CN106407920A - Stripe noise elimination method of fingerprint image - Google Patents
Stripe noise elimination method of fingerprint image Download PDFInfo
- Publication number
- CN106407920A CN106407920A CN201610808563.2A CN201610808563A CN106407920A CN 106407920 A CN106407920 A CN 106407920A CN 201610808563 A CN201610808563 A CN 201610808563A CN 106407920 A CN106407920 A CN 106407920A
- Authority
- CN
- China
- Prior art keywords
- pixel
- fingerprint image
- fringes noise
- image block
- matrixes
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000008030 elimination Effects 0.000 title abstract description 4
- 238000003379 elimination reaction Methods 0.000 title abstract description 4
- 238000002372 labelling Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 208000031481 Pathologic Constriction Diseases 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 210000001215 vagina Anatomy 0.000 description 1
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
- G06V40/1347—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Collating Specific Patterns (AREA)
- Image Input (AREA)
- Image Analysis (AREA)
Abstract
The present invention belongs to the fingerprint recognition field and provides a stripe noise elimination method of a fingerprint image. The method includes the following steps that: a fingerprint image is obtained, and image enhancement is performed on the fingerprint image; the position of stripe noises and the direction field of each fingerprint image block are acquired according to the pixels of the fingerprint image which has been subjected to image enhancement; and interpolation operation is performed on the stripe noises according to the position of the stripe noises and the direction field of each fingerprint image block, so that the stripe noises can be eliminated. With the stripe noise elimination method of the fingerprint image adopted, the stripe noises in the fingerprint image can be effectively eliminated, a variety of kinds of indicators of a fingerprint recognition system can be improved, and the accuracy of fingerprint image recognition can be improved.
Description
Technical field
The present invention relates to the fringes noise removing method in fingerprint identification technology field, more particularly, to fingerprint image.
Background technology
At present, the application of mobile fingerprint identifying system is more and more extensive, using also more and more convenient, however, with to mobile phone
The going deep into of the application of fingerprint recognition system, the demand more and more higher to fingerprint recognition index for the user, but due to each side such as hardware
The reason face, the various noise of fingerprint image generally existing in gatherer process, the presence of this noise is deposited to fingerprint recognition
In certain impact, in sum, exist in prior art and lead to impact to refer on there is noise during Fingerprint recognition
The problem of stricture of vagina identification.
Content of the invention
It is an object of the invention to provide the fringes noise removing method of fingerprint image is it is intended to solve presence in prior art
On there is a problem of during Fingerprint recognition noise lead to affect fingerprint recognition.
The present invention is achieved in that the fringes noise removing method providing a kind of fingerprint image, and described fringes noise disappears
Except method comprises the following steps：
Obtain fingerprint image, and image enhaucament is carried out to described fingerprint image；
Pixel according to the fingerprint image after image enhaucament obtains the position of fringes noise；
Fingerprint image after image enhaucament is divided into multiple nonoverlapping fingerprint image blocks, and obtains each fingerprint
The field of direction of image block；
The field of direction of the position according to described fringes noise and each fingerprint image block described enters row interpolation to fringes noise
Computing is to eliminate fringes noise.
The embodiment of the present invention provides the fringes noise removing method of fingerprint image, obtains fingerprint image, and to fingerprint image
Carry out image enhaucament, the pixel according to the fingerprint image after image enhaucament obtains position and each fingerprint of fringes noise
The field of direction of image block, and the field of direction of the position according to fringes noise and each fingerprint image block enters row interpolation to fringes noise
Computing, to eliminate fringes noise, can effectively eliminate the fringes noise of fingerprint image presence, thus improving fingerprint recognition system
Various indexs, improve the accuracy rate of Fingerprint recognition.
Brief description
For the technical scheme being illustrated more clearly that in the embodiment of the present invention, below will be to embodiment or description of the prior art
In required use accompanying drawing be briefly described it should be apparent that, drawings in the following description be only the present invention some
Embodiment, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these
Accompanying drawing obtains other accompanying drawings.
Fig. 1 is a kind of flow chart of the fringes noise removing method of fingerprint image that an embodiment of the present invention provides；
Fig. 2 is in step S101 in the fringes noise removing method of a kind of fingerprint image that an embodiment of the present invention provides
The fingerprint image schematic diagram obtaining；
Fig. 3 is in step S101 in the fringes noise removing method of a kind of fingerprint image that an embodiment of the present invention provides
Fingerprint image is carried out with the image schematic diagram after image enhaucament；
Fig. 4 is step S102 in the fringes noise removing method of a kind of fingerprint image that an embodiment of the present invention provides
A kind of embodiment flow chart；
Fig. 5 is step S102 in the fringes noise removing method of a kind of fingerprint image that an embodiment of the present invention provides
Another embodiment flow chart；
Fig. 6 is step S103 in the fringes noise removing method of a kind of fingerprint image that an embodiment of the present invention provides
Flow chart；
Fig. 7 is step S103 in the fringes noise removing method of a kind of fingerprint image that an embodiment of the present invention provides
Field of direction schematic diagram；
Fig. 8 is step S104 in the fringes noise removing method of a kind of fingerprint image that an embodiment of the present invention provides
Remove the image schematic diagram after fringes noise；
Fig. 9 a is another width fingerprint image schematic diagram；
Fig. 9 b is to adopt fingerprint image schematic diagram after fringes noise removing method of the present invention to Fig. 9 a；
Figure 10 a is another width fingerprint image schematic diagram；
Figure 10 b is to adopt fingerprint image schematic diagram after fringes noise removing method of the present invention to Figure 10 a；
Figure 11 a is another width fingerprint image schematic diagram；
Figure 11 b is to adopt fingerprint image schematic diagram after fringes noise removing method of the present invention to Figure 11 a；
Figure 12 a is another width fingerprint image schematic diagram；
Figure 12 b is to adopt fingerprint image schematic diagram after fringes noise removing method of the present invention to Figure 12 a.
Specific embodiment
In order that the objects, technical solutions and advantages of the present invention become more apparent, below in conjunction with drawings and Examples, right
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only in order to explain the present invention, and
It is not used in the restriction present invention.
In order to technical scheme is described, to illustrate below by specific embodiment.
The embodiment of the present invention provides a kind of fringes noise removing method of fingerprint image, as shown in figure 1, fringes noise eliminates
Method comprises the following steps：
Step S101. obtains fingerprint image, and carries out image enhaucament to fingerprint image.
In step S101, specifically, the fingerprint image with fringes noise for the collection, it is for instance possible to use resolution is
112*88, as shown in Fig. 2 there are many nickings in visible fingerprint image.
In step S101, optionally, image enhaucament can be carried out using Laplace filter it is preferred that setting is filtered
The template of ripple device is (3*3)：
[-1,-1,-1；-1,9,-1；-1,-1,-1]；
The fingerprint image of striped noise is strengthened through Gauss and obtains after wave filter strengthening image, as shown in figure 3, fingerprint
Fringes noise seem and become apparent from.
Step S102. obtains the position of fringes noise according to the pixel of the fingerprint image after image enhaucament.
In step s 102, optionally, by obtaining the picture element matrix of fingerprint image, projective transformation is carried out to picture element matrix
To obtain the position of fringes noise.
Specifically, as shown in figure 4, step S102 comprises the following steps：
Step S1021. obtains 3 × 3 matrixes centered on each pixel in fingerprint image, and according to 3 × 3 matrixes pair
Each pixel is marked, and wherein, pixel does not include boundary pixel point.
In step S1021, specifically, gather each pixel in fingerprint image it is assumed that P4 is Current Scan pixel,
P3 is the pixel on the P4 pixel left side, and P5 is the pixel on the right of P4 pixel, then each position in 3 × 3 matrixes centered on P4
Relation is：
P0 P1 P2
P3 P4 P5
P6 P7 P8
In step S1021, according to 3 × 3 matrixes, pixel is marked, specifically includes：
When the pixel of first row and the 3rd row pixel in 3 × 3 matrixes detect certain pixel is all higher than and its phase
The adjacent pixel of secondary series pixel and the second preset value and when, this pixel is marked.
Specifically, scan fingerprint image really after removing boundary pixel point, if meet following condition simultaneously：
P0>P1+K, P2>P1+K；
P3>P4+K, P5>P4+K；
P6>P7+K, P8>P7+K；
Wherein K is empirical value, i.e. the second preset value, then this pixel of labelling is 255, if be unsatisfactory for, this pixel of labelling
Point is 0.
The image of the pixel composition after labelling is projected to carry out projective transformation to X-axis by step S1022.,
And when projection width in X-axis for the image that the pixel after labelling forms is more than the first preset value, judge to be located in X-axis
There is nicking in projection coordinate position.
In step S1022, specifically, the image re-flagging pixel is carried out projective transformation, upright projection is to throwing
In X-axis in shadow coordinate system, projection array is projecty [width], and width is the width of fingerprint image.If
projecty[x]>H, then it is assumed that the position that abscissa is x has nicking, is otherwise set to 0 projecty [x], wherein h is
Empirical value, i.e. the first preset value.
Further, as shown in figure 5, judging that in step S1022 the projection coordinate position being located in X-axis has nicking
Also include afterwards：
Step S1023. obtains maximal projection width according to the projection width in X-axis for the image of the pixel composition after labelling
Degree.
Whether projection width in X-axis for the image of the pixel composition after step S1024. judge mark throws more than maximum
Shadow width and the product of the 3rd preset value, are then to enter step S1025, the projection in X-axis corresponding to retaining projection is sat
Target nicking, no, then enter step S1026, delete the nicking of the corresponding projection coordinate in X-axis of projection.
The purpose of above-mentioned steps S1023 and step S1024 is to remove unconspicuous striped, specifically, traversal
Projecty [x], finds out maximal projection value maxproject, then traversal projecty [x] successively, if projecty [x]>a*
Maxproject then retains projecty [x], otherwise projecty [x] is set to 0.A is empirical value, i.e. the 3rd preset value.
Through above-mentioned steps S1021 to step S1024, nicking noise can be determined according to the value of projecty [x]
Position, i.e. projecty [x]>Obtained noise position when 0.
Fingerprint image after image enhaucament is divided into multiple nonoverlapping fingerprint image blocks by step S103., and obtains
Take the field of direction of each fingerprint image block.
In step s 103, a series of fingerprint image block fingerprint image I piecemeal being nonoverlapping w*w, and obtain every
The squared gradient vector of individual fingerprint image block, the squared gradient vector further according to each fingerprint image block obtains the field of direction.
In step s 103, specifically, as shown in fig. 6, the field of direction obtaining each fingerprint image block includes：
Step S1031. obtains horizontal gradient and the vertical gradient of each pixel each fingerprint image block Nei.
In step S1031, specifically, the level of each pixel in each fingerprint image block is obtained by below equation
Gradient：
Vx (x, y)=2* (P5-P3)+(P2-P0)+(P8-P6)；
Obtain the vertical gradient of each pixel in each fingerprint image block by below equation：
Vy (x, y)=2* (P7-P1)+(P6-P0)+(P8-P2)；
Wherein, vx (x, y) is the horizontal gradient of each pixel, and vy (x, y) is the vertical gradient of each pixel, each
Pixel forms 3 × 3 matrixes centered on this pixel with pixel about, and P0 is first in 3 × 3 matrixes
The pixel of the pixel of row first row, P1 is the pixel of the pixel of the first row secondary series in 3 × 3 matrixes, and P2 is position
The pixel of the tertial pixel of the first row in 3 × 3 matrixes, P4 is the pixel of this pixel, and P3 is positioned at 3 × 3 matrixes
In the pixel of the second row first row pixel, P5 is the picture of the pixel of the second row secondary series in 3 × 3 matrixes
Element, P6 is the pixel of the pixel of the third line first row in 3 × 3 matrixes, and P7 is the third line in 3 × 3 matrixes
The pixel of the pixel of secondary series, P8 is the pixel of the tertial pixel of the third line in 3 × 3 matrixes.
Step S1032. obtains the squared gradient vector of each fingerprint image block according to horizontal gradient and vertical gradient.
In step S1031, specifically, the block gradient vector of each fingerprint image block is obtained according to below equation：
Obtain the squared gradient vector of each fingerprint image block according to below equation：
GX=2*dx*dy；
GY=dx2-dy2.
Step S1033. obtains the field of direction of each fingerprint image block according to the squared gradient vector of each fingerprint image block.
In step S1031, specifically, the squared gradient absolute value of a vector UGX, UGY of each fingerprint image block are obtained；
Obtain the field of direction of each fingerprint image block according to below equation：
If UGY>UGX and GY<0, pDirection=0；
If UGY<=UGX and GX<0, pDirection=1；
If UGY>UGX and GY>=0, pDirection=2；
If UGY<=UGX and GX>=0, pDirection=3；
Wherein, pDirection is the field of direction, and as pDirection=0, the field of direction is 0 degree, works as pDirection=1
When, the field of direction is 45 degree, and as pDirection=2, the field of direction is 90 degree, and as pDirection=3, the field of direction is 135
Degree.
As shown in fig. 7, the field of direction for acquisition fingerprint image.
Step S104. enters row interpolation according to the position of fringes noise and the field of direction of each fingerprint image block to fringes noise
Computing is to eliminate fringes noise.
In step S104, the field of direction being obtained by above-mentioned steps carries out difference to fringes noise, specifically,
When pDirection is equal to 0 or 2, and P4<P3 and P4<During P5,
P4=(P3+P5)/2；
When pDirection is equal to 1, and P4<P2 and P4<During P6,
P4=(P2+P6)/2；
When pDirection is equal to 3, and P4<P0 and P4<During P8,
P4=(P0+P8)/2.
As described in Figure 8, be through step S104 remove fringes noise after image schematic diagram.
The embodiment of the present invention provides the fringes noise removing method of fingerprint image, obtains fingerprint image, and to fingerprint image
Carry out image enhaucament, the pixel according to the fingerprint image after image enhaucament obtains position and each fingerprint of fringes noise
The field of direction of image block, and the field of direction of the position according to fringes noise and each fingerprint image block enters row interpolation to fringes noise
Computing, to eliminate fringes noise, can effectively eliminate the fringes noise of fingerprint image presence, thus improving fingerprint recognition system
Various indexs, improve the accuracy rate of Fingerprint recognition.
Based on the method for above-mentioned offer, the present invention carries out test and comparison to multiple with fringes noise fingerprint image：
As Fig. 9 a, 10a, 11a, 12a, it is all the fingerprint image with fringes noise, Fig. 9 b, 10b, 11b, 12b are and it
Corresponding, eliminate the image after fringes noise through the inventive method, can see that striped this method can be effectively by comparing
Elimination fringes noise.
Those of ordinary skill in the art are it is to be appreciated that combine the list of each example of the embodiments described herein description
Unit and algorithm steps, being capable of being implemented in combination in electronic hardware or computer software and electronic hardware.These functions are actually
To be executed with hardware or software mode, the application-specific depending on technical scheme and design constraint.Professional and technical personnel
Each specific application can be used different methods to realize described function, but this realization is it is not considered that exceed
The scope of the present invention.
Those skilled in the art can be understood that, for convenience and simplicity of description, the system of foregoing description,
Device and the specific work process of unit, may be referred to the corresponding process in preceding method embodiment, will not be described here.
It should be understood that disclosed system, apparatus and method in several embodiments provided herein, permissible
Realize by another way.For example, device embodiment described above is only schematically, for example, described unit
Divide, only a kind of division of logic function, actual can have other dividing mode when realizing, for example multiple units or assembly
Can in conjunction with or be desirably integrated into another system, or some features can be ignored, or does not execute.Another, shown or
The coupling each other discussing or direct-coupling or communication connection can be by some interfaces, the indirect coupling of device or unit
Close or communicate to connect, can be electrical, mechanical or other forms.
The described unit illustrating as separating component can be or may not be physically separate, show as unit
The part showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.The mesh to realize this embodiment scheme for some or all of unit therein can be selected according to the actual needs
's.
In addition, can be integrated in a processing unit in each functional unit in each embodiment of the present invention it is also possible to
It is that unit is individually physically present it is also possible to two or more units are integrated in a unit.
If described function realized using in the form of SFU software functional unit and as independent production marketing or use when, permissible
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
Partly being embodied in the form of software product of part that prior art is contributed or this technical scheme, this meter
Calculation machine software product is stored in a storage medium, including some instructions with so that a computer equipment (can be individual
People's computer, server, or network equipment etc.) execution each embodiment methods described of the present invention all or part of step.
And aforesaid storage medium includes：USB flash disk, portable hard drive, read only memory (ROM, Read-Only Memory), random access memory are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.
Above content is to further describe it is impossible to assert with reference to specific preferred implementation is made for the present invention
Being embodied as of the present invention is confined to these explanations.For general technical staff of the technical field of the invention,
Without departing from making some equivalent substitutes or obvious modification on the premise of present inventive concept, and performance or purposes are identical, all should
It is considered as belonging to the scope of patent protection that the present invention is determined by the claims submitted to.
Claims (9)
1. a kind of fingerprint image fringes noise removing method it is characterised in that described fringes noise removing method include following
Step：
Obtain fingerprint image, and image enhaucament is carried out to described fingerprint image；
Pixel according to the fingerprint image after image enhaucament obtains the position of fringes noise；
Fingerprint image after image enhaucament is divided into multiple nonoverlapping fingerprint image blocks, and obtains each fingerprint image
The field of direction of block；
The field of direction of the position according to described fringes noise and each fingerprint image block described carries out interpolation arithmetic to fringes noise
To eliminate fringes noise.
2. fringes noise removing method as claimed in claim 1 it is characterised in that described according to the finger after image enhaucament
The pixel of print image obtains the position of fringes noise, including：
Obtain 3 × 3 matrixes centered on each pixel in fingerprint image, and according to described 3 × 3 matrixes to each pixel
It is marked, wherein, pixel does not include boundary pixel point；
The image of the pixel composition after labelling is projected to X-axis to carry out projective transformation, and the picture after labelling
When projection width in X-axis for the image of vegetarian refreshments composition is more than the first preset value, judge that the projection coordinate position being located in X-axis is deposited
In nicking.
3. fringes noise removing method as claimed in claim 2 it is characterised in that described according to described 3 × 3 matrixes to pixel
Point is marked, including：
When the pixel of first row and the 3rd row pixel in 3 × 3 matrixes detect certain pixel is all higher than being adjacent
The pixel of secondary series pixel and the second preset value and when, this pixel is marked.
4. fringes noise removing method as claimed in claim 2 is it is characterised in that the projection that described judgement is located in X-axis is sat
Cursor position also includes after there is nicking：
Projection width in X-axis for the image according to the pixel composition after labelling obtains maximal projection width；
Whether the projection width in X-axis for the image of the pixel composition after judge mark is more than described maximal projection width and the
The product of three preset values, is then to retain the nicking of the corresponding projection coordinate in X-axis of described projection, no, then delete
The nicking of the corresponding projection coordinate in X-axis of described projection.
5. fringes noise removing method as claimed in claim 1 is it is characterised in that the side of each fingerprint image block of described acquisition
Include to field：
Obtain horizontal gradient and the vertical gradient of each pixel each fingerprint image block Nei；
Obtain the squared gradient vector of each fingerprint image block according to described horizontal gradient and described vertical gradient；
The field of direction of each fingerprint image block according to the squared gradient vector of each fingerprint image block described obtains.
6. fringes noise removing method as claimed in claim 5 is it is characterised in that every in each fingerprint image block of described acquisition
The horizontal gradient of individual pixel and vertical gradient, including：
Obtain the horizontal gradient of each pixel in each fingerprint image block by below equation：
Vx (x, y)=2* (P5-P3)+(P2-P0)+(P8-P6)；
Obtain the vertical gradient of each pixel in each fingerprint image block by below equation：
Vy (x, y)=2* (P7-P1)+(P6-P0)+(P8-P2)；
Wherein, vx (x, y) is the horizontal gradient of each pixel, and vy (x, y) is the vertical gradient of each pixel, each pixel
Point and pixel 3 × 3 matrixes centered on this pixel for the formation about, P0 is the first row in 3 × 3 matrixes the
The pixel of the pixel of string, P1 is the pixel of the pixel of the first row secondary series in 3 × 3 matrixes, P2 be positioned at 3 ×
The pixel of the tertial pixel of the first row in 3 matrixes, P4 is the pixel of this pixel, and P3 is in 3 × 3 matrixes
The pixel of the pixel of two row first rows, P5 is the pixel of the pixel of the second row secondary series in 3 × 3 matrixes, and P6 is
The pixel of the pixel of the third line first row in 3 × 3 matrixes, P7 is the third line secondary series in 3 × 3 matrixes
The pixel of pixel, P8 is the pixel of the tertial pixel of the third line in 3 × 3 matrixes.
7. fringes noise removing method as claimed in claim 6 is it is characterised in that described according to described horizontal gradient and described
Vertical gradient obtains the squared gradient vector of each fingerprint image block, including：
Obtain the block gradient vector of each fingerprint image block according to below equation：
Obtain the squared gradient vector of each fingerprint image block according to below equation：
GX=2*dx*dy；
GY=dx2-dy2；
Wherein, w is configured to line number and the columns of matrix for fingerprint image block.
8. fringes noise removing method as claimed in claim 7 is it is characterised in that each fingerprint image block described in described basis
Squared gradient vector obtain the field of direction of each fingerprint image block described, including：
Obtain the squared gradient absolute value of a vector UGX, UGY of each fingerprint image block described；
Obtain the field of direction of each fingerprint image block according to below equation：
If UGY>UGX and GY<0, pDirection=0；
If UGY<=UGX and GX<0, pDirection=1；
If UGY>UGX and GY>=0, pDirection=2；
If UGY<=UGX and GX>=0, pDirection=3；
Wherein, pDirection is the field of direction, and as pDirection=0, the field of direction is 0 degree, as pDirection=1,
The field of direction is 45 degree, and as pDirection=2, the field of direction is 90 degree, and as pDirection=3, the field of direction is 135 degree.
9. fringes noise removing method as claimed in claim 8 is it is characterised in that the described position according to described fringes noise
With the field of direction of each fingerprint image block described, interpolation arithmetic is carried out to eliminate fringes noise to fringes noise, including：
When pDirection is equal to 0 or 2, and P4<P3 and P4<During P5, P4=(P3+P5)/2；
When pDirection is equal to 1, and P4<P2 and P4<During P6, P4=(P2+P6)/2；
When pDirection is equal to 3, and P4<P0 and P4<During P8, P4=(P0+P8)/2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610808563.2A CN106407920B (en) | 2016-09-07 | 2016-09-07 | The fringes noise removing method of fingerprint image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610808563.2A CN106407920B (en) | 2016-09-07 | 2016-09-07 | The fringes noise removing method of fingerprint image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106407920A true CN106407920A (en) | 2017-02-15 |
| CN106407920B CN106407920B (en) | 2019-08-23 |
Family
ID=57999089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610808563.2A Active CN106407920B (en) | 2016-09-07 | 2016-09-07 | The fringes noise removing method of fingerprint image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106407920B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107038432A (en) * | 2017-05-12 | 2017-08-11 | 西安电子科技大学 | Fingerprint image orientation extracting method based on frequency information |
| CN108932498A (en) * | 2018-07-05 | 2018-12-04 | 刘金涛 | Office space fingerprint recognition authenticates mechanism |
| CN109117754A (en) * | 2018-07-25 | 2019-01-01 | 徐敬媛 | Real time fingerprint identifying platform |
| CN109785470A (en) * | 2018-08-03 | 2019-05-21 | 秦广民 | Gate inhibition's intelligent control mechanism, supermarket |
| CN110263754A (en) * | 2019-06-28 | 2019-09-20 | 北京迈格威科技有限公司 | Shield lower fingerprint and removes shading method, apparatus, computer equipment and storage medium |
| CN111784599A (en) * | 2020-06-24 | 2020-10-16 | 西北工业大学 | Method for eliminating infrared image stripe noise |
| CN112967206A (en) * | 2021-03-25 | 2021-06-15 | 西安中科立德红外科技有限公司 | Self-adaptive infrared image and video vertical line removing method based on image blocking |
| CN116883292A (en) * | 2023-09-07 | 2023-10-13 | 上海海栎创科技股份有限公司 | pseudo-Gaussian-based image direction field acquisition method, system and computer equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101253536A (en) * | 2005-06-30 | 2008-08-27 | 日本电气株式会社 | Fingerprint image background detecting device and detecting method |
| CN102737230A (en) * | 2012-05-25 | 2012-10-17 | 华中科技大学 | Non-local mean filtering method based on direction field estimation |
| CN103413116A (en) * | 2013-06-14 | 2013-11-27 | 南京信息工程大学 | Effective fingerprint direction field calculating method |
-
2016
- 2016-09-07 CN CN201610808563.2A patent/CN106407920B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101253536A (en) * | 2005-06-30 | 2008-08-27 | 日本电气株式会社 | Fingerprint image background detecting device and detecting method |
| CN102737230A (en) * | 2012-05-25 | 2012-10-17 | 华中科技大学 | Non-local mean filtering method based on direction field estimation |
| CN103413116A (en) * | 2013-06-14 | 2013-11-27 | 南京信息工程大学 | Effective fingerprint direction field calculating method |
Non-Patent Citations (5)
| Title |
|---|
| 卞维新 等: "低质量指纹图像方向场提取", 《中国图象图形学报》 * |
| 卞维新 等: "线性投影分析在指纹方向场提取中的应用研究", 《小型微型计算机系统》 * |
| 张晔 等: "一种基于信息融合的指纹奇异点提取及纹型分类算法", 《计算机应用与软件》 * |
| 梅园 等: "一种基于梯度的健壮的指纹方向场估计算法", 《计算机研究与发展》 * |
| 陈艳艳: "一种改进的指纹方向场估算方法", 《现代计算机》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107038432B (en) * | 2017-05-12 | 2019-12-17 | 西安电子科技大学 | Fingerprint image direction field extraction method based on frequency information |
| CN107038432A (en) * | 2017-05-12 | 2017-08-11 | 西安电子科技大学 | Fingerprint image orientation extracting method based on frequency information |
| CN108932498A (en) * | 2018-07-05 | 2018-12-04 | 刘金涛 | Office space fingerprint recognition authenticates mechanism |
| CN108932498B (en) * | 2018-07-05 | 2020-08-21 | 岳阳县辉通物联网科技有限公司 | Fingerprint identification authentication mechanism in office place |
| CN109117754A (en) * | 2018-07-25 | 2019-01-01 | 徐敬媛 | Real time fingerprint identifying platform |
| CN109785470A (en) * | 2018-08-03 | 2019-05-21 | 秦广民 | Gate inhibition's intelligent control mechanism, supermarket |
| CN110263754A (en) * | 2019-06-28 | 2019-09-20 | 北京迈格威科技有限公司 | Shield lower fingerprint and removes shading method, apparatus, computer equipment and storage medium |
| CN110263754B (en) * | 2019-06-28 | 2021-08-06 | 北京迈格威科技有限公司 | Method and device for removing shading of off-screen fingerprint, computer equipment and storage medium |
| CN111784599A (en) * | 2020-06-24 | 2020-10-16 | 西北工业大学 | Method for eliminating infrared image stripe noise |
| CN111784599B (en) * | 2020-06-24 | 2022-04-29 | 西北工业大学 | Method for eliminating infrared image stripe noise |
| CN112967206A (en) * | 2021-03-25 | 2021-06-15 | 西安中科立德红外科技有限公司 | Self-adaptive infrared image and video vertical line removing method based on image blocking |
| CN116883292A (en) * | 2023-09-07 | 2023-10-13 | 上海海栎创科技股份有限公司 | pseudo-Gaussian-based image direction field acquisition method, system and computer equipment |
| CN116883292B (en) * | 2023-09-07 | 2023-11-28 | 上海海栎创科技股份有限公司 | pseudo-Gaussian-based image direction field acquisition method, system and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106407920B (en) | 2019-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106407920A (en) | Stripe noise elimination method of fingerprint image | |
| CN108875511B (en) | Image generation method, device, system and computer storage medium | |
| CN104899853B (en) | Image area dividing method and device | |
| CN110189341B (en) | Image segmentation model training method, image segmentation method and device | |
| CN105117464B (en) | Application pushing method and device and service equipment | |
| CN107633216A (en) | The feature extracting method and device of high-spectrum remote sensing | |
| CN110209551B (en) | Abnormal equipment identification method and device, electronic equipment and storage medium | |
| CN110633289A (en) | License plate number determining method, server and parking management system | |
| CN104574358A (en) | Method and apparatus for scene segmentation from focal stack images | |
| CN110969092A (en) | Pulse signal denoising method and device and terminal equipment | |
| CN105953773A (en) | Method and device for acquiring gradient angle of slope | |
| CN110457396A (en) | One kind being based on block chain scientific data processing method, device, equipment and storage medium | |
| CN107977504B (en) | Asymmetric reactor core fuel management calculation method and device and terminal equipment | |
| CN108960012B (en) | Feature point detection method and device and electronic equipment | |
| CN110751490A (en) | Fraud identification method and device, electronic equipment and computer-readable storage medium | |
| CN103914373B (en) | A kind of method and apparatus for priority corresponding to determining module characteristic information | |
| CN108268868A (en) | Inclination value-acquiring method and device, terminal, the storage medium of ID Card Image | |
| CN111047579B (en) | Feature quality assessment method and image feature uniform extraction method | |
| CN105069747A (en) | Image interpolation method and device | |
| CN104298570A (en) | Data processing method and device | |
| CN104322057A (en) | Pattern processing apparatus, pattern processing method, and pattern processing program | |
| CN109961405B (en) | Image filtering method and device | |
| CN108805903B (en) | AR engine-based multi-mark point identification method and device | |
| CN111429399B (en) | Linear detection method and device | |
| CN107085727A (en) | The determination method and its device of a kind of image boundary function |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |