CN102819729A - Fingerprint recognizing method - Google Patents
Fingerprint recognizing method Download PDFInfo
- Publication number
- CN102819729A CN102819729A CN2012102462519A CN201210246251A CN102819729A CN 102819729 A CN102819729 A CN 102819729A CN 2012102462519 A CN2012102462519 A CN 2012102462519A CN 201210246251 A CN201210246251 A CN 201210246251A CN 102819729 A CN102819729 A CN 102819729A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- triangle
- fingerprints
- unique point
- unique
- 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.)
- Granted
Links
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a fingerprint recognizing method. The fingerprint recognizing method comprises the following steps: structuring triangles by every characteristic point of a fingerprint to be recognized and a known fingerprint; judging that the triangles are equal to each other; representing every characteristic point of two fingerprints by three ordered arrays formed by the distance from every characteristic point of two fingerprints to three top points of a respective reference triangle; comparing every characteristic point of two fingerprints except for three top points of the reference triangle, and recording the time when three ordered arrays of every characterize point with the same type are equal to each other; at last, according to the equal time of the fingerprint characteristic point, judging the similarity of two fingerprints. The fingerprint recognizing method has the following positive effects that: the recognizing rate of the fingerprint is improved by applying the method based on a triple structure to a fingerprint recognizing system, thereby solving the problems in the existing fingerprint recognizing technology that the situations that the fingerprint image to be matched and the original fingerprint image are displaced, rotated and incomplete are very difficult to correct or exactly position, and the fault-tolerance ability is low.
Description
Technical field
The invention belongs to the fingerprint identification technology field, be specifically related to a kind of fingerprint identification method.
Background technology
Existing fingerprint identification technology based on unique point is gathered earlier fingerprint image, and the unique point that takes the fingerprint again is when identification, if singular point is arranged, then through the singular point identification of aliging; If there is not singular point, then alignment just is difficult to, and can produce bigger error.Thus, the present fingerprint recognition based on unique point just is difficult to alignment, produces following not enough:
1, when fingerprint to be compared and original fingerprint rotate, existing recognition methods is difficult to aligned.
2, when displacement had both taken place and also rotation had taken place in fingerprint to be compared and original fingerprint, the more difficult aligned of existing recognition methods.
If it is incomplete that 3 fingerprints to be compared take place, the fault-tolerant ability of then existing recognition methods comparison can significantly descend, and this situation usually runs into when public security is solved a case, so existing fingerprint identification method can not satisfy the police reconnaissance requirements of one's work.
Summary of the invention
In order to overcome the above-mentioned shortcoming of prior art, the invention provides a kind of fingerprint identification method.
The technical solution adopted for the present invention to solve the technical problems is: a kind of fingerprint identification method comprises the steps:
Step 1, utilize the IMAQ instrument to gather all images information of fingerprint;
Step 2, the information of fingerprint image is handled the unique point that takes the fingerprint;
Step 3, respectively with each unique point structure triangle of fingerprint to be identified and known fingerprint;
Step 4, judge fingerprint to be identified each unique point set by step three structures triangle whether with each unique point of known fingerprint set by step the triangle of three structures equate:
1) if all unequal, explain that then these two pieces of fingerprints are not same piece of fingerprints, comparison finishes;
2) if the triangle of some unique point of fingerprint to be identified structure equate with the triangle that some unique points of known fingerprint are constructed, then get into step 5;
Step 5, be the benchmark triangle with the triangle of confirming in the step 4 respectively, represent each unique point of two pieces of fingerprints with each unique point of two pieces of fingerprints to orderly three arrays of the distance composition on leg-of-mutton three summits of benchmark separately;
Step 6, each unique point except that leg-of-mutton three summits of benchmark in two pieces of fingerprints is compared, and note the number of times that orderly three arrays of each identical unique point of type equate;
The equal times of step 7, the fingerprint feature point noted according to step 6 adopts the similar determination methods of existing fingerprint that the similarity of two pieces of fingerprints is made judgement: if two pieces of fingerprints are same piece of fingerprints, then judge and finish; If not same piece of fingerprint; Whether the triangle that then continues all the other unique points structures of comparison fingerprint to be identified equates with the triangle of some unique point structures of known fingerprint; If equate; Then get into step 5, all compare until the triangle of the whole unique points structure of fingerprint to be identified and finish.
The described use unique point of step 3 is constructed leg-of-mutton method and is: be as the criterion with each fingerprint feature point respectively; In this fingerprint, find out two unique points nearest with it; Judge whether this point two points nearest with it constitute triangle, if then note this triangle; If not, then this unique point structure triangle failure of mark, this unique point is not participated in comparison, and continues with other unique point structure triangles.
Compared with prior art; Good effect of the present invention is: through being used for fingerprint recognition system based on the method for tlv triple structure; Improved the discrimination of fingerprint; Solved in the existing fingerprint identification technology, when fingerprint image to be matched and the original fingerprint image is subjected to displacement, rotates and incomplete, be difficult to calibration or accurately location and the low problem of fault-tolerant ability.
Embodiment
A kind of fingerprint identification method comprises the steps:
Step 1, utilize the IMAQ instrument to gather all images information of fingerprint;
Step 2, the information of fingerprint image is handled the unique point that takes the fingerprint;
Step 3, respectively with each unique point structure triangle of two pieces of fingerprints (fingerprint to be identified and known fingerprint), concrete grammar is following:
Be as the criterion with each fingerprint feature point respectively, in this fingerprint, find out two unique points nearest, judge whether this point two points nearest with it constitute triangle, if then note this triangle with it; If not, then this unique point structure triangle failure of mark, this unique point is not participated in comparison, and continues with other unique points by the described method construct triangle of this step.
Step 4, judge fingerprint to be identified each unique point set by step three structures triangle whether with each unique point of known fingerprint set by step the triangle of three structures equate:
1) if all unequal, explain that then these two pieces of fingerprints are not same piece of fingerprints, comparison finishes;
2) if the triangle of some unique point of fingerprint to be identified structure equate with the triangle that some unique points of known fingerprint are constructed, then get into step 5;
Step 5, be the benchmark triangle with the triangle of confirming in the step 4 respectively, orderly three arrays of forming to the distance on separately leg-of-mutton three summits of benchmark with each unique points of two pieces of fingerprints (a, b c) represent each unique points of two pieces of fingerprints:
The principle of this step is following:
For one on the plane given △ ABC, each the some P on the plane all determine unique one three array (a, b, c), a wherein, b, c are respectively three the summit As of a P to △ ABC, B, the distance of C; Otherwise (x, y z) may not necessarily determine some Q on the unique plane to given arbitrary three arrays, and it is respectively with x, and y, z are its summit A to △ ABC, B, the distance of C.
True in view of the above; The present invention is the benchmark triangle with the triangle of confirming in the step 4 respectively, to whole fingerprint feature point not with traditional rectangular coordinate or polar coordinate representation, but with the orderly three array (as of unique point to the distance composition of confirming an Atria summit; B c) representes.
Why adopt this method, be because:
1, this construction method is in pattern-recognition; As long as in two planes, find an equal triangle; Can be benchmark just, calculate the scalar distance on point or unique point leg-of-mutton three summits to this plane on the plane respectively, mate again with these two vertexs of a triangle.Coupling can very accurately be mated like this, does not need calibration, does not also have propagation of error, and calculated amount is little.
When 2, mating with a complete plane or plane characteristic point for the plane of an incompleteness or plane characteristic point, if adopt traditional matching way, then this problem is exactly an individual np problem; Calculated amount is quite big, if adopt the method, that is: on two planes, finds earlier a triangle respectively; If these two triangles equate, just can adopt 1 method to mate, not a np problem so just; Reduced calculated amount, simultaneously also more accurate.
Step 6, each unique point except that leg-of-mutton three summits of benchmark in two pieces of fingerprints is compared, and note three arrays (a, b, c) the equal number of times of each identical unique point of type;
The equal times of step 7, the fingerprint feature point noted according to step 6 adopts the similar determination methods of existing fingerprint that the similarity of two pieces of fingerprints is made judgement: if two pieces of fingerprints are same piece of fingerprints, then judge and finish; If not same piece of fingerprint; Whether the triangle that then continues all the other unique points structures of comparison fingerprint to be identified equates with the triangle of some unique point structures of known fingerprint; If equate; Then get into step 5, all compare until the triangle of the whole unique points structure of fingerprint to be identified and finish.
Claims (2)
1. a fingerprint identification method is characterized in that: comprise the steps:
Step 1, utilize the IMAQ instrument to gather all images information of fingerprint;
Step 2, the information of fingerprint image is handled the unique point that takes the fingerprint;
Step 3, respectively with each unique point structure triangle of fingerprint to be identified and known fingerprint;
Step 4, judge fingerprint to be identified each unique point set by step three structures triangle whether with each unique point of known fingerprint set by step the triangle of three structures equate:
1) if all unequal, explain that then these two pieces of fingerprints are not same piece of fingerprints, comparison finishes;
2) if the triangle of some unique point of fingerprint to be identified structure equate with the triangle that some unique points of known fingerprint are constructed, then get into step 5;
Step 5, be the benchmark triangle with the triangle of confirming in the step 4 respectively, represent each unique point of two pieces of fingerprints with each unique point of two pieces of fingerprints to orderly three arrays of the distance composition on leg-of-mutton three summits of benchmark separately;
Step 6, each unique point except that leg-of-mutton three summits of benchmark in two pieces of fingerprints is compared, and note the number of times that orderly three arrays of each identical unique point of type equate;
The equal times of step 7, the fingerprint feature point noted according to step 6 adopts the similar determination methods of existing fingerprint that the similarity of two pieces of fingerprints is made judgement: if two pieces of fingerprints are same piece of fingerprints, then judge and finish; If not same piece of fingerprint; Whether the triangle that then continues all the other unique points structures of comparison fingerprint to be identified equates with the triangle of some unique point structures of known fingerprint; If equate; Then get into step 5, all compare until the triangle of the whole unique points structure of fingerprint to be identified and finish.
2. a kind of fingerprint identification method according to claim 1; It is characterized in that: the described use unique point of step 3 is constructed leg-of-mutton method and is: be as the criterion with each fingerprint feature point respectively; In this fingerprint, find out two unique points nearest with it; Judge whether this point two points nearest with it constitute triangle, if then note this triangle; If not, then this unique point structure triangle failure of mark, this unique point is not participated in comparison, and continues with other unique point structure triangles.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210246251.9A CN102819729B (en) | 2012-07-17 | 2012-07-17 | Fingerprint recognizing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210246251.9A CN102819729B (en) | 2012-07-17 | 2012-07-17 | Fingerprint recognizing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102819729A true CN102819729A (en) | 2012-12-12 |
| CN102819729B CN102819729B (en) | 2014-07-16 |
Family
ID=47303838
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210246251.9A Active CN102819729B (en) | 2012-07-17 | 2012-07-17 | Fingerprint recognizing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102819729B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104298980A (en) * | 2014-11-03 | 2015-01-21 | 北京大唐智能卡技术有限公司 | Fingerprint matching method and device based on smart card |
| CN104301099A (en) * | 2014-10-16 | 2015-01-21 | 内江师范学院 | Encryption method for fingerprint feature point topological structure |
| CN105574507A (en) * | 2015-12-17 | 2016-05-11 | 内江师范学院 | Fingerprint fusion method based on characteristic points |
| CN106203240A (en) * | 2015-05-07 | 2016-12-07 | 神盾股份有限公司 | Fingerprinting method and electronic installation |
| CN107888956A (en) * | 2017-11-01 | 2018-04-06 | 深圳智英电子有限公司 | Fingerprint recognition certification top box of digital machine and control method based on big-dipper satellite positioning |
| WO2018113208A1 (en) * | 2017-06-14 | 2018-06-28 | 钟杰东 | Partial fingerprint and partial iris payment device |
| CN116311395A (en) * | 2022-08-18 | 2023-06-23 | 荣耀终端有限公司 | Fingerprint identification method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050232473A1 (en) * | 2004-04-18 | 2005-10-20 | Zhongqiu Liu | Fingerprint verification method and apparatus based on global ridgeline |
| CN1912889A (en) * | 2005-08-11 | 2007-02-14 | 中国科学院自动化研究所 | Deformed fingerprint identification method based on local triangle structure characteristic collection |
| CN1983301A (en) * | 2006-06-14 | 2007-06-20 | 北京握奇数据系统有限公司 | Method, device and use for matching two-stage mixed-fingerprint characteristics |
-
2012
- 2012-07-17 CN CN201210246251.9A patent/CN102819729B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050232473A1 (en) * | 2004-04-18 | 2005-10-20 | Zhongqiu Liu | Fingerprint verification method and apparatus based on global ridgeline |
| CN1912889A (en) * | 2005-08-11 | 2007-02-14 | 中国科学院自动化研究所 | Deformed fingerprint identification method based on local triangle structure characteristic collection |
| CN1983301A (en) * | 2006-06-14 | 2007-06-20 | 北京握奇数据系统有限公司 | Method, device and use for matching two-stage mixed-fingerprint characteristics |
Non-Patent Citations (2)
| Title |
|---|
| 尹义龙等: "基于Delaunay三角化的指纹匹配方法", 《计算机研究与发展》 * |
| 柴海燕: "基于相似三角形原理的指纹匹配算法", 《通信技术》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104301099A (en) * | 2014-10-16 | 2015-01-21 | 内江师范学院 | Encryption method for fingerprint feature point topological structure |
| CN104301099B (en) * | 2014-10-16 | 2017-04-12 | 内江师范学院 | Encryption method for fingerprint feature point topological structure |
| CN104298980A (en) * | 2014-11-03 | 2015-01-21 | 北京大唐智能卡技术有限公司 | Fingerprint matching method and device based on smart card |
| CN104298980B (en) * | 2014-11-03 | 2018-08-28 | 北京大唐智能卡技术有限公司 | A kind of finger print matching method and device based on smart card |
| CN106203240A (en) * | 2015-05-07 | 2016-12-07 | 神盾股份有限公司 | Fingerprinting method and electronic installation |
| CN105574507A (en) * | 2015-12-17 | 2016-05-11 | 内江师范学院 | Fingerprint fusion method based on characteristic points |
| CN105574507B (en) * | 2015-12-17 | 2018-07-13 | 内江师范学院 | A kind of fingerprint fusing method of feature based point |
| WO2018113208A1 (en) * | 2017-06-14 | 2018-06-28 | 钟杰东 | Partial fingerprint and partial iris payment device |
| CN107888956A (en) * | 2017-11-01 | 2018-04-06 | 深圳智英电子有限公司 | Fingerprint recognition certification top box of digital machine and control method based on big-dipper satellite positioning |
| CN116311395A (en) * | 2022-08-18 | 2023-06-23 | 荣耀终端有限公司 | Fingerprint identification method and device |
| CN116311395B (en) * | 2022-08-18 | 2023-11-14 | 荣耀终端有限公司 | Fingerprint identification method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102819729B (en) | 2014-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102819729A (en) | Fingerprint recognizing method | |
| Li et al. | A monocular SLAM system leveraging structural regularity in Manhattan world | |
| CN102930525B (en) | Line matching method based on affine invariant feature and homography | |
| CN109523501A (en) | One kind being based on dimensionality reduction and the matched battery open defect detection method of point cloud data | |
| CN103308925A (en) | Integral three-dimensional color laser radar data point cloud generating method and device thereof | |
| CN105184243B (en) | A kind of environmental characteristic expression based on 3 d grid map and knowledge method for distinguishing | |
| CN103425988A (en) | Real-time positioning and matching method with arc geometric primitives | |
| CN105806315A (en) | Active coded information based non-cooperative object relative measurement system and measurement method thereof | |
| Wang et al. | Robust component-based localizationin sparse networks | |
| CN103994765A (en) | Positioning method of inertial sensor | |
| CN104715154A (en) | Nuclear K-mean value track correlation method based on KMDL criteria | |
| CN105354841A (en) | Fast matching method and system for remote sensing images | |
| CN101685532B (en) | Method for correcting simple linear wide-angle lens | |
| CN106504287A (en) | Monocular vision object space alignment system based on template | |
| Wu et al. | Track-clustering error evaluation for track-based multi-camera tracking system employing human re-identification | |
| CN103886338A (en) | Multispectral image matching method and system thereof | |
| Meng et al. | Accurate LiDAR-based Localization in Glass-walled Environment | |
| CN105320940A (en) | Traffic sign detection method based on center-boundary connection model | |
| CN110145966A (en) | A kind of finite time convergence control Global robust sliding formwork method of guidance | |
| Fu et al. | Targetless extrinsic calibration of stereo cameras, thermal cameras, and laser sensors in the wild | |
| Wang et al. | Slam-based cooperative calibration for optical sensors array with gps/imu aided | |
| Liu et al. | A 6D-pose estimation method for UAV using known lines | |
| Junejo et al. | Using solar shadow trajectories for camera calibration | |
| CN105574507A (en) | Fingerprint fusion method based on characteristic points | |
| Kaneko et al. | Stata Center Frame: A Novel World Assumption for Self-Localization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |