CN104361325A - Fingerprint feature construction method based on minutiae - Google Patents
Fingerprint feature construction method based on minutiae Download PDFInfo
- Publication number
- CN104361325A CN104361325A CN201410650866.7A CN201410650866A CN104361325A CN 104361325 A CN104361325 A CN 104361325A CN 201410650866 A CN201410650866 A CN 201410650866A CN 104361325 A CN104361325 A CN 104361325A
- Authority
- CN
- China
- Prior art keywords
- point
- coordinate system
- minutiae
- minutiae point
- rcs
- 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
- G06V40/1371—Matching features related to minutiae or pores
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 invention relates to a fingerprint feature construction method based on minutiae, and belongs to the technical field of the automatic fingerprint recognition. The method is used for obtaining minutia pairs in the fingerprint matching process and includes the first step of preprocessing a fingerprint image, the second step of establishing a right-angle coordinate system called RCS and determining the directions of the coordinate system, the third step of defining and finding the effectively minutiae belonging to the RCS coordinate system, and the fourth step of calculating the number of regression lines related to the effective minutiae and conducting inspection. The method has the advantages that by means of the features, the features of the minutiae and the regression line information related to the minutiae are combined, and the reliability of the extracted features is improved; the directions of the coordinate system are determined, and the anti-rotation performance of the algorithm can be effectively improved; the method for calculating the number of the regression lines is described in details and achieved, and the inspection shows that the calculation result is quite accurate; only the features of the minutiae belonging to the RCS coordinate system are extracted, the number of the extracted features of the minutiae is reduced, and the running efficiency of the algorithm is improved.
Description
Technical field
The present invention relates to auto Fingerprint Identification System field, be specifically related to a kind of minutiae feature extraction algorithm based on crestal line number.
Background technology
In automatic recognition system, fingerprint is the most frequently used biological pattern, because its reliable expressive force, and practicality and cheapness.Having proposed multiple method solves the deformation problems of fingerprint image to improve matching rate at present, wherein has a kind of method to be combined by minutiae feature traditional for crestal line characteristic sum to resist non-linear deformation, improves fingerprint matching rate.We know that crestal line feature has unchangeability for geometric transformations such as rotation, distortions, the relation represented between minutiae point that crestal line is also simple and clear simultaneously.So the method establishes the rectangular coordinate system based on crestal line, be called RCS coordinate system, and by its extracting ridges feature.But the shortcoming that the method exists has: first is that RCS coordinate system is very complicated because its more than transverse axis, and the quantity of transverse axis is determined by the quantity of the effective minutiae point in RCS coordinate system; Second is the crestal line feature extraction algorithm cost more time.
Summary of the invention
The present invention, in order to solve the problems of the technologies described above, by setting up RCS coordinate system, define and finding the effective minutiae point belonging to RCS coordinate system, and extracts crestal line number this feature relevant with effective minutiae point, to improve the ability of anti-deformation of algorithm.
4, the present invention is by the following technical solutions: based on the fingerprint characteristic building method of minutiae point, it is characterized in that, comprise the following steps,
Step one, pre-service is carried out to fingerprint image;
(1) i-th minutiae point I of optional fingerprint T
i, from then on minutiae point begins through eight neighborhood edge following algorithm, follow the tracks of crestal line, and by the coordinate figure under this minutiae point global coordinate system stored in structure Img_thintemp, because a crestal line has two end points, there are at most two minutiae point associated, when there being two minutiae point, structure is expressed as Img_thintemp (y, x) .minutiae1x, Img_thintemp (y, x) .minutiae1y, Img_thintemp (y, x) .minutiae2x, Img_thintemp (y, x) .minutiae2y, wherein (y, x) matrix coordinate of former pixel image on crestal line is represented, (minutiae1x, and (minutiae2x minutiae1y), minutiae2y) coordinate of two minutiae point on crestal line is respectively, when there being a minutiae point, the coordinate of this minutiae point is (minutiae1x, minutiae1y),
(2) travel through details point set I, repeat the process of (1);
Step 2, set up rectangular coordinate system RCS, and determine coordinate system direction; Appoint from the details point set I of fingerprint T and get a minutiae point and be designated as O (x
0, y
0, θ), it can be used as the initial point of coordinate system, wherein (x
0, y
0) representing the coordinate of minutiae point O, θ represents the direction of minutiae point O; The axle that definition is parallel to minutiae point O direction is transverse axis H, and the axle perpendicular to minutiae point O direction is Z-axis V, fingerprint image is divided into four regions AI, AII, AIII and AIV, determines the direction of each region relative to transverse axis H and Z-axis V;
Step 3, searching belong to effective minutiae point of RCS coordinate system; By being called through the minutiae point that the crestal line of Z-axis V exists the effective minutiae point belonging to RCS coordinate system, be designated as M
p, the direction calculating formula of effective minutiae point is as follows:
Wherein
represent the direction of effective minutiae point under RCS coordinate system,
with
represent the direction of Z-axis and transverse axis respectively, (x
o, y
o) represent origin position, (x
py
p) represent available point M
pcoordinate position, available point M
pregion is expressed as follows:
Step 4, calculate the crestal line number relevant to effective minutiae point testing, after setting up RCS coordinate system, solve the intersection point of itself and crestal line according to the function analytic expression of Z-axis V and be stored in array intersection (i, k) in, k represents a kth intersection point, the value of i be 1 or 2, intersection (1, what store k) is that y under the global coordinate system of a kth intersection point rounds value, (2, what store k) is that x under the global coordinate system of a kth intersection point rounds value to intersection, find the origin deposited in array intersection, record its sequence number value origin_sequence, the initial value of defining variable count is 1, forward, travel through the intersection point of Z-axis V and crestal line backward, namely array intersection is traveled through, often search an intersection point, count is from adding 1, simultaneously, judge this intersection point place structure Img_thintemp (y, x) value of member variable in, if not empty, so count value is assigned to effective minutiae point (minutiae1x, or (minutiae2x minutiae1y), minutiae2y) structure member ridgecount.
In described step one (1), a crestal line exists a minutiae point, the coordinate of this minutiae point is (minutiae1x, minutiae1y).
Determine the direction of transverse axis H and Z-axis V in described step one (2), formula is as follows:
Wherein
for global coordinate system x-axis direction,
for global coordinate system y-axis direction, θ is initial point direction.
If find in described step 3 when belonging to effective minutiae point of RCS coordinate system and run into bifurcation, then this bifurcation belongs to RCS coordinate system, and the minutiae point on the following crestal line of bifurcation does not enter RCS coordinate system.
The beneficial effect that the present invention reaches: the crestal line information that (1) is correlated with by this minutiae point of characteristic sum minutiae point itself had combines, and improves the reliability of extracted feature; (2) determine coordinate system direction, effectively improve the anti-rotation of algorithm; (3) achieve the method that crestal line number calculates, result of calculation accuracy significantly improves; (4) only extract the minutiae feature belonging to RCS coordinate system, reduce the quantity that minutiae feature extracts, improve algorithm operational efficiency.
Accompanying drawing explanation
Fig. 1 is for setting up RCS coordinate system schematic diagram;
Fig. 2 is fingerprint image block plan;
Fig. 3 is the minutiae point signature storing crestal line number feature;
Fig. 4 is final matching results.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
I-th minutiae point I of step 1, print T
iand by the coordinate figure under this minutiae point global coordinate system stored in structure Img_thintemp, be specifically expressed as Img_thintemp(y, x) .minutiae1x, Img_thintemp (y, x) .minutiae1y, Img_thintemp (y, x) .minutiae2x, Img_thintemp (y, x) .minutiae2y, traversal details point set I, repeats said process.
Step 2, appoint from I and get a minutiae point and be designated as O (x
0, y
0, θ), it can be used as the initial point of coordinate system, as shown in Figure 1.According to RCS coordinate system, fingerprint image being divided into four regions is AI, AII, AIII, AIV, and as shown in Figure 2, each region is relevant with the direction of transverse axis H and Z-axis V, is defined as follows shown in table:
Wherein symbol "+" represents the positive dirction of RCS coordinate axis, and symbol "-" represents the negative direction of RCS coordinate axis.
Step 3, define and find the effective minutiae point belonging to RCS coordinate system.
If have a crestal line through Z-axis V, and there is minutiae point on this crestal line, so this minutiae point belongs to RCS coordinate system and is designated as M
p.Especially, if run into bifurcation, so this bifurcation belongs to RCS coordinate system, and the minutiae point on the following crestal line of bifurcation no longer takes into account RCS coordinate system.
The direction calculating formula of effective minutiae point is as follows:
Wherein
represent the direction of effective minutiae point under RCS coordinate system,
with
represent the direction of Z-axis and transverse axis respectively, (x
o, y
o) represent origin position, (x
p, y
p) represent available point M
pcoordinate position.
Available point M
pplace subregion
Step 4, set up RCS coordinate system after, solve the intersection point of itself and crestal line according to the function analytic expression of Z-axis V and be stored in array intersection (i, k) in, k represents a kth intersection point, the value of i is 1 or 2, find the origin deposited in array intersection, record its sequence number value origin_sequence, the initial value of defining variable count is 1.Forward, travel through the intersection point of Z-axis V and crestal line backward, namely travel through array intersection, until traverse first or last intersection point.Often search an intersection point, count is from adding 1.Simultaneously, judge this intersection point place structure Img_thintemp (y, x) value of member variable in, if not empty, so count value is assigned to effective minutiae point (minutiae1x, minutiae1y) or the structure member ridgecount of (minutiae2x, minutiae2y), as shown in Figure 3.
To travel through forward, two kinds of special circumstances are described.
Special circumstances 1: for the process of crestal line breakpoint in fingerprint image
According to following formula:
D
(i, i-1)represent i-th Euclidean distance between intersection point and (i-1) individual intersection point, d
(i-1, i-2)represent the Euclidean distance between (i-1) individual intersection point and (i-2) individual intersection point.If meet formula (5), then count is from adding 1.
Special circumstances 2: the process of passing through Z-axis V is repeated for a crestal line
When searching i-th intersection point, judge this intersection point place structure Img_thintemp (y, x) in, the value of member variable, if not empty, then judges minutiae point (minutiae1x, or (minutiae2x minutiae1y), the value of structure member ridgecount minutiae2y), if not empty, so i=i+1, search for next intersection point, count value is constant.
Be more than better embodiment of the present invention, but protection scope of the present invention is not limited thereto.Any those of ordinary skill in the art are in the technical scope disclosed by the present invention, and the conversion expected without creative work or replacement, all should be encompassed within protection scope of the present invention.Therefore the protection domain that protection scope of the present invention should limit with claim is as the criterion.
Claims (4)
1., based on the fingerprint characteristic building method of minutiae point, it is characterized in that, comprise the following steps,
Step one, pre-service is carried out to fingerprint image;
(1) i-th minutiae point I of optional fingerprint T
i, from then on minutiae point begins through eight neighborhood edge following algorithm, follow the tracks of crestal line, and by the coordinate figure under this minutiae point global coordinate system stored in structure Img_thintemp, because a crestal line has two end points, there are at most two minutiae point associated, when there being two minutiae point, structure is expressed as Img_thintemp (y, x) .minutiae1x, Img_thintemp (y, x) .minutiae1y, Img_thintemp (y, x) .minutiae2x, Img_thintemp (y, x) .minutiae2y, wherein (y, x) matrix coordinate of former pixel image on crestal line is represented, (minutiae1x, and (minutiae2x minutiae1y), minutiae2y) coordinate of two minutiae point on crestal line is respectively, when there being a minutiae point, the coordinate of this minutiae point is (minutiae1x, minutiae1y),
(2) travel through details point set I, repeat the process of (1);
Step 2, set up rectangular coordinate system RCS, and determine coordinate system direction; Appoint from the details point set I of fingerprint T and get a minutiae point and be designated as O (x
0, y
0, θ), it can be used as the initial point of coordinate system, wherein (x
0, y
0) representing the coordinate of minutiae point O, θ represents the direction of minutiae point O; The axle that definition is parallel to minutiae point O direction is transverse axis H, and the axle perpendicular to minutiae point O direction is Z-axis V, fingerprint image is divided into four regions AI, AII, AIII and AIV, determines the direction of each region relative to transverse axis H and Z-axis V;
Step 3, searching belong to effective minutiae point of RCS coordinate system; By being called through the minutiae point that the crestal line of Z-axis V exists the effective minutiae point belonging to RCS coordinate system, be designated as M
p, the direction calculating formula of effective minutiae point is as follows:
Wherein
represent the direction of effective minutiae point under RCS coordinate system,
with
represent the direction of Z-axis and transverse axis respectively, (x
o, y
o) represent origin position, (x
p, y
p) represent available point M
pcoordinate position, available point M
pregion is expressed as follows:
Step 4, calculate the crestal line number relevant to effective minutiae point testing, after setting up RCS coordinate system, solve the intersection point of itself and crestal line according to the function analytic expression of Z-axis V and be stored in array intersection (i, k) in, k represents a kth intersection point, the value of i be 1 or 2, intersection (1, what store k) is that y under the global coordinate system of a kth intersection point rounds value, (2, what store k) is that x under the global coordinate system of a kth intersection point rounds value to intersection, find the origin deposited in array intersection, record its sequence number value origin_sequence, the initial value of defining variable count is 1, forward, travel through the intersection point of Z-axis V and crestal line backward, namely array intersection is traveled through, often search an intersection point, count is from adding 1, simultaneously, judge this intersection point place structure Img_thintemp (y, x) value of member variable in, if not empty, so count value is assigned to effective minutiae point (minutiae1x, or (minutiae2x minutiae1y), minutiae2y) structure member ridgecount.
2. the fingerprint characteristic building method based on minutiae point according to claim 1, it is characterized in that: in described step one (1), a crestal line exists a minutiae point, the coordinate of this minutiae point is (minutiae1x, minutiae1y).
3. the fingerprint characteristic building method based on minutiae point according to claim 1, it is characterized in that: the direction determining transverse axis H and Z-axis V in described step one (2), formula is as follows:
Wherein
for global coordinate system x-axis direction,
for global coordinate system y-axis direction, θ is initial point direction.
4. the fingerprint characteristic building method based on minutiae point according to claim 1, it is characterized in that: run into bifurcation if found in described step 3 when belonging to effective minutiae point of RCS coordinate system, then this bifurcation belongs to RCS coordinate system, and the minutiae point on the following crestal line of bifurcation does not enter RCS coordinate system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410650866.7A CN104361325A (en) | 2014-11-14 | 2014-11-14 | Fingerprint feature construction method based on minutiae |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410650866.7A CN104361325A (en) | 2014-11-14 | 2014-11-14 | Fingerprint feature construction method based on minutiae |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104361325A true CN104361325A (en) | 2015-02-18 |
Family
ID=52528583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410650866.7A Pending CN104361325A (en) | 2014-11-14 | 2014-11-14 | Fingerprint feature construction method based on minutiae |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104361325A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112733670A (en) * | 2020-12-31 | 2021-04-30 | 北京海鑫科金高科技股份有限公司 | Fingerprint feature extraction method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4607384A (en) * | 1984-05-01 | 1986-08-19 | At&T - Technologies, Inc. | Fingerprint classification arrangement |
| JP2002190031A (en) * | 2000-10-11 | 2002-07-05 | Hiroaki Kunieda | Curve identification system |
| CN101814131A (en) * | 2009-02-25 | 2010-08-25 | 中国科学院自动化研究所 | Method for improving security of fuzzy fingerprint safe |
-
2014
- 2014-11-14 CN CN201410650866.7A patent/CN104361325A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4607384A (en) * | 1984-05-01 | 1986-08-19 | At&T - Technologies, Inc. | Fingerprint classification arrangement |
| JP2002190031A (en) * | 2000-10-11 | 2002-07-05 | Hiroaki Kunieda | Curve identification system |
| CN101814131A (en) * | 2009-02-25 | 2010-08-25 | 中国科学院自动化研究所 | Method for improving security of fuzzy fingerprint safe |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112733670A (en) * | 2020-12-31 | 2021-04-30 | 北京海鑫科金高科技股份有限公司 | Fingerprint feature extraction method and device, electronic equipment and storage medium |
| CN112733670B (en) * | 2020-12-31 | 2024-02-27 | 北京海鑫科金高科技股份有限公司 | Fingerprint feature extraction method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101539993B (en) | Multi-acquisition-instrument fingerprint crossing-matching method based on size scaling estimation | |
| CN101620677B (en) | Fingerprint identification method based on triangulation and LOD technology | |
| CN107346550B (en) | It is a kind of for the three dimensional point cloud rapid registering method with colouring information | |
| CN103136525B (en) | High-precision positioning method for special-shaped extended target by utilizing generalized Hough transformation | |
| CN103927532B (en) | Person's handwriting method for registering based on stroke feature | |
| CN104765768A (en) | Mass face database rapid and accurate retrieval method | |
| CN101727452B (en) | Image processing method and device | |
| CN104978582B (en) | Shelter target recognition methods based on profile angle of chord feature | |
| CN105096298A (en) | Grid feature point extraction method based on fast line extraction | |
| CN105354841A (en) | Fast matching method and system for remote sensing images | |
| CN103954280A (en) | Rapid, high-robustness and autonomous fixed star identification method | |
| CN104102909A (en) | Vehicle characteristic positioning and matching method based on multiple-visual information | |
| CN104077769A (en) | Error matching point pair removing algorithm in image registration | |
| CN108021878B (en) | Contour line negative-direction landform intelligent identification method | |
| Feng et al. | Fingerprint indexing using ridge invariants | |
| CN105427287A (en) | Projection transformation-based connected region marking method | |
| CN101582114A (en) | Fingerprint identification method based on rotation angle | |
| CN103733225A (en) | Characteristic point coordination system, characteristic point coordination method, and recording medium | |
| CN110084779A (en) | A kind of extraction of aircraft thickness covering end surface features point and denoising method based on laser scanning | |
| CN106022348A (en) | Finger retrieving method base on specific point direction field and fingerprint projection | |
| CN104361325A (en) | Fingerprint feature construction method based on minutiae | |
| CN111489386B (en) | Point cloud characteristic point extraction method, device, storage medium, equipment and system | |
| WO2017107406A1 (en) | Information recognition method and system using sweat gland position information | |
| CN104361331A (en) | Fingerprint matching method based on bipartite graph optimal matching | |
| CN102332088B (en) | Vote symbolic machine visual identification method based on run length feature |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150218 |