contrast fingerprint template;
In fingerprint template storehouse, search for fingerprint template, compare with contrast fingerprint template;
When in fingerprint template storehouse, when searching the fingerprint template identical with contrasting fingerprint template, judge the alignment score relation of fingerprint template and the contrast fingerprint template searched;
If contrast fingerprint template and the alignment score of the fingerprint template searched are more than or equal to the alignment score of setting, then judge that contrast fingerprint template and the fingerprint template searched are the fingerprint templates from same finger, namely judge comparison success, no longer store new fingerprint template in fingerprint template storehouse;
If contrast fingerprint template and the alignment score of the fingerprint template searched are less than the alignment score of setting, then judge that comparison is unsuccessful, namely in fingerprint template storehouse, be stored into this contrast fingerprint template.
2. multi-template fingerprint identification method according to claim 1, is characterized in that, the size of each fingerprint template is 810 bytes.
3. multi-template fingerprint identification method according to claim 1, is characterized in that, when fingerprint search comparison, the fingerprint template in contrast fingerprint template and fingerprint template storehouse is carried out comparison one by one.
4. multi-template fingerprint identification method according to claim 1, is characterized in that, when the sensor on fingerprint module gathers fingerprint, first obtains fingerprint image, then after correcting fingerprint image, generates fingerprint template.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510451322.2A CN105320935A (en) | 2015-07-29 | 2015-07-29 | Multiple-template fingerprint identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510451322.2A CN105320935A (en) | 2015-07-29 | 2015-07-29 | Multiple-template fingerprint identification method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105320935A true CN105320935A (en) | 2016-02-10 |
Family
ID=55248290
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510451322.2A Pending CN105320935A (en) | 2015-07-29 | 2015-07-29 | Multiple-template fingerprint identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105320935A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105825202A (en) * | 2016-03-31 | 2016-08-03 | 宇龙计算机通信科技(深圳)有限公司 | Early warning processing method of multi-fingerprint hybrid registration, and mobile terminal |
CN106845550A (en) * | 2017-01-22 | 2017-06-13 | 阿依瓦(北京)技术有限公司 | A kind of image-recognizing method based on multi-template |
CN112990163A (en) * | 2021-05-18 | 2021-06-18 | 深圳阜时科技有限公司 | Fingerprint calibration method, electronic device and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002222424A (en) * | 2001-01-29 | 2002-08-09 | Nec Corp | Fingerprint matching system |
CN1972186A (en) * | 2005-11-24 | 2007-05-30 | 中国科学院自动化研究所 | A mobile identity authentication system and its authentication method |
CN101231692A (en) * | 2007-12-24 | 2008-07-30 | 浙江金指码科技有限公司 | Learning type intellectual fingerprint identification comparison method adjusted by fingerprint eigenvalue |
CN101620675A (en) * | 2009-06-16 | 2010-01-06 | 浙江维尔电子有限公司 | Method for enhancing pass rate of fingerprint authentication |
CN102254167B (en) * | 2011-08-16 | 2013-06-19 | 杭州晟元芯片技术有限公司 | Method for reducing false reject rate of fingerprint comparison |
-
2015
- 2015-07-29 CN CN201510451322.2A patent/CN105320935A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002222424A (en) * | 2001-01-29 | 2002-08-09 | Nec Corp | Fingerprint matching system |
CN1972186A (en) * | 2005-11-24 | 2007-05-30 | 中国科学院自动化研究所 | A mobile identity authentication system and its authentication method |
CN101231692A (en) * | 2007-12-24 | 2008-07-30 | 浙江金指码科技有限公司 | Learning type intellectual fingerprint identification comparison method adjusted by fingerprint eigenvalue |
CN101620675A (en) * | 2009-06-16 | 2010-01-06 | 浙江维尔电子有限公司 | Method for enhancing pass rate of fingerprint authentication |
CN102254167B (en) * | 2011-08-16 | 2013-06-19 | 杭州晟元芯片技术有限公司 | Method for reducing false reject rate of fingerprint comparison |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105825202A (en) * | 2016-03-31 | 2016-08-03 | 宇龙计算机通信科技(深圳)有限公司 | Early warning processing method of multi-fingerprint hybrid registration, and mobile terminal |
CN106845550A (en) * | 2017-01-22 | 2017-06-13 | 阿依瓦(北京)技术有限公司 | A kind of image-recognizing method based on multi-template |
CN106845550B (en) * | 2017-01-22 | 2020-03-17 | 阿依瓦(北京)技术有限公司 | Image identification method based on multiple templates |
CN112990163A (en) * | 2021-05-18 | 2021-06-18 | 深圳阜时科技有限公司 | Fingerprint calibration method, electronic device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Uludag et al. | Biometric template selection and update: a case study in fingerprints | |
CN100356388C (en) | Biocharacteristics fusioned identity distinguishing and identification method | |
CN105825176A (en) | Identification method based on multi-mode non-contact identity characteristics | |
CN109934114B (en) | Finger vein template generation and updating algorithm and system | |
CN101145198A (en) | Certainty coding method and system in fingerprint identification | |
CN102682309A (en) | Face feature registering method and device based on template learning | |
CN105243719A (en) | Control method and system for access control | |
CN104537290A (en) | Password system and achievement method based on multi-fingerprint identification | |
CN105320935A (en) | Multiple-template fingerprint identification method | |
TWI783199B (en) | Processing method of face recognition and electronic device | |
CN103714159A (en) | Coarse-to-fine fingerprint identification method fusing second-level and third-level features | |
Li et al. | Palmprint identification using Hausdorff distance | |
Bai et al. | An efficient indexing scheme based on k-plet representation for fingerprint database | |
CN103886303A (en) | Palmprint recognition method and device | |
CN102368291B (en) | Personal authentication system based on invisible consciousness of fingerprint image | |
Adhiyaman et al. | Fingerprint matching and similarity checking system using minutiae based technique | |
Yang et al. | NDTC: A novel topology-based fingerprint matching algorithm using N-layer Delaunay triangulation net check | |
CN206331449U (en) | A kind of fingerprint recognition system for possessing versatility | |
CN106228154A (en) | Supercargo's identity authorization system based on escort delivery identification electronic Verification System | |
CN106372600A (en) | Three-in-one high precision escorting handover identity electronic authentication system | |
Abdulameer | Developing and valuation for techniques fingerprint recognition system | |
Mehrotra et al. | An efficient dual stage approach for iris feature extraction using interest point pairing | |
Anitha et al. | A novel bimodal biometric identification system based on finger geometry and palm print | |
Zhang et al. | Multi-grid spatial and temporal feature fusion for human identification at a distance | |
CN102368293A (en) | Personal identity authentication system based on stealth consciousness |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160210 |
|
RJ01 | Rejection of invention patent application after publication |