CN107451549A - The sef-adapting filter of contactless Fingerprint Image Enhancement and Curvature-driven - Google Patents
The sef-adapting filter of contactless Fingerprint Image Enhancement and Curvature-driven Download PDFInfo
- Publication number
- CN107451549A CN107451549A CN201710605485.0A CN201710605485A CN107451549A CN 107451549 A CN107451549 A CN 107451549A CN 201710605485 A CN201710605485 A CN 201710605485A CN 107451549 A CN107451549 A CN 107451549A
- Authority
- CN
- China
- Prior art keywords
- mrow
- mfrac
- msub
- fingerprint
- fingerprint image
- 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
- 238000001228 spectrum Methods 0.000 claims abstract description 31
- 238000000034 method Methods 0.000 claims description 24
- 238000001914 filtration Methods 0.000 claims description 12
- 230000003595 spectral effect Effects 0.000 claims description 8
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims 1
- 238000007781 pre-processing Methods 0.000 claims 1
- 230000002708 enhancing effect Effects 0.000 abstract description 9
- 230000000694 effects Effects 0.000 abstract description 4
- 238000005286 illumination Methods 0.000 description 6
- 230000000452 restraining effect Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000004243 sweat 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
- G06V40/13—Sensors therefor
- G06V40/1312—Sensors therefor direct reading, e.g. contactless acquisition
-
- G06T5/77—
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20056—Discrete and fast Fourier transform, [DFT, FFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Abstract
The invention discloses a kind of contactless Fingerprint Image Enhancement and the sef-adapting filter of Curvature-driven.While the contactless Fingerprint Image Enhancement enhancing information in fingerprint that the invention provides, the noise pattern frequency in singular point region and non-singular point region is effective filtered out and has remained the basic frequency in fingerprint ridge pattern；Reduce gradation of image dynamic range, fingerprint image gray value is reached preset value, so as to improve the accuracy in take the fingerprint direction and ridge frequency；The main component of information in fingerprint frequency spectrum is enhanced, weakens submember.And the sef-adapting filter of Curvature-driven provided by the present invention realizes and the low area of curvature and high curvature areas in information in fingerprint are filtered respectively, while filter effect is strengthened, original crestal line structure of fingerprint is protected well.
Description
Technical field
The present invention relates to a kind of Fingerprint Image Enhancement and a kind of wave filter, strengthens more particularly, to a kind of contactless fingerprint
The sef-adapting filter of method and Curvature-driven.
Background technology
It is also one of maximally effective biometric feature earliest that fingerprint, which is,.Fingerprint enhancement is weight in fingerprint recognition system
The pretreatment link wanted, image enhancement effects directly affect follow-up recognition result.Existing many fingerprint identification technologies are most
Number be for restraining formula fingerprint image, the formula fingerprint of restraining have it is unhygienic, invisible fingerprints of sweat illegally usurp, deformation and user it is not friendly
The defects of good.Application of the fingerprint in field of biological recognition is limited to a certain extent.The defects of to avoid restraining formula fingerprint, scholar
The equipment such as proposition digital camera gather contactless fingerprint.But contactless fingerprint image is sampled in gatherer process
The other factors such as resolution ratio, camera exposure degree and focusing influence, and image is inevitably present Noise, crestal line and valley line pair
The shortcomings of and backlight lower than degree is uneven, it is thus impossible to by the existing treatment technology for restraining formula fingerprint that handles for contactless
Fingerprint image.
The crestal line change in fingerprint image non-singular point region is smooth, and crestal line directional curvature is relatively low, but singular point region
Crestal line change is violent, and crestal line directional curvature is higher.Because follow-up fingerprint matching and identification, rely primarily on the detection of singular point,
Therefore the main purpose of fingerprint enhancing is accurately to recover by noise pollution or the fingerprint ridge line structure of fracture.
Most of existing wave filters, either spatial filter or frequency domain filter, do not accounted in filtering
Fingerprint ridge curvature of a curve, therefore have the following disadvantages:Existing method is to carry out identical or class to whole fingerprint ridge line mostly
As filtering algorithm, do not differentiate between the singular point region of higher curvature and the non-singular point region of low curvature.Therefore these methods are difficult
Estimate the ridge frequency in the singular point region of low quality fingerprint.The contactless general contrast of fingerprint is low, uneven illumination and noisy,
Therefore existing method cannot be directly used to contactless fingerprint enhancing.
The content of the invention
In order to solve the problems of in the prior art, of the invention first purpose is to provide a kind of contactless
Fingerprint Image Enhancement, this method can be in the fingers collected to uneven illumination, contrast and noisy contactless fingerprint
While print image information is strengthened, moreover it is possible to effectively filter out the noise pattern frequency in singular point region and non-singular point region simultaneously
Retain the basic frequency in fingerprint ridge pattern.
In addition, second object of the present invention is to provide a kind of sef-adapting filter of Curvature-driven, the wave filter energy
It is enough that high curvature areas in fingerprint image and low area of curvature are filtered respectively, can be well while filtering is strengthened
Protect original crestal line structure in fingerprint image.
Here, to realize first purpose of the present invention, the contactless Fingerprint Image Enhancement provided, first to being adopted
The fingerprint image signal collected is pre-processed；The direction in pretreated fingerprint image and frequency are extracted again；Calculate fingerprint
The orientation consistency of image, corresponding Butterworth trap band is built in frequency domain further according to direction, frequency and orientation consistency
Hinder wave filter HNR(u, v) and Butterworth trap bandpass filter HNP(u, v) is respectively to the low area of curvature of fingerprint and fingerprint Gao Qu
Rate region is filtered, and inverse Fourier transform reconstruct entire image is carried out to filtered fingerprint image.
Method provided by the invention is by high-pass and low-pass filter respectively to the low area of curvature and fingerprint higher curvature in fingerprint
Region is filtered, and while the information in fingerprint collected to contactless fingerprint strengthens, is effective filtered out
The noise pattern frequency in singular point region and non-singular point region simultaneously remains the basic frequency in fingerprint ridge pattern.In addition,
This method, which can also be directed to uneven illumination, contrast and noisy fingerprint image, to be strengthened.
Specifically, the fingerprint image signal carry out pretreatment be the fingerprint image of collection is carried out histogram equalization and
Normalization pretreatment, is concretely comprised the following steps：
A：The fingerprint image of collection is divided into overlapped w × w fingerprint-block B (i, j)；
B：Each fingerprint-block B (i, j) is normalized using one below relational expression, the fingerprint after being normalized
Block image g (x, y)；
Or
F (x, y) is pixel value at fingerprint-block B (i, j) certain point in formula (1), formula (2), M0And V0Ash respectively set in advance
Spend average and variance；M and V is respectively the average and variance of former fingerprint image.
Fingerprint image is pre-processed using normalized mode, reduces gradation of image dynamic range, makes
Fingerprint image gray value reaches preset value, so as to improve the accuracy in take the fingerprint direction and ridge frequency.
Specifically, the direction and frequency in the pretreated fingerprint image of extraction are extracted especially by following steps：
A：To fingerprint image plus cosine window, discrete fourier change then is carried out to fingerprint image；
B：Root filtering process is carried out to the fingerprint image in step A after discrete fourier changes；
C：The direction of filtered fingerprint image is asked for using formula (3)~formula (6)；After filtering being asked using formula (7)~formula (8)
Fingerprint image frequency；
M in formula (4) and formula (5)iAnd MlAsked for by formula (6)：
M=∑s | F (θ, r) | (6)
F (θ, r) is polar coordinates of the fingerprint image through Fourier spectrum in formula (6), and r is modulus value, and it meets l≤r≤l+1, its
Middle l spans are 1~15；
The frequency of the fingerprint image is asked in the following manner：
Using the midpoint of spectral image as origin, radius is that l carries out equal portions segmentation to spectral image, and using formula (7), we can
To obtain the spectrum energy that each concentric circles is included
El=∑ | F (θ, r) | l ＜=r ＜ l+1 (7)
Wherein l represents the radius of concentric circles；L value is 1~15；After trying to achieve the spectrum energy that each concentric circles includes,
The distance L of spectrum peak and origin is determined using formula (8).
The frequency of fingerprint image is L inverse.
Root filtering process is carried out to information in fingerprint, the main component of information in fingerprint frequency spectrum is enhanced, weakens
Submember.
Specifically, the orientation consistency is asked for using relationship below：
In formula：I, j is the coordinate of certain point in fingerprint image, and θ (u, v) is the angle of the central point in crestal line spectrum distribution region
Degree, u, v are the centre coordinate in crestal line spectrum distribution region, and w is the window size of fingerprint image.
3rd, specifically, the Butterworth notch band stop filters HNR(u, v) is by two high-pass filter HkAnd H-kForm,
HNR(u, v) meets following relation：
Wherein：D0kAnd D0-kFor constant, 1.5, n are taken1And n2Respectively high-pass filter HkAnd H-kExponent number, take 2~5；Dk
(u, v) and D-k(u, v) is asked for by relationship below respectively：
In formula (10), formula (11) u, v be crestal line spectrum distribution region centre coordinate, uk、vk、u-kAnd v-kRespectively two is high
The centre frequency coordinate of bandpass filter,For the origin of coordinate system；
The Butterworth trap bandpass filter HNP(u, v) expression formula is (13).
HNP(u, v)=1-HNR(u,v) (13)
Specifically, the Butterworth trap bandpass filter HNP(u, v) is Gaussian band-pass filter.
To realize second object of the present invention, in the sef-adapting filter for the Curvature-driven that this is provided, including Bart
Butterworth notch band stop filters HNR(u, v) and Butterworth trap bandpass filter HNP(u,v)。
Realized using low pass filter and high-pass filter to the low area of curvature and higher curvature in information in fingerprint
Region filters respectively, while filter effect is strengthened, protects original crestal line structure of fingerprint well.
Specifically, the Butterworth notch band stop filters HNR(u, v) is made up of two high-pass filters, and Bart irrigates
The expression formula of this notch band stop filters is formula (10)；The expression formula of the Butterworth trap bandpass filter is formula (13).
Specifically, the Butterworth trap bandpass filter HNP(u, v) is Gaussian band-pass filter.
The sef-adapting filter of Curvature-driven provided by the present invention goes for being used in any fingerprint recognition system
Fingerprint recognition, in particular for because of uneven illumination, contrast is low and the fingerprint image that noise be present has remarkable result.
Compared with prior art, the beneficial effect of Fingerprint Image Enhancement provided by the present invention is：Strengthen fingerprint image letter
While breath, the noise pattern frequency in singular point region and non-singular point region is effective filtered out and has remained fingerprint ridge mould
Basic frequency in formula；Reduce gradation of image dynamic range, fingerprint image gray value is reached preset value, so as to improve
Print direction and the accuracy of ridge frequency；The main component of information in fingerprint frequency spectrum is enhanced, weakens submember.
And the sef-adapting filter of Curvature-driven provided by the present invention is realized to the low curvature in information in fingerprint
Region and high curvature areas filter respectively, while filter effect is strengthened, protect original crestal line structure of fingerprint well.
Brief description of the drawings
Fig. 1 is the flow chart of contactless Fingerprint Image Enhancement provided by the present invention；
Fig. 2 is filter result comparison diagram of the low quality fingerprint image under various algorithms.
Embodiment
In order to which technical scheme provided by the present invention is better described, herein with reference to the drawings and specific embodiments to the present invention
Technical scheme be further described.
The flow chart of contactless Fingerprint Image Enhancement provided by the present invention is as shown in figure 1, this method is known for fingerprint
The fingerprint in the information in fingerprint of extraction is strengthened during not, is easy to fingerprint recognition system to identify exactly and refers to
Line.This method can be used for restraining formula fingerprint recognition system, it can also be used to which contactless fingerprint recognition system, it is specific treated
Cheng Shi：The fingerprint image signal collected is pre-processed first；The direction in pretreated fingerprint image is extracted again
Field and frequency fields；The orientation consistency of fingerprint image is calculated, phase is built in frequency domain further according to direction, frequency and orientation consistency
The Butterworth notch band stop filters H answeredNR(u, v) and Butterworth trap bandpass filter HNP(u, v) is low to fingerprint respectively
Area of curvature and fingerprint high curvature areas are filtered, and inverse Fourier transform reconstruct view picture figure is carried out to filtered fingerprint image
Picture.
This method can be handled the fingerprint image view picture extracted, but in order to ensure that enhancing effect is optimal, it is best
It is that the fingerprint image of extraction is divided into some fingerprint-blocks to be handled by this method again, herein just with the fingerprint image after division
As information is described in detail to Fingerprint Image Enhancement provided by the present invention, concretely comprise the following steps：
Step 1：Take the fingerprint information, generates fingerprint image；
Step 2：Fingerprint-block B (i, j) by Fingerprint Image Segmentation into overlapped w × w；Wherein each fingerprint-block it is overlapping
Part can be any part, and 12 pixels of such as each fingerprint block edge are overlapped；
Step 3：Histogram equalization and normalization pretreatment are carried out to each fingerprint-block；Wherein, after normalization pretreatment
To normalized image can be any, the application provides a kind of expression of each fingerprint-block image g (x, y) after normalization herein
Mode, as shown in formula (1) and formula (2),
Or
F (x, y) is pixel value at fingerprint-block B (i, j) certain point in formula, M0And V0Gray average respectively set in advance and
Variance；M and V is respectively the average and variance of former fingerprint image, can be drawn by prior art；
Step 4：Direction and the frequency of pretreated each fingerprint-block are extracted, any of which can be used herein to referring to
Direction and frequency in line block are extracted, and extracting method is as follows provided herein by the application：
A：To each fingerprint-block B (i, j) plus cosine window, discrete fourier change then is carried out to each fingerprint-block B (i, j)；
Added cosine window is preferably raised cosine window, it is preferably rebuild enhanced fingerprint image, reduce fingerprint-block it
Between blocking effect；
B：Root filtering process is carried out by root wave filter to each fingerprint-block in step A after discrete fourier changes；
C：The direction of filtered each fingerprint-block is asked for using formula (3)~formula (6)Filtering is asked using formula (7)~formula (8)
The frequency f of each fingerprint-block afterwards；
M in formula (4) and formula (5)iAnd MlAsked for by formula (6)：
M=∑s | F (θ, r) | (6)
F (θ, r) is polar coordinates of the fingerprint image through Fourier spectrum in formula (6), and r is modulus value, and it meets l≤r≤l+1, its
Middle l spans are 1~15；
And the frequency of the fingerprint image is asked in the following manner：
Using the midpoint of spectral image as origin, radius is that l carries out equal portions segmentation to spectral image, and using formula (7), we can
To obtain the spectrum energy that each concentric circles is included
(7)
El=∑ | F (θ, r) | l ＜=r ＜ l+1
Wherein l represents the radius of concentric circles；L value is 1~15；After trying to achieve the spectrum energy that each concentric circles includes,
The distance L of spectrum peak and origin is determined using formula (8).
The frequency f of fingerprint image is L inverse；
Step 5：Calculating the orientation consistency of each fingerprint-block, (orientation consistency reflects the side of a certain fingerprint-block of fingerprint image
To the direction otherness with each piece of its neighborhood, therefore weigh using orientation consistency index the intensity of variation in direction.For height
Area of curvature, the value of its orientation consistency is always very low, close to 0, non-high curvature areas, the value of orientation consistency close to
1), the application asks for the orientation consistency of each fingerprint-block using relationship below：
In formula：I, j is the coordinate of certain point in fingerprint-block, and θ (u, v) is the angle of the central point in crestal line spectrum distribution region
Degree, u, v are the centre coordinate in crestal line spectrum distribution region, and w is the window size of fingerprint-block；
Step 6：Constructed according to the direction θ of each fingerprint-block, frequency f and orientation consistency Coh (i, j) information in frequency domain
Corresponding Butterworth notch band stop filters HNR(u, v) and Butterworth trap bandpass filter HNP(u, v), for referring to
Low curvature area and higher curvature area in print image filter respectively is filtered enhancing, enhances the fingerprint image letter in each fingerprint-block
Breath；Butterworth notch band stop filters H in the stepNR(u, v) and Butterworth trap bandpass filter HNP(u, v) can
To use existing any a low pass filter and high-pass filter H, and it is then used by the application：Butterworth trap
Bandstop filter HNR(u, v) is by two two high-pass filter HkAnd H-kForm, Butterworth notch band stop filters HNR(u,
V) expression formula is such as shown in (10)：
Wherein：HNR(u, v) be low pass filter bandwidth, D0kAnd D0-kFor constant, 1.5, n are taken1And n2Respectively high pass is filtered
Ripple device HkAnd H-kExponent number, take 2~5；Dk(u, v) and D-k(u, v) is asked for by relationship below respectively：
In formula (11), formula (12) u, v be crestal line spectrum distribution region centre coordinate, uk、vk、u-kAnd v-kRespectively two is high
The centre frequency coordinate of bandpass filter,For the origin of coordinate system；
The Butterworth trap bandpass filter HNPThe expression formula of (u, v) is formula (13).
HNP(u, v)=1-HNR(u,v) (13)
Step 7：To carrying out inverse Fourier transform through the filtered each fingerprint-block of step 6, view picture figure is reconstructed by each fingerprint-block
Picture.
It is described by high-pass filter H in step 6 thereonkAnd H-kThe Butterworth notch band stop filters H of compositionNR
(u, v), high-pass filter HkAnd H-kCentre frequency be translated into Butterworth notch band stop filters HNRIn (u, v).
And Butterworth trap bandpass filter HNP(u, v) uses Gaussian band-pass filter, more effectively enhances Gao Qu
Rate region crestal line information and the purpose for protecting original crestal line structure；Other wave filters can certainly be used.Here, the application institute
The condition that the Gaussian band-pass filter of use to be met is as follows：
The otherwise (15) of H (p)=0
In formula：ρ is the frequency of the fingerprint image signal in input filter, can be asked for by formula (16)；ρ0Centered on frequency
Rate, ρBWFor the bandwidth of wave filter；
In formula：U, v is the centre coordinate of the main region of crestal line spectrum distribution.
Above is view picture Fingerprint Image Segmentation is carried out enhancing processing to each fingerprint-block, finally led to again into some fingerprint-blocks
Cross each fingerprint-block reconstruct view picture fingerprint image.Above method is intended merely to make enhancing effect processing mode that is more preferable, and taking, removes
It is outer with upper type processing, directly view picture fingerprint image can also be handled, not be divided into some fingerprint-blocks.More than
Pixel value, the direction of each fingerprint-block and each fingerprint at certain point coordinates, fingerprint-block point in example in described fingerprint-block
Frequency of block etc., should be then that certain point in the fingerprint image in view picture fingerprint image is sat when directly handling view picture fingerprint image
Frequency of pixel value, the direction of fingerprint image and fingerprint image etc. at certain point in mark, fingerprint image.
In addition, the present invention is when handling fingerprint image, it is contemplated that a kind of non-stationary information during fingerprint image, to referring to
When print image is handled, because its local message is not proper periodicity two-position signal, some local fingerprint figures
As the main spectrum component and unobvious of information, if directly asking for local ridge orientation and frequency, larger error unavoidably be present, be
Reduce this situation, the present invention before root filtering is carried out to fingerprint image by frequency spectrum of the formula (16) to fingerprint image at
Reason, retain its crestal line spectrum component, weaken noise spectrum.
F (u, v)=I (u, v) × Q (17)
In formula：F (u, v) is crestal line frequency spectrum, and I (u, v) is spectral magnitude, and Q can then be asked for by formula (18).
In formula：I (u, v) is spectral magnitude, and DC is frequency spectrum flip-flop, and k is constant, value 7.
Here, the sef-adapting filter of Curvature-driven provided herein includes Butterworth notch band stop filters
HNR(u, v) and Butterworth trap bandpass filter HNP(u, v), wherein Butterworth notch band stop filters HNR(u, v) can be with
It is made up of independent Butterworth filter, it is preferred that be made up of two high-pass filters, now, the resistance of Butterworth trap band
Wave filter HNRThe expression formula of (u, v) is formula (10)；And Butterworth trap bandpass filter HNPThe expression formula of (u, v) is then formula
(13)。
Wherein, Butterworth trap bandpass filter HNP(u, v) is then Gaussian band-pass filter.
In order to verify the performance of the sef-adapting filter of Curvature-driven provided by the present invention, it have chosen several low quality and refer to
Print image is as shown in Figure 2.(a), (b), (c), (d) and (e) represents fingerprint artwork, root wave filter, direction filter respectively in wherein Fig. 2
The result of ripple device, diffusion filter and wave filter of the present invention.The original image uneven illumination of the first row is even, and upper left is brighter, and
There are two long bands to cut off crestal line from left to right, the artwork left-half of the second row is more black, and human eye can hardly recognize streakline
And there is fracture and fuzzy in minutiae point, the streakline in artwork compared with blackboard point.The artwork lower right of the third line is too bright and causes streakline
It is fuzzy.
In order to preferably be analyzed filter result and be contrasted, enhancing image is entered with NIST NFIS2 open source softwares
Matched after row feature point extraction.Contactless Fingerprint Image Enhancement provided by the present invention and other method are contrasted.It is right
The false acceptance rate (FAR) of characteristic matching, false rejection rate (FRR) and etc. the objective evaluation standard of error rate (EER) counted
Calculate, obtained result is as shown in table 1.The filter result of the inventive method is equal in every objective evaluation index as can be seen from the table
Add, this also effectively illustrates that the filtering performance of the inventive method is better than other various methods from objective angle.In addition,
As can be known from Fig. 2, method proposed by the present invention is to low contrast, uneven illumination and noisy contactless Fingerprint enhancement
When, contrast between the noise, enhancing crestal line and valley line of contactless fingerprint can be effectively filtered out, while repair and strengthen correctly
Crestal line structure.
The matching result of table 1 contrasts
Although the foregoing describing the embodiment of the present invention, those skilled in the art should be appreciated that this
Be merely illustrative of, various changes or modifications can be made to present embodiment, without departing from the present invention principle and essence,
Protection scope of the present invention is only limited by the claims that follow.
Claims (9)
1. contactless Fingerprint Image Enhancement, it is characterised in that：This method is carried out to the fingerprint image signal collected first
Pretreatment；The direction in pretreated fingerprint image and frequency are extracted again；The orientation consistency of fingerprint image is calculated, further according to
Direction, frequency and orientation consistency build corresponding Butterworth notch band stop filters H in frequency domainNR(u, v) and Bart irrigate
This trap bandpass filter HNP(u, v) is filtered to the low area of curvature of fingerprint and fingerprint high curvature areas respectively, after filtering
Fingerprint image carry out inverse Fourier transform reconstruct entire image.
2. contactless Fingerprint Image Enhancement as claimed in claim 1, it is characterised in that：The fingerprint image signal carries out pre-
Processing is to carry out histogram equalization and normalization pretreatment to the fingerprint image of collection, is concretely comprised the following steps：
A：The fingerprint image of collection is divided into overlapped w × w fingerprint-block B (i, j)；
B：Each fingerprint-block B (i, j) is normalized using one below relational expression, the fingerprint-block figure after being normalized
As g (x, y)；
<mrow>
<mtable>
<mtr>
<mtd>
<mrow>
<mi>g</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msub>
<mi>M</mi>
<mn>0</mn>
</msub>
<mo>+</mo>
<msqrt>
<mfrac>
<mrow>
<msub>
<mi>V</mi>
<mn>0</mn>
</msub>
<msup>
<mrow>
<mo>(</mo>
<mi>f</mi>
<mo>(</mo>
<mrow>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
</mrow>
<mo>)</mo>
<mo>-</mo>
<mi>M</mi>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
<mi>V</mi>
</mfrac>
</msqrt>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>i</mi>
<mi>f</mi>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>></mo>
<mi>M</mi>
</mrow>
</mtd>
</mtr>
</mtable>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
Or
<mrow>
<mtable>
<mtr>
<mtd>
<mrow>
<mi>g</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msub>
<mi>M</mi>
<mn>0</mn>
</msub>
<mo>-</mo>
<msqrt>
<mfrac>
<mrow>
<msub>
<mi>V</mi>
<mn>0</mn>
</msub>
<msup>
<mrow>
<mo>(</mo>
<mi>f</mi>
<mo>(</mo>
<mrow>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
</mrow>
<mo>)</mo>
<mo>-</mo>
<mi>M</mi>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
<mi>V</mi>
</mfrac>
</msqrt>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>o</mi>
<mi>t</mi>
<mi>h</mi>
<mi>e</mi>
<mi>r</mi>
<mi>w</mi>
<mi>i</mi>
<mi>s</mi>
<mi>e</mi>
</mrow>
</mtd>
</mtr>
</mtable>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
F (x, y) is pixel value at fingerprint-block B (i, j) certain point in formula (1), formula (2), M0And V0Gray scale respectively set in advance is equal
Value and variance；M and V is respectively the average and variance of former fingerprint image.
3. contactless Fingerprint Image Enhancement as claimed in claim 1 or 2, it is characterised in that：The extraction is pretreated
Direction and frequency in fingerprint image are extracted especially by following steps：
A：To fingerprint image plus cosine window, discrete fourier change then is carried out to fingerprint image；
B：Root filtering process is carried out to the fingerprint image in step A after discrete fourier changes；
C：The direction of filtered fingerprint image is asked for using formula (3)~formula (6)；Filtered finger is sought using formula (7)~formula (8)
The frequency of print image；
<mrow>
<mi>a</mi>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>15</mn>
</munderover>
<mrow>
<mo>(</mo>
<mfrac>
<msub>
<mi>M</mi>
<mi>i</mi>
</msub>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>l</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>15</mn>
</munderover>
<msub>
<mi>M</mi>
<mi>l</mi>
</msub>
</mrow>
</mfrac>
<mo>&times;</mo>
<mi>s</mi>
<mi>i</mi>
<mi>n</mi>
<mo>(</mo>
<mrow>
<mn>2</mn>
<mo>&times;</mo>
<mi>i</mi>
<mo>&times;</mo>
<mfrac>
<mn>180</mn>
<mn>16</mn>
</mfrac>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4</mn>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mi>b</mi>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>15</mn>
</munderover>
<mrow>
<mo>(</mo>
<mfrac>
<msub>
<mi>M</mi>
<mi>i</mi>
</msub>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>l</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>15</mn>
</munderover>
<msub>
<mi>M</mi>
<mi>l</mi>
</msub>
</mrow>
</mfrac>
<mo>&times;</mo>
<mi>c</mi>
<mi>o</mi>
<mi>s</mi>
<mo>(</mo>
<mrow>
<mn>2</mn>
<mo>&times;</mo>
<mi>i</mi>
<mo>&times;</mo>
<mfrac>
<mn>180</mn>
<mn>16</mn>
</mfrac>
</mrow>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>5</mn>
<mo>)</mo>
</mrow>
</mrow>
M in formula (4) and formula (5)iAnd MlAsked for by formula (6)：
M=∑s | F (θ, r) | (6)
F (θ, r) is polar coordinates of the fingerprint image through Fourier spectrum in formula (6), and r is modulus value, and it meets that l≤r≤l+1, wherein l take
It is 1~15 to be worth scope；
The frequency of the fingerprint image is asked in the following manner：
Using the midpoint of spectral image as origin, radius is that l carries out equal portions segmentation to spectral image, and each is asked for using formula (7)
The spectrum energy that concentric circles is included
El=∑ | F (θ, r) | l ＜=r ＜ l+1 (7)
Wherein l represents the radius of concentric circles；L value is 1~15；After trying to achieve the spectrum energy that each concentric circles includes, utilize
Formula (8) determines the distance L of spectrum peak and origin.
<mrow>
<mi>L</mi>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>15</mn>
</munderover>
<mfrac>
<msub>
<mi>r</mi>
<mi>i</mi>
</msub>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>l</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>15</mn>
</munderover>
<msub>
<mi>r</mi>
<mi>l</mi>
</msub>
</mrow>
</mfrac>
<mo>&times;</mo>
<mi>i</mi>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>8</mn>
<mo>)</mo>
</mrow>
</mrow>
The frequency of fingerprint image is L inverse.
4. the contactless Fingerprint Image Enhancement as described in claim 1 or 2 or 3, it is characterised in that：The orientation consistency profit
Asked for relationship below：
<mrow>
<mi>C</mi>
<mi>o</mi>
<mi>h</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<msqrt>
<mrow>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>u</mi>
<mo>=</mo>
<mi>i</mi>
<mo>-</mo>
<mfrac>
<mi>w</mi>
<mn>2</mn>
</mfrac>
</mrow>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mfrac>
<mi>w</mi>
<mn>2</mn>
</mfrac>
</mrow>
</munderover>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>v</mi>
<mo>=</mo>
<mi>j</mi>
<mo>-</mo>
<mfrac>
<mi>w</mi>
<mn>2</mn>
</mfrac>
</mrow>
<mrow>
<mi>j</mi>
<mo>+</mo>
<mfrac>
<mi>w</mi>
<mn>2</mn>
</mfrac>
</mrow>
</munderover>
<mi>cos</mi>
<msup>
<mrow>
<mo>(</mo>
<mrow>
<mn>2</mn>
<mi>&theta;</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>u</mi>
<mo>,</mo>
<mi>v</mi>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>u</mi>
<mo>=</mo>
<mi>i</mi>
<mo>-</mo>
<mfrac>
<mi>w</mi>
<mn>2</mn>
</mfrac>
</mrow>
<mrow>
<mi>i</mi>
<mo>+</mo>
<mfrac>
<mi>w</mi>
<mn>2</mn>
</mfrac>
</mrow>
</munderover>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>v</mi>
<mo>=</mo>
<mi>j</mi>
<mo>-</mo>
<mfrac>
<mi>w</mi>
<mn>2</mn>
</mfrac>
</mrow>
<mrow>
<mi>j</mi>
<mo>+</mo>
<mfrac>
<mi>w</mi>
<mn>2</mn>
</mfrac>
</mrow>
</munderover>
<mi>sin</mi>
<msup>
<mrow>
<mo>(</mo>
<mrow>
<mn>2</mn>
<mi>&theta;</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>u</mi>
<mo>,</mo>
<mi>v</mi>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
<mi>M</mi>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>9</mn>
<mo>)</mo>
</mrow>
</mrow>
In formula：I, j is the coordinate of certain point in fingerprint image, and θ (u, v) is the angle of the central point in crestal line spectrum distribution region,
U, v is the centre coordinate in crestal line spectrum distribution region, and w is the window size of fingerprint image.
5. contactless Fingerprint Image Enhancement as claimed in claim 1 or 2 or 3 or 4, it is characterised in that：The Butterworth
Notch band stop filters HNR(u, v) is by two high-pass filter HkAnd H-kForm, HNR(u, v) meets following relation：
<mrow>
<msub>
<mi>H</mi>
<mrow>
<mi>N</mi>
<mi>R</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>,</mo>
<mi>v</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mn>1</mn>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<mfrac>
<msub>
<mi>D</mi>
<mrow>
<mn>0</mn>
<mi>k</mi>
</mrow>
</msub>
<mrow>
<msub>
<mi>D</mi>
<mi>k</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>,</mo>
<mi>v</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>)</mo>
</mrow>
<mrow>
<mn>2</mn>
<msub>
<mi>n</mi>
<mn>1</mn>
</msub>
</mrow>
</msup>
</mrow>
</mfrac>
<mo>&times;</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mn>1</mn>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<mfrac>
<msub>
<mi>D</mi>
<mrow>
<mn>0</mn>
<mo>-</mo>
<mi>k</mi>
</mrow>
</msub>
<mrow>
<msub>
<mi>D</mi>
<mrow>
<mo>-</mo>
<mi>k</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>,</mo>
<mi>v</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>)</mo>
</mrow>
<mrow>
<mn>2</mn>
<msub>
<mi>n</mi>
<mn>2</mn>
</msub>
</mrow>
</msup>
</mrow>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>10</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein：D0kAnd D0-kFor constant, 1.5, n are taken1And n2Respectively high-pass filter HkAnd H-kExponent number, take 2~5；Dk(u,v)
And D-k(u, v) is asked for by relationship below respectively：
<mrow>
<msub>
<mi>D</mi>
<mi>k</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>,</mo>
<mi>v</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msup>
<mrow>
<mo>&lsqb;</mo>
<msup>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>-</mo>
<mfrac>
<mi>n</mi>
<mn>2</mn>
</mfrac>
<mo>-</mo>
<msub>
<mi>u</mi>
<mi>k</mi>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<mi>v</mi>
<mo>-</mo>
<mfrac>
<mi>m</mi>
<mn>2</mn>
</mfrac>
<mo>-</mo>
<msub>
<mi>v</mi>
<mi>k</mi>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>&rsqb;</mo>
</mrow>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
</msup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>11</mn>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mi>D</mi>
<mrow>
<mo>-</mo>
<mi>k</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>,</mo>
<mi>v</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msup>
<mrow>
<mo>&lsqb;</mo>
<msup>
<mrow>
<mo>(</mo>
<mi>u</mi>
<mo>-</mo>
<mfrac>
<mi>n</mi>
<mn>2</mn>
</mfrac>
<mo>+</mo>
<msub>
<mi>u</mi>
<mrow>
<mo>-</mo>
<mi>k</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<mrow>
<mo>(</mo>
<mi>v</mi>
<mo>-</mo>
<mfrac>
<mi>m</mi>
<mn>2</mn>
</mfrac>
<mo>+</mo>
<msub>
<mi>v</mi>
<mrow>
<mo>-</mo>
<mi>k</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
</msup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>12</mn>
<mo>)</mo>
</mrow>
</mrow>
In formula (10), formula (11) u, v be crestal line spectrum distribution region centre coordinate, uk、vk、u-kAnd v-kRespectively two high passes are filtered
The centre frequency coordinate of ripple device,For the origin of coordinate system；
The Butterworth trap bandpass filter HNP(u, v) expression formula is (13).
HNP(u, v)=1-HNR(u,v) (13)
6. the contactless Fingerprint Image Enhancement as described in claim 1 or 2 or 3 or 4 or 5, it is characterised in that：The Bart irrigates
This trap bandpass filter HNP(u, v) is Gaussian band-pass filter.
7. a kind of Curvature-driven being used in the contactless Fingerprint Image Enhancement described in claim 1-6 any one is adaptive
Answer wave filter, it is characterised in that：The wave filter includes Butterworth notch band stop filters HNR(u, v) and Butterworth trap band
Bandpass filter HNP(u,v)。
8. the sef-adapting filter of Curvature-driven as claimed in claim 7, it is characterised in that：The Butterworth trap band resistance
Wave filter HNR(u, v) is made up of two high-pass filters, and the expression formula of Butterworth notch band stop filters is formula (10)；Institute
The expression formula for stating Butterworth trap bandpass filter is formula (13).
9. the sef-adapting filter of Curvature-driven as claimed in claim 7 or 8, it is characterised in that：The Butterworth trap
Bandpass filter HNP(u, v) is Gaussian band-pass filter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710605485.0A CN107451549B (en) | 2017-07-24 | 2017-07-24 | Non-contact fingerprint enhancement method and curvature-driven adaptive filter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710605485.0A CN107451549B (en) | 2017-07-24 | 2017-07-24 | Non-contact fingerprint enhancement method and curvature-driven adaptive filter |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107451549A true CN107451549A (en) | 2017-12-08 |
| CN107451549B CN107451549B (en) | 2020-05-12 |
Family
ID=60488874
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710605485.0A Expired - Fee Related CN107451549B (en) | 2017-07-24 | 2017-07-24 | Non-contact fingerprint enhancement method and curvature-driven adaptive filter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107451549B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784195A (en) * | 2018-12-20 | 2019-05-21 | 金菁 | A kind of fingerprint identification method checked card for enterprise's fingerprint and system |
| CN109858418A (en) * | 2019-01-23 | 2019-06-07 | 上海思立微电子科技有限公司 | The treating method and apparatus of fingerprint image |
| CN110728201A (en) * | 2019-09-20 | 2020-01-24 | 南京元初科技有限公司 | Image processing method and device for fingerprint identification |
| CN111741031A (en) * | 2020-08-26 | 2020-10-02 | 深圳信息职业技术学院 | Block chain based network communication encryption method |
| CN112232159A (en) * | 2020-09-30 | 2021-01-15 | 墨奇科技（北京）有限公司 | Fingerprint identification method, device, terminal and storage medium |
| CN113313627A (en) * | 2021-06-08 | 2021-08-27 | 中国科学院大学 | Fingerprint image reconstruction method and fingerprint image feature extraction method and device |
| CN115035640A (en) * | 2022-08-10 | 2022-09-09 | 湖南朗国视觉识别研究院有限公司 | Intelligent door lock unlocking method based on human body feature recognition and door lock system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020146178A1 (en) * | 2000-09-01 | 2002-10-10 | International Business Machines Corporation | System and method for fingerprint image enchancement using partitioned least-squared filters |
| CN101271516A (en) * | 2008-04-02 | 2008-09-24 | 范九伦 | Direction filtering reinforcement method of fingerprint image |
| CN102254163A (en) * | 2011-08-03 | 2011-11-23 | 山东志华信息科技股份有限公司 | Template size self-adaptable Gabor fingerprint image enhancement method |
| CN104732217A (en) * | 2015-03-27 | 2015-06-24 | 电子科技大学 | Self-adaptive template size fingerprint direction field calculating method |
-
2017
- 2017-07-24 CN CN201710605485.0A patent/CN107451549B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020146178A1 (en) * | 2000-09-01 | 2002-10-10 | International Business Machines Corporation | System and method for fingerprint image enchancement using partitioned least-squared filters |
| CN101271516A (en) * | 2008-04-02 | 2008-09-24 | 范九伦 | Direction filtering reinforcement method of fingerprint image |
| CN102254163A (en) * | 2011-08-03 | 2011-11-23 | 山东志华信息科技股份有限公司 | Template size self-adaptable Gabor fingerprint image enhancement method |
| CN104732217A (en) * | 2015-03-27 | 2015-06-24 | 电子科技大学 | Self-adaptive template size fingerprint direction field calculating method |
Non-Patent Citations (2)
| Title |
|---|
| 唐永鹤等: "基于 Retinex 与 STFT 的非接触指纹图像增强", 《计算机工程》 * |
| 梅园等: "基于直线曲线混合Gabor滤波器的指纹增强算法", 《计算机科学》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784195A (en) * | 2018-12-20 | 2019-05-21 | 金菁 | A kind of fingerprint identification method checked card for enterprise's fingerprint and system |
| CN109858418A (en) * | 2019-01-23 | 2019-06-07 | 上海思立微电子科技有限公司 | The treating method and apparatus of fingerprint image |
| CN110728201A (en) * | 2019-09-20 | 2020-01-24 | 南京元初科技有限公司 | Image processing method and device for fingerprint identification |
| CN110728201B (en) * | 2019-09-20 | 2023-04-07 | 南京元初科技有限公司 | Image processing method and device for fingerprint identification |
| CN111741031A (en) * | 2020-08-26 | 2020-10-02 | 深圳信息职业技术学院 | Block chain based network communication encryption method |
| CN112232159A (en) * | 2020-09-30 | 2021-01-15 | 墨奇科技（北京）有限公司 | Fingerprint identification method, device, terminal and storage medium |
| CN113313627A (en) * | 2021-06-08 | 2021-08-27 | 中国科学院大学 | Fingerprint image reconstruction method and fingerprint image feature extraction method and device |
| CN113313627B (en) * | 2021-06-08 | 2023-10-20 | 中国科学院大学 | Fingerprint image reconstruction method, fingerprint image feature extraction method and device |
| CN115035640A (en) * | 2022-08-10 | 2022-09-09 | 湖南朗国视觉识别研究院有限公司 | Intelligent door lock unlocking method based on human body feature recognition and door lock system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107451549B (en) | 2020-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107451549A (en) | The sef-adapting filter of contactless Fingerprint Image Enhancement and Curvature-driven | |
| Ryu et al. | Enhancement of feature extraction for low-quality fingerprint images using stochastic resonance | |
| Sutthiwichaiporn et al. | Adaptive boosted spectral filtering for progressive fingerprint enhancement | |
| CN102629316B (en) | Image enhancement method in automatic fingerprint identification technology | |
| CN100578529C (en) | High precision palm print recognition method based on two-dimensional quadrature Log-Gabor filtering | |
| CN110188614A (en) | It is a kind of based on skin crack segmentation NLM filtering refer to vein denoising method | |
| Xie et al. | Guided Gabor filter for finger vein pattern extraction | |
| WO2011097936A1 (en) | Fingerprint image enhancement method | |
| CN107273812B (en) | A kind of living body iris method for anti-counterfeit for authentication | |
| CN101667137A (en) | Method for extracting finger vein grain by using directional filtering technique | |
| CN106778498A (en) | A kind of method for strengthening Fingerprint recognition | |
| CN102254163A (en) | Template size self-adaptable Gabor fingerprint image enhancement method | |
| Selvi et al. | FBFET: Fuzzy based fingerprint enhancement technique based on adaptive thresholding | |
| CN105930811A (en) | Palm texture feature detection method based on image processing | |
| Arora et al. | A quantitative survey of various fingerprint enhancement techniques | |
| CN107977935A (en) | A kind of vena metacarpea image texture filtering reinforcement method | |
| CN103886291B (en) | Palmprint image wrinkle detection method based on dynamic template | |
| CN102368333A (en) | Fingerprint enhancement method based on time domain and frequency domain filtering | |
| CN102073856A (en) | Frequency energy difference based fingerprint identification | |
| CN108009996A (en) | A kind of finger vein image enhancement method and its system, product based on ridgelet transform | |
| Kumar et al. | Finger vein based human identification and recognition using gabor filter | |
| CN107644198A (en) | It is a kind of based on Gabor filter and the palm vein recognition methods of LBP operators and system | |
| Yadav et al. | Statistical measures for Palmprint image enhancement | |
| CN107563254A (en) | A kind of method and system for the fingerprint image frequency domain filtering enhancing that weak parameter relies on | |
| Petrovici et al. | Identifying fingerprint alteration using the reliability map of the orientation field |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200512 Termination date: 20210724 |