CN107463916A - Fingerprint minutiae feature acquisition methods based on spiral operator - Google Patents
Fingerprint minutiae feature acquisition methods based on spiral operator Download PDFInfo
- Publication number
- CN107463916A CN107463916A CN201710703010.5A CN201710703010A CN107463916A CN 107463916 A CN107463916 A CN 107463916A CN 201710703010 A CN201710703010 A CN 201710703010A CN 107463916 A CN107463916 A CN 107463916A
- Authority
- CN
- China
- Prior art keywords
- mrow
- fingerprint
- msup
- minutiae
- spiral
- 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
- G06V40/1347—Preprocessing; Feature extraction
- G06V40/1353—Extracting features related to minutiae or pores
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
Fingerprint minutiae feature acquisition methods of the invention based on spiral operator are related to the technologies such as fingerprint pretreatment；This method is obtained three steps and formed by fingerprint pretreatment, field of behaviour demodulation minutiae feature；Fingerprint image is regarded as to the striated pattern signal in a two-dimensional variable cycle, minutiae point in fingerprint image then shows as the spiral singular point in the field of behaviour, fingerprint minutiae test problems are converted into function Solve problems, wherein, phase demodulating is obtained by solution of the analytical function to single base signal, and spiral singular point is obtained by calculating extreme point that field of behaviour Poincare exponential integral obtains；Information in being operated present invention, avoiding binaryzation, refinement etc. loses problem, with very strong noise immunity, also the post processing of fake minutiae need not be carried out, effectively reduce system time cost, simultaneously, not by being influenceed during fingerprint image acquisition caused by finger pressure, translation, rotation and dry and wet environment, have the advantages that computation complexity is low, processing speed is fast, comparison accuracy is high.
Description
Technical field
Fingerprint minutiae feature acquisition methods of the invention based on spiral operator are related to fingerprint pretreatment technology, striated pattern
Signal phase technology for information acquisition and fingerprint minutiae feature extractive technique.
Background technology
Fingerprint, because it has the characteristics that stability, collection property, generality and uniqueness, it has also become biological characteristic
Synonym.Fingerprint refers to the convex recessed uneven streakline of the positive surface skin in human finger end, the regular arrangement form of these streaklines
Different line types.Fingerprint recognition system is a typical PRS, including fingerprint image acquisition, pretreatment, spy
The module such as sign extraction and matching.Wherein, the levels of precision of Finger print characteristic abstract has important shadow to the whether accurate of fingerprint matching
Ring.In fingerprint image, due to the discontinuous and caused minutiae point of crestal line, such as bifurcation, end point, starting point and singular point
It is the characteristic information being most widely used in fingerprint recognition system, therefore, the minutiae point that reliably and effectively takes the fingerprint just turns into and referred to
Top priority in line identifying system.
Include at present using the more time domain minutiae point step that takes the fingerprint：The smooth of fingerprint image, region detection, two-value
The morphological image operation such as change and refinement, take the fingerprint minutiae point on this basis.Wherein, binary conversion treatment can cause part former
The loss of beginning information, influence the order of accuarcy of comparison result.It is and burr present in fingerprint image, short-term, broken string, false bridge, small
The noise such as hole and island, fake minutiae can be produced in micronization processes again, the post-processing operation that increase removes fake minutiae will
Considerable degree of increase identifying system time cost.Importantly, fingerprint image acquisition process is by finger pressure, translation and rotation
The factor such as turning influences, and can cause the nonlinear change in final extraction details point coordinates and direction, make the minutiae point extracted in time domain
Information can not ensure higher credibility, influence system of fingerprints recognition efficiency.
The content of the invention
In view of the above-mentioned problems, the invention discloses a kind of fingerprint minutiae feature acquisition methods based on spiral operator, phase
To the details in fingerprint point extracting method based on morphological image in time domain, present invention, avoiding in the operation such as binaryzation, refinement
Information lose problem, there is very strong noise immunity, need not also carry out the post processing of fake minutiae, effectively reduction system time into
This；Meanwhile the operation of this method in a frequency domain is not made by finger pressure, translation, rotation and dry and wet environment during fingerprint image acquisition
Into influence, have the advantages that computation complexity is low, processing speed is fast, comparison accuracy is high.
What present disclosure was realized in：
Fingerprint minutiae feature acquisition methods based on spiral operator, by fingerprint pretreatment, field of behaviour demodulation minutiae point
Feature obtains three step compositions.
The above-mentioned fingerprint minutiae feature acquisition methods based on spiral operator, described fingerprint pretreatment step are specially：
Fingerprint is considered as a two-dimentional FM/AM signal, fingerprint stripe of the frequency through ovennodulation is established in two-dimensional space domain
Model：
Wherein, a (x, y) is grey level compensation item, and b (x, y) is the range value of modulation item,To believe comprising fingerprint characteristic
The phase of breath, n (x, y) are the high-frequency noise in fingerprint image；
The noise and grey level compensation value in fingerprint signal are eliminated using Gassian low-pass filter and mean filter, is obtained：
Wherein, g (x, y) is the fingerprint signal of only amplitude information and phase information.
The above-mentioned fingerprint minutiae feature acquisition methods based on spiral operator, described field of behaviour demodulation step are by fingerprint
Phase information demodulates from the two-dimentional FM/AM fingerprint signal for removing interference to be come, and is specially：
First, in a frequency domain with two spiral operator H1(u, v) and H2(u, v) respectively with fingerprint signal g (x, y) Fu
Leaf transformation G (u, v) carries out convolution, obtains two single base component of signal R1(u, v) and R2(u,v)；
Wherein,
R1(u, v)=H1(u,v)G(u,v)
R2(u, v)=H2(u,v)G(u,v)
U represents frequency domain abscissa, and v represents frequency domain ordinate；
Secondly, by R1(u, v) and R2(u, v) is transformed into time domain, obtains r respectively1(x, y) and r2(x, y), make g (x, y), r1
(x, y) and r2(x, y) collectively forms the single base signal of a three-dimensional；
Order：
gN=[g (x, y), r1(x,y),r2(x,y)]
gNFor three components of the single base signal of the three-dimensional；
Finally, three-dimensional single base signal is solved according to analytical function, obtains partial fingerprint image direction and Local Phase
Position information；
Amplitude information b (x, y), i.e. fingerprint modulation item range value are obtained according to equation below：
Local direction θ (x, y) is obtained according to equation below：
Phase information is obtained according to equation below
Described phase informationFor the field of behaviour.
The above-mentioned fingerprint minutiae feature acquisition methods based on spiral operator, described minutiae feature obtaining step are specific
For：In the field of behaviour, fingerprint minutiae is expressed as spiral singular point, details in fingerprint vertex neighborhood direction is shown as into spiral shape
State, it is right-handed screw to define clock wise spirals form, and counter-clockwise helical form is negative spiral；Details in fingerprint is calculated according to equation below
The characteristic information of point：
If the q (i, j) being calculated is：
2 π, then the point is minutiae point, corresponding right-handed screw；
- 2 π, then the point is minutiae point, corresponding negative spiral；
Other, then the point is not minutiae point.
Beneficial effect：
Firstth, in the methods of the invention, in order to reduce the interference effect in fingerprint image, the low frequency of finger print information will be represented
Signal enhancing, the high frequency signal attenuation of noise is represented, eliminate the influence of noise and grey level compensation value in fingerprint image, only had
The finger print information of amplitude information and phase information, irrelevant variable is reduced for subsequent treatment, reduces computation complexity.
Secondth, in the methods of the invention, using the relation between analytical function component from the direct demodulation phase of original fingerprint
, retain original fingerprint information, without graphical operations such as binaryzation, refinements, without going pseudo- post processing, improve result of calculation
While accuracy, system time cost is reduced.
3rd, in the methods of the invention, fingerprint is regarded to the striated pattern signal in a two-dimensional variable cycle as, in a frequency domain
Fingerprint minutiae extraction process is carried out, avoids during fingerprint image acquisition the factor such as finger pressure, translation, rotation to time domain
Details point coordinates and the non-linear effects in direction are extracted, while reducing computation complexity, largely improves fingerprint knowledge
Other system effectiveness.
Brief description of the drawings
Fig. 1 is the minutiae point schematic diagram in the field of behaviour.
Fig. 2 is minutiae point eight neighborhood direction schematic diagram in the field of behaviour.
Specific embodiment
The specific embodiment of the invention is described in further detail below in conjunction with the accompanying drawings.
The fingerprint minutiae feature acquisition methods based on spiral operator of the present embodiment, by fingerprint pretreatment, field of behaviour solution
The minutiae feature that reconciles obtains three step compositions.
Described fingerprint pretreatment step is specially：Fingerprint is considered as a two-dimentional FM/AM signal, in two-dimensional space
Fingerprint stripe model of the frequency through ovennodulation is established in domain：
Wherein, a (x, y) is grey level compensation item, and b (x, y) is the range value of modulation item,To believe comprising fingerprint characteristic
The phase of breath, n (x, y) are the high-frequency noise in fingerprint image；
The noise and grey level compensation value in fingerprint signal are eliminated using Gassian low-pass filter and mean filter, is obtained：
Wherein, g (x, y) is the fingerprint signal of only amplitude information and phase information.
Described field of behaviour demodulation step is the two-dimentional FM/AM fingerprint signal from removal interference by fingerprint phase information
In demodulate come, be specially：
First, in a frequency domain with two spiral operator H1(u, v) and H2(u, v) respectively with fingerprint signal g (x, y) Fu
Leaf transformation G (u, v) carries out convolution, obtains two single base component of signal R1(u, v) and R2(u,v)；
Wherein,
R1(u, v)=H1(u,v)G(u,v)
R2(u, v)=H2(u,v)G(u,v)
U represents frequency domain abscissa, and v represents frequency domain ordinate；
Secondly, by R1(u, v) and R2(u, v) is transformed into time domain, obtains r respectively1(x, y) and r2(x, y), make g (x, y), r1
(x, y) and r2(x, y) collectively forms the single base signal of a three-dimensional；
Order：
gN=[g (x, y), r1(x,y),r2(x,y)]
gNFor three components of the single base signal of the three-dimensional；
Finally, three-dimensional single base signal is solved according to analytical function, obtains partial fingerprint image direction and Local Phase
Position information；
Amplitude information b (x, y), i.e. fingerprint modulation item range value are obtained according to equation below：
Local direction θ (x, y) is obtained according to equation below：
Phase information is obtained according to equation below
Described phase informationFor the field of behaviour.
Described minutiae feature obtaining step is specially：In the field of behaviour, it is unusual that fingerprint minutiae is expressed as spiral
Point, details in fingerprint vertex neighborhood direction is shown as into spiral, it is right-handed screw to define clock wise spirals form, counter-clockwise helical shape
State is negative spiral；Minutiae point and its eight neighborhood direction difference in the field of behaviour are as depicted in figs. 1 and 2；Calculated according to equation below
The characteristic information of fingerprint minutiae：
If the q (i, j) being calculated is：
2 π, then the point is minutiae point, corresponding right-handed screw；
- 2 π, then the point is minutiae point, corresponding negative spiral；
Other, then the point is not minutiae point.
Claims (4)
1. the fingerprint minutiae feature acquisition methods based on spiral operator, it is characterised in that demodulated by fingerprint pretreatment, the field of behaviour
Three step compositions are obtained with minutiae feature.
2. the fingerprint minutiae feature acquisition methods according to claim 1 based on spiral operator, it is characterised in that described
Fingerprint pretreatment step be specially：Fingerprint is considered as a two-dimentional FM/AM signal, frequency is established in two-dimensional space domain
Fingerprint stripe model through ovennodulation：
Wherein, a (x, y) is grey level compensation item, and b (x, y) is the range value of modulation item,To include fingerprint feature information
Phase, n (x, y) are the high-frequency noise in fingerprint image；
The noise and grey level compensation value in fingerprint signal are eliminated using Gassian low-pass filter and mean filter, is obtained：
Wherein, g (x, y) is the fingerprint signal of only amplitude information and phase information.
3. the fingerprint minutiae feature acquisition methods according to claim 1 based on spiral operator, it is characterised in that described
Field of behaviour demodulation step be by fingerprint phase information from remove interference two-dimentional FM/AM fingerprint signal in demodulate come,
Specially：
First, in a frequency domain with two spiral operator H1(u, v) and H2(u, v) becomes with fingerprint signal g (x, y) Fourier respectively
Change G (u, v) and carry out convolution, obtain two single base component of signal R1(u, v) and R2(u,v)；
Wherein,
<mrow>
<msub>
<mi>H</mi>
<mn>1</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>,</mo>
<mi>v</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>i</mi>
<mfrac>
<mi>u</mi>
<msqrt>
<mrow>
<msup>
<mi>u</mi>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mi>v</mi>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
</mfrac>
</mrow>
<mrow>
<msub>
<mi>H</mi>
<mn>2</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>,</mo>
<mi>v</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>i</mi>
<mfrac>
<mi>v</mi>
<msqrt>
<mrow>
<msup>
<mi>u</mi>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mi>v</mi>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
</mfrac>
</mrow>
R1(u, v)=H1(u,v)G(u,v)
R2(u, v)=H2(u,v)G(u,v)
U represents frequency domain abscissa, and v represents frequency domain ordinate；
Secondly, by R1(u, v) and R2(u, v) is transformed into time domain, obtains r respectively1(x, y) and r2(x, y), make g (x, y), r1(x,y)
And r2(x, y) collectively forms the single base signal of a three-dimensional；
Order：
gN=[g (x, y), r1(x,y),r2(x,y)]
gNFor three components of the single base signal of the three-dimensional；
Finally, three-dimensional single base signal is solved according to analytical function, obtains partial fingerprint image direction and local phase letter
Breath；
Amplitude information b (x, y), i.e. fingerprint modulation item range value are obtained according to equation below：
<mrow>
<mi>b</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msqrt>
<mrow>
<mi>g</mi>
<msup>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msub>
<mi>r</mi>
<mn>1</mn>
</msub>
<msup>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msub>
<mi>r</mi>
<mn>2</mn>
</msub>
<msup>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
</mrow>
Local direction θ (x, y) is obtained according to equation below：
<mrow>
<mi>&theta;</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msup>
<mi>tan</mi>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msup>
<mrow>
<mo>(</mo>
<mo>-</mo>
<mfrac>
<mrow>
<msub>
<mi>r</mi>
<mn>1</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mi>r</mi>
<mn>2</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>)</mo>
</mrow>
</mrow>
Phase information is obtained according to equation below
Described phase informationFor the field of behaviour.
4. the fingerprint minutiae feature acquisition methods according to claim 1 based on spiral operator, it is characterised in that described
Minutiae feature obtaining step be specially：In the field of behaviour, fingerprint minutiae is expressed as spiral singular point, by details in fingerprint
Vertex neighborhood direction shows as spiral, and it is right-handed screw to define clock wise spirals form, and counter-clockwise helical form is negative spiral；Press
The characteristic information of fingerprint minutiae is calculated according to equation below：
If the q (i, j) being calculated is：
2 π, then the point is minutiae point, corresponding right-handed screw；
- 2 π, then the point is minutiae point, corresponding negative spiral；
Other, then the point is not minutiae point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710703010.5A CN107463916A (en) | 2017-08-16 | 2017-08-16 | Fingerprint minutiae feature acquisition methods based on spiral operator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710703010.5A CN107463916A (en) | 2017-08-16 | 2017-08-16 | Fingerprint minutiae feature acquisition methods based on spiral operator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107463916A true CN107463916A (en) | 2017-12-12 |
Family
ID=60550114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710703010.5A Pending CN107463916A (en) | 2017-08-16 | 2017-08-16 | Fingerprint minutiae feature acquisition methods based on spiral operator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107463916A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109063681A (en) * | 2018-08-28 | 2018-12-21 | 哈尔滨理工大学 | Direction of fingerprint information acquisition method based on fingerprint phase gradient |
| CN109902569A (en) * | 2019-01-23 | 2019-06-18 | 上海思立微电子科技有限公司 | Conversion method, device and the fingerprint identification method of fingerprint image |
| CN112070032A (en) * | 2020-09-10 | 2020-12-11 | 哈尔滨理工大学 | Fingerprint minutiae acquiring method based on fingerprint phase gradient |
| CN112084999A (en) * | 2020-09-22 | 2020-12-15 | 哈尔滨理工大学 | Method for acquiring fingerprint direction information through signal analysis |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09147113A (en) * | 1995-11-27 | 1997-06-06 | Nippon Telegr & Teleph Corp <Ntt> | Fingerprint collating method and device therefor |
| CN1588424A (en) * | 2004-07-02 | 2005-03-02 | 清华大学 | Finger print identifying method based on broken fingerprint detection |
| CN101777128A (en) * | 2009-11-25 | 2010-07-14 | 中国科学院自动化研究所 | Fingerprint minutiae matching method syncretized to global information and system thereof |
-
2017
- 2017-08-16 CN CN201710703010.5A patent/CN107463916A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09147113A (en) * | 1995-11-27 | 1997-06-06 | Nippon Telegr & Teleph Corp <Ntt> | Fingerprint collating method and device therefor |
| CN1588424A (en) * | 2004-07-02 | 2005-03-02 | 清华大学 | Finger print identifying method based on broken fingerprint detection |
| CN101777128A (en) * | 2009-11-25 | 2010-07-14 | 中国科学院自动化研究所 | Fingerprint minutiae matching method syncretized to global information and system thereof |
Non-Patent Citations (4)
| Title |
|---|
| CHUONG T.NGUYEN 等: "AM-FM Models，Partial Hilbert Transform，and the Monogenic Signal", 《2012 19TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING》 * |
| MICHAEL UNSER 等: "Multiresolution Monogenic Signal Analysis Using the Riesz–Laplace Wavelet Transform", 《IEEE TRANSACTIONS ON IMAGE PROCESSING》 * |
| SHENG LI 等: "An Improved Scheme for Full Fingerprint Reconstruction", 《IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY》 * |
| 严汇莹: "一种免校准指纹相位特征提取算法的研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109063681A (en) * | 2018-08-28 | 2018-12-21 | 哈尔滨理工大学 | Direction of fingerprint information acquisition method based on fingerprint phase gradient |
| CN109902569A (en) * | 2019-01-23 | 2019-06-18 | 上海思立微电子科技有限公司 | Conversion method, device and the fingerprint identification method of fingerprint image |
| CN112070032A (en) * | 2020-09-10 | 2020-12-11 | 哈尔滨理工大学 | Fingerprint minutiae acquiring method based on fingerprint phase gradient |
| CN112084999A (en) * | 2020-09-22 | 2020-12-15 | 哈尔滨理工大学 | Method for acquiring fingerprint direction information through signal analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107463916A (en) | Fingerprint minutiae feature acquisition methods based on spiral operator | |
| Jiang et al. | Detecting the fingerprint minutiae by adaptive tracing the gray-level ridge | |
| Khan et al. | Efficient hardware implementation for fingerprint image enhancement using anisotropic Gaussian filter | |
| Yu et al. | A novel license plate location method based on wavelet transform and EMD analysis | |
| CN106485740B (en) | A kind of multidate SAR image registration method of combination stable point and characteristic point | |
| CN102222229B (en) | Method for preprocessing finger vein images | |
| CN107563377A (en) | It is a kind of to detect localization method using the certificate key area of edge and character area | |
| CN102629318B (en) | Fingerprint image segmentation method based on support vector machine | |
| CN101604385A (en) | A kind of palm grain identification method and palmmprint recognition device | |
| CN103955674B (en) | Palm print image acquisition device and palm print image positioning and segmenting method | |
| CN102629316B (en) | Image enhancement method in automatic fingerprint identification technology | |
| CN102254163A (en) | Template size self-adaptable Gabor fingerprint image enhancement method | |
| CN104424641A (en) | Detection method for image fuzzy tampering | |
| CN109063681A (en) | Direction of fingerprint information acquisition method based on fingerprint phase gradient | |
| CN106778754A (en) | A kind of industrial ammeter digit recognition method of robust | |
| CN107506742A (en) | Direction of fingerprint characteristic-acquisition method based on fringe | |
| Hastings | Ridge enhancement in fingerprint images using oriented diffusion | |
| CN104933407A (en) | Fingerprint recognition method based on SIFT | |
| Patel et al. | An improved approach in fingerprint recognition algorithm | |
| Wei et al. | Detection of lane line based on Robert operator | |
| Ding et al. | Fingerprint enhancement rooted in the spectra diffusion by the aid of the 2D adaptive Chebyshev band-pass filter with orientation-selective | |
| CN104657983B (en) | A kind of fabric ball top Density Detection method filtered based on Gabor | |
| CN106446903A (en) | Recognition method for position of wave-band switch of instrument | |
| CN102663756A (en) | Registration method of special shaped elements and high-density packing components in printed circuit board | |
| CN105095854B (en) | The contactless online palmprint matching process of low resolution |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171212 |