CN1588424A - Finger print identifying method based on broken fingerprint detection - Google Patents

Abstract

The invention is a fingerprint discriminating method based on broken design detection which belongs to fingerprint identification field. Its character lies in: it carries on broken design detection to detail points extracted with traditional method with 12 groups of best filter, each filter has a discrete value of an angle between the broken design direction and the X axis; works out the filter value under the 12 groups of broken design directions and sets a uniform floor level, acquires 12 groups of binary image, then the stripe region is displayed with rectangular with primary cell analysis method of matrix, and the region is parameterized with length, width and direction of the rectangular; all the binary images are combined together and a real broken design image is acquired, the parameterized images are combined and a broken design model is acquired in order to eliminate the false detail points. To the old people, with the same error reception rate, the fault refusing rate can be decreased to less than 10%.

Description

Fingerprint identification method based on disconnected line detection

Technical field

The present invention relates to the fingerprint identification technology field, relate in particular to the technology that the fingerprint that disconnected line is arranged is handled and discerned.

Background technology:

In modern society, it is urgent day by day fast, effectively, automatically to carry out the requirement that the person distinguishes, the turnover of important department security personnel, the control of passing by, immigration inspection, secret or valuables place of retention, prevents that credit card deception, network security etc. from all needing to carry out reliably the person and differentiating.In the foundation of authentication, key, certificate may lose, stolen or duplicate, password is forgotten about, is obscured or stolen a glance at easily again, and biological characteristic (comprising fingerprint, people's face, hand shape, handwritten signature, iris etc.) is people's a inherent attribute, they above-mentioned situation can not occur, therefore become the optimal foundation of distinguishing.This wherein, fingerprint recognition is to use the most general, the highest, the easiest received personal identification identification of discrimination.First of material evidence, the existing history very very long and achievement is abundant of fingerprint recognition.The automatic fingerprint recognition of computer based starts from twentieth century sixties, and it at first is applied in the criminal detection.In recent years, fingerprint automation recognition is generalized to fields such as work attendance, gate inhibition, safe deposit box, social insurance gradually from criminal application, and China determines tentatively that also introducing finger print information in the new breed of identity cards carries out personal identification.After the U.S.'s 911 incidents, obtain unprecedented attention especially based on the person identification of fingerprint automation recognition.

Present fingerprint automation recognition method mainly all is based on minutia, promptly extracts minutiae point (destination node of crestal line or point of crossing in the fingerprint) and characterizes fingerprint image as feature, discerns by comparing these features.Its step generally comprises: fingerprint image acquisition, directional diagram extraction, figure image intensifying, fingerprint ridge line refinement, minutiae point extraction etc.Round how extracting minutiae point faster and better, recent two decades comes domestic and international research unit to make extensive work, and existing fingerprint product all is based on this method, SecuTouch as U.S. BAC company, the FIU-500 of Japan Sony company, the Veriprox of U.S. BII company, the Bogo2000 of Korea S Bogo company, the U.are.U 2000 of U.S. DP company, the Biologon of American I dentix company etc.Along with the popularization that fingerprint recognition is used, the deficiency of existing system and method also more and more displays.Although illustrate in the propaganda of a lot of products and the report that it can reach more than 99%, this result is based upon on some prerequisites (as than higher reject rate).For the bad crowd of fingerprint quality elderly population particularly, its effect then is on duty mutually, and general recognition system all is to adopt the strategy that this user is refused.The world population ratio is just presenting aging at present, and the elderly has accounted for 30% of total population ratio, if solve bad this problem, applying of fingerprint recognition will be had a strong impact on.In fact, also just because of these reasons, fingerprint recognition all has been subjected to serious restriction in application such as social insurance, bank savings.We can say that this problem has become the bottleneck problem of fingerprint recognition.

For the elderly, they with advancing age, fingerprint can a large amount of disconnected lines occur owing to the gauffer of skin, when using traditional algorithm, will produce false crestal line destination node or point of crossing, thereby cause a lot of false minutiae point, at this moment discerning probability of errors can be very high, has had a strong impact on the result of identification.

The present invention is directed to the elderly population fingerprint has this situation of disconnected line mostly, utilizes disconnected line to detect the effect of improving fingerprint recognition.At present, in all patents that can find or deliver in the document, still do not find similarly report and patent.

Summary of the invention

The fingerprint recognition at elderly population that the purpose of this invention is to provide a kind of practicality is improved one's methods, can handle fingerprint with disconnected line, can detect disconnected line automatically, utilize disconnected line to remove some false minutiae point, thereby reach the purpose that improves the traditional recognition method effect.

Core concept of the present invention is that the disconnected line that will classic method be impacted detects automatically by computing machine, and near the minutiae point that occurs the line that will break is again removed.What mainly utilize when particularly, disconnected line detects is that fingerprint texture has periodic characteristics to disconnected line with the direction of fingerprint texture is inconsistent on direction; The strategy that when utilizing disconnected line to improve fingerprint recognition, mainly adopts near the minutiae point the line that to break to remove.

The invention is characterized in that it includes following two stages successively:

One, learning phase, computing machine carry out extraction, the storage of minutiae point to the fingerprint of all registrations under off-line state, successively minutiae point is broken after line detects, removes fake minutiae again, set up database; It contains following steps successively:

(1) computing machine is carried out initialization

Set following each initial value:

In the detection step of fingerprint effective coverage, for being divided into the original fingerprint image of grid that size is 4 * 4 pixels, when (i j) is the gray average I of each grid in the upper left corner with point _Avg(i, j) and variance Var (i, when j) being in the following ranges, this grid be effective, is labeled as 1; Otherwise be invalid, be labeled as 0;

Th1＜I _Avg(i, j)＜th2 and Var (i, j)＞th3, th wherein is expressed as threshold value, th1=20; Th2=220; Th3=6;

When disconnected line detection-phase carries out multi-channel filter, set variances sigma=30 of Gaussian function, the reach η of wave filter=1/4;

(2) computing machine is gathered the original image and the storage of all registered fingerprints by getting the finger device;

(3) effective coverage of COMPUTER DETECTION fingerprint, it comprises following steps successively:

(3.1) original image is divided into the grid that size is 4 * 4 pixels;

(3.2) computing machine is calculated as follows that (i j) is the gray average I of each grid in the upper left corner with point _Avg(i, j) and variance Var (i, j):

$I_{\mathrm{avg}}(i,j)=\frac{1}{16}\underset{x=0}{\overset{3}{\mathrm{\Σ}}}\underset{y=0}{\overset{3}{\mathrm{\Σ}}}I(i+x,j+y),$

$\mathrm{Var}(i,j)=\frac{1}{16}\underset{x=0}{\overset{3}{\mathrm{\Σ}}}\underset{y=0}{\overset{3}{\mathrm{\Σ}}}{(I(i+x,j+y)-I_{\mathrm{avg}}(i,j))}^2,$

Wherein, (i+x j+y) is (i+x, gradation of image value j+y) to I;

(3.3) computing machine is pressed following formula and is judged whether above-mentioned each grid is effective:

If th1＜I _Avg(i, j)＜th2 and Var (i, j)＞th3, then this grid significant notation is 1;

(3.4) denoising is handled

(3.4.1) above-mentioned image being carried out 3 * 3 filtering, promptly check with the tested point to be 9 points in 3 * 3 neighborhoods at center, is effectively if having only this tested point, thinks that then this point is a noise, changes and is labeled as 0, and the grid that to show with this point be the upper left corner is invalid; If to have only this tested point is invalid, think that then this point is an available point, to change and be labeled as 1, the grid that to show with this point be the upper left corner is effective;

(3.4.2) remove effective coverage middle " hole ",, fill up all Null Spots between Far Left and the rightmost available point, it is labeled as effectively promptly line by line to above-mentioned image scanning; By column scan, fill up topmost and all Null Spots between the available point bottom, it is labeled as effectively, thereby obtains the effective coverage, long and wide 1/4 of the former figure that is respectively;

(4) use the pyramid algorithm travel direction field of adding up based on gradient to estimate that it comprises following steps successively:

(4.1) utilize the horizontal direction operator S of Soble operator _xWith vertical direction operator S _yAsk for point (x, shade of gray y):

Horizontal direction: $G_x(x,y)=\frac{1}{8}{\mathrm{\Σ}}_{j=y-1}^{y+1}{\mathrm{\Σ}}_{i=x-1}^{x+1}{S}_x(x-i,y-i)I(i,j),$

Vertical direction: $G_y(x,y)=\frac{1}{8}{\mathrm{\Σ}}_{j=y-1}^{y+1}{\mathrm{\Σ}}_{i=x-1}^{x+1}{S}_y(x-i,y-j)I(i,j),$

Wherein (i j) is (i, gray-scale value j), S to I _x(x-i, y-j), S _y(x-i y-j) represents the Soble operator of level and vertical direction respectively, in that (operator is that 3 * 3 mask is represented with a size respectively for x-i, value y-j);

(4.2) fingerprint image is divided into size and is the grid of W * W, W=7, carry out following steps more successively:

(4.2.1) ask for the local direction θ of each grid correspondence with following formula:

$\mathrm{\θ}(i,j)=\frac{1}{2}{\tan }^{-1}\left(\frac{{\mathrm{\Σ}}_{i=1}^{\stackrel{\‾}{W}}{\mathrm{\Σ}}_{j=1}^{\stackrel{\‾}{W}}2G_x(i,j)G_y(i,j)}{{\mathrm{\Σ}}_{i=1}^{\stackrel{\‾}{W}}{\mathrm{\Σ}}_{j=1}^{\stackrel{\‾}{W}}(G_x^2(i,j)-G_y^2(i,j))}\right);$

(4.2.2) calculated direction field consistency level:

${\mathrm{<figure-callout\; id="0"\; label="E"\; filenames="A200410062256.100291.png"\; state="\{\{state\}\}">E</figure-callout>}}_0=\frac{1}{N}\sqrt{\underset{(i^{\&prime;},j^{\&prime;})\&Element;\mathrm{\&Omega;}}{\mathrm{\&Sigma;}}{|\mathrm{\&theta;}(i^{\&prime;},j^{\&prime;})-\mathrm{\&theta;}(i,j)|}^2};$

Wherein, Ω is that (i, the j) neighborhood of grid are taken as 5 * 5, and N is the number of contained grid among the Ω, N=25; θ (i ', j ') and θ (i, j) be respectively (i ', j ') and (i, j) local direction of grid;

If E ₀＞T _c, then make W=1.5 W, reappraise the direction of each grid among the Ω, repeating step (4.2.1) and (4.2.2); Until E ₀≤ T _c, T here _c=1.5;

(5) adopt the Gabor filtering method to carry out the figure image intensifying, it comprises following steps successively:

(5.1) Gabor wave filter spatial domain expression-form is:

$G(x,y,\mathrm{\&theta;})=\exp \left\{\frac{-1}{2}\right[\frac{x^{\&prime;2}}{{\mathrm{\&delta;}}_{x^{\&prime;}}^2}+\frac{y^{\&prime;2}}{{\mathrm{\&delta;}}_{y^{\&prime;}}^2}\left]\right\}\cos \left({2\mathrm{\&pi;fx}}^{\&prime;}\right),$ Wherein

θ ∈ [0,180) be the field of direction vertical direction of current point, x, y be in the mask each point with respect to the coordinate of mask central point, δ _{X '}=δ _{Y '}=5.0, f=0.6, spatial domain mask size is 7 * 7 pixels;

(5.2) auto adapted filtering:

Suppose input fingerprint gray level image be I (x, y), θ be (i j) puts the vertical direction of field of direction direction, then uses above-mentioned filter filtering as follows:

$F(i,j)=\frac{{\mathrm{\&Sigma;}}_{x=-w}^w{\mathrm{\&Sigma;}}_{y=-w}^{w}G(x,y,\mathrm{\&theta;})I(i+x,j+y)}{{\mathrm{\&Sigma;}}_{x=-w}^w{\mathrm{\&Sigma;}}_{y=-w}^{w}G(x,y,\mathrm{\&theta;})};$ W=3 wherein;

Ask for a numerical value by following formula then:

$\mathrm{flag}(i,j)=\frac{{\mathrm{\&Sigma;}}_{x=-\frac{L}{2}}^{\frac{L}{2}-D}|F(i+x\cos \mathrm{\&theta;},j+x\sin \mathrm{\&theta;})-F(i+(x+D)\cos \mathrm{\&theta;},j+(x+D)\sin \mathrm{\&theta;})|}{{\mathrm{\&Sigma;}}_{x=-\frac{L}{2}}^{\frac{L}{2}-D}\left[\begin{array}{c}|F(i+x\cos \mathrm{\&theta;},j+x\sin \mathrm{\&theta;})-F(i+(x+D)\cos \mathrm{\&theta;},j+(x+D)\sin \mathrm{\&theta;})|\\ \&times;F[i+(x+\frac{D}{2})\cos \mathrm{\&theta;},j+(x+\frac{D}{2})\sin \mathrm{\&theta;}]\end{array}\right]},$

Wherein L=12 is the statistics zone length, and D=2 is the statistics step-length, carries out crestal line and extracts: if F (i, j)＞flag (i, j), then (i, j) being positioned at paddy is background, is prospect otherwise be positioned at ridge;

(6) crestal line refinement, it comprises following steps successively:

(6.1) promptly do not change topological structure and do not delete under the prerequisite of straight line end points at the skeleton that keeps former figure, decide tested point " going " or " staying " according to the different conditions that with the tested point is 8 neighborhoods at center, " go " usefulness " 0 " expression, " staying " usefulness " 1 " expression;

(6.2) set up 1 dimension concordance list table, marked index is 0～255, totally 256 elements, and each element is got 1 expression and is kept, and 0 expression is removed;

(6.3) have a few in the traversal effective coverage, investigate its 8 neighborhood, all permutation and combination are mapped between 0～255 by following formula:

index＝A32×2 ⁰+A31×2 ¹+A21×2 ²+A11×2 ³

+A12×2 ⁴+A13×2 ⁵+A23×2 ⁶+A33×2 ⁷；

Wherein, Aij represents the value of the point in 8 neighborhoods, is that the element of index is table[index by index value in the search index table then], determine this tested point whether to keep or remove;

(6.4) repeating (6.3) occurs up to the point that is not removed;

(6.5) refinement aftertreatment:

(6.5.1), according to refinement figure, tentatively determine the end points in the minutiae point, promptly this is as 1 and to have and only have a point in 8 points on every side be 1, and bifurcation point, and promptly this is as 1 and to have and only have three points in 8 points on every side be 1;

(6.5.2), along the minutiae point growth, minutiae point is carried out aftertreatment:

(a), for end points, if there is the direction of another end points approaching with it in its neighborhood of 12 * 12, promptly differential seat angle then all removes these two end points less than the Tha=30 degree;

(b), the adjacent sub crunode that forms annular is coupled together, for a bifurcation, if there is the direction of another bifurcation approaching with it in its neighborhood of 12 * 12, promptly differential seat angle then removes the both less than the Tha=30 degree;

(c), remove two end points of some little stub correspondences, for an end points, if along its place crestal line through just meeting another end points within 12 pixels, then two end points are all removed;

(6.5.3), screen out direction and this field of direction differential seat angle unique point greater than 30 degree;

(7) disconnected line detects, and it comprises following steps successively:

(7.1) to the point in the former fingerprint image (x, the gray-scale value I that y) goes out (x y) carries out multi-channel filter, and it comprises following steps successively:

(7.1.1) the angle γ of disconnected line direction and x axle is dispersed turn to 12 directions, the angle between every adjacent both direction is 15 °, thereby γ gets 12 direction: γ=0, π/12, and π/6 ..., 11 π/12;

(7.1.2) for each γ, respective filter mask size is 81 * 81, is γ through direction then _iThe filtered fingerprint image of optimal filter in point (x, the value F that y) locates _{γ i}(x, y) expression:

$F_{{\mathrm{\&gamma;}}_i}(x,y)=\underset{k=-40}{\overset{40}{\mathrm{\&Sigma;}}}\underset{l=-40}{\overset{40}{\mathrm{\&Sigma;}}}I(x+k,y+l)\&times;F({\mathrm{\&gamma;}}_i,k,l|{\mathrm{\&sigma;}}^2,\mathrm{\&eta;}),$

Wherein, (x+k is at point (x+k, gray-scale value y+l), F (γ, x, y| σ at image y+l) to I ², η) express formula for wave filter:

$F(\mathrm{\&gamma;},x,y|{\mathrm{\&sigma;}}^2,\mathrm{\&eta;})=G(\mathrm{\&gamma;},u(x,y),v(x,y)|{\mathrm{\&sigma;}}^2,\mathrm{\&eta;})$

$=\exp \{-\frac{{\mathrm{<figure-callout\; id="2"\; label="u"\; filenames="A200410062256.100281.png,A200410062256.100291.png"\; state="\{\{state\}\}">u</figure-callout>}}^2+{\mathrm{\&eta;<figure-callout\; id="2"\; label="v"\; filenames="A200410062256.100281.png,A200410062256.100291.png"\; state="\{\{state\}\}">v</figure-callout>}}^2}{{2\mathrm{\&sigma;}}^2}\}({\mathrm{\&sigma;}}^2-u^2),$

Wherein, u=xcos γ+ysin γ, v=-xsin γ+ycos γ;

(7.1.3) each figure that obtains by wave filter is carried out binaryzation with 200 as threshold value:

(7.1.4) disconnected line parametrization is for each the banded disconnected line zone on the different directions, with the pca method in the matrix analysis, it is the direction that PCA estimates this belt-like zone, length and width, and then be similar to this belt-like zone with a rectangle, it comprises following steps successively:

(7.1.4.1) in the image of binaryzation, the pixel in each belt-like zone can be used $S=\left[\begin{array}{cccc}{x}_1& x_2& & x_M\\ & & \&hellip;& \\ y_1& y_2& & y_M\end{array}\right]$ Represent that wherein first row is the each point horizontal ordinate, second row is the each point ordinate, and M is the number of pixel in the belt-like zone;

(7.1.4.2) obtain average m and the variance var of S:

$\stackrel{\&OverBar;}{m}=\left[\begin{array}{c}\stackrel{\&OverBar;}{x}\\ \stackrel{\&OverBar;}{y}\end{array}\right]=\frac{1}{M}\underset{l=1}{\overset{M}{\mathrm{\&Sigma;}}}\left[\begin{array}{c}{x}_l\\ y_l\end{array}\right],$

$\mathrm{var}=\frac{1}{M}\underset{\mathrm{<figure-callout\; id="1"\; label="l"\; filenames="A200410062256.100281.png,A200410062256.100291.png"\; state="\{\{state\}\}">l</figure-callout>}1=1}{\overset{M}{\mathrm{\&Sigma;}}}\underset{\mathrm{<figure-callout\; id="2"\; label="l"\; filenames="A200410062256.100281.png,A200410062256.100291.png"\; state="\{\{state\}\}">l</figure-callout>}2=1}{\overset{M}{\mathrm{\&Sigma;}}}\left(\right(\left[\begin{array}{c}{x}_{l1}\\ y_{l1}\end{array}\right]-\stackrel{\&OverBar;}{m})\&CenterDot;{(\left[\begin{array}{c}{x}_{l2}\\ y_{l2}\end{array}\right]-\stackrel{\&OverBar;}{m})}^T);$

(7.1.4.3) obtain all eigenwerts of variance matrix var, select two maximum eigenvalue ₁, λ ₂, require λ ₁〉=λ ₂And their characteristics of correspondence vector q ₁, q ₂

(7.1.4.4) can obtain by (7.1.4.3):

Center (the C of rectangle _x, C _y): i.e. mean value of areas m, i.e. C _x=x, C _y=y;

The direction θ of rectangle: corresponding major axis, it is the big pairing proper vector q of eigenwert ₁

The long l of rectangle and wide ω can obtain by calculating along the mean breadth of two feature axis respectively, specific implementation: in the image basis of binaryzation, in belt-like zone, travel through along the direction perpendicular to direction θ, the average length of this belt-like zone of statistics on direction θ is as the long l of rectangle; And then travel through along the direction of the direction θ of rectangle, statistics is perpendicular to the average length of this belt-like zone on the θ direction wide ω as rectangle;

(7.1.4.5) merge: the figure merging corresponding to all binaryzations of different directions obtains the disconnected line in the whole fingerprint image; All parameterized figure corresponding to different directions are merged, and the parametrization that obtains the disconnected line in the whole fingerprint image is represented;

(8) remove based on the false minutiae point of disconnected line: for the small neighbourhood of each minutiae point, generally be 7 * 7 wicket, investigate,, just judge that this minutiae point is false point, it is removed if certain in the neighborhood a bit drops in the detected disconnected line;

(9) full details of remainder point is sent into database, canned data comprises the total number of minutiae point, minutiae point coordinate and direction;

Two, cognitive phase

Computing machine to the fingerprint of each input according to above-mentioned (2)-(7) carry out minutiae point at line drawing, and and database in the fingerprint minutiae stored compare that to find out matching degree the highest, comparison and coupling contain following steps successively:

(1) use based on the method for Hough conversion and carry out the minutiae point registration:

Calculate compensation rotation and shifting deviation, calculate: two fingerprints minutiae point is separately constituted the point set that contains M and N minutiae point separately respectively, concentrate from two points and respectively select a minutiae point to be expressed as (x respectively according to following method ₁, y ₁, θ ₁) and (x ₂, y ₂, θ ₂), utilize coordinate, direction between them to obtain a translational movement: ${\mathrm{\&Delta;}}_t=\left[\begin{array}{c}{\mathrm{\&Delta;}}_x\\ {\mathrm{\&Delta;}}_y\end{array}\right]=\left[\begin{array}{c}{x}_2-x_1\\ y_2-{\mathrm{<figure-callout\; id="1"\; label="y"\; filenames="A200410062256.100281.png,A200410062256.100291.png"\; state="\{\{state\}\}">y</figure-callout>}}_1\end{array}\right],$ Rotation amount: Δ _θ=θ ₂-θ ₁, it is right to minutiae point to travel through all M * N, statistics (Δ _x, Δ _y, Δ _θ) number of times that occurs, the highest translation rotation amount of win the vote is exactly the translation rotation amount of final use, writes down number of votes obtained vote simultaneously;

The coordinate transform of using below can be realized by following formula:

x″＝x′×cos(Δ _θ)-y′×sin(Δ _θ)+Δ _x；

y″＝x′×sin(Δ _θ)-y′×cos(Δ _θ)+Δ _y；

Wherein (x ', y ') be the coordinate before the rotation translation, (x ", y ") is the coordinate after the rotation translation

(2) extract public effective coverage:

Remember two pieces of fingerprint r, the effective coverage behind the t registration is respectively R _r, R _t, according to the parameter of trying to achieve above, to R _tBe rotated translation, then public effective coverage is R=R _r∩ R _t

(3) comparison fingerprint r, all minutiae point among the t, the minutiae point logarithm that the record comparison is successful;

(4) calculated fingerprint r, the similarity M of t minutiae point set _Rt, 0＜M _Rt＜1:

$M_{\mathrm{rt}}=\frac{\mathrm{count}}{\max (\mathrm{cou}{\mathrm{nt}}_t,{\mathrm{count}}_r)}\&times;\min (\frac{\mathrm{vote}}{\mathrm{Th}},1);$

Wherein count represents to compare successful minutiae point logarithm, count _rThe minutiae point number of expression fingerprint r in the public effective coverage of two width of cloth fingerprints, count _tThe minutiae point number of expression fingerprint t in the public effective coverage of two width of cloth fingerprints; Th is an empirical value, is taken as 12;

(5) difference that error rate is required according to us, a given threshold value Th_M _n=0.4, if M _n＞Th_M _n, think that then two width of cloth fingerprints are from same finger; Otherwise, think that then two width of cloth fingerprints are not from same finger.

Our experimental result on 1760 width of cloth fingerprints shows that getting rid of false raising of putting discrimination is that significantly false rejection rate can reduce 1% to 3% under the same error acceptance rate, then can reduce more than 10% at the crowd that disconnected line is arranged.Have bigger variation if consider disconnected in actual applications line, this improvement meeting is more obvious.

The example of the disconnected line eliminating of utilization fake minutiae as shown in figure 13.

Description of drawings

Fig. 1. disconnected line testing process figure;

Fig. 2. the fingerprint image example:

2a original fingerprint image; 2b effective coverage figure (representing) with black;

Fig. 3. filtered image under the different passages:

3a, original fingerprint image (index goes out in the effective coverage);

3b1～3b12 is respectively in 12 directions, i.e. γ=0, and π/12, π/6 ..., 11 π/12 time, the filtering result who obtains;

Fig. 4. the fingerprint line figure that breaks:

4a removes the binary image under all passages behind the overlay region;

4b, the long axis direction that each belt-like zone is tried to achieve by PCA;

4c, the image after the disconnected line parametrization;

Fig. 5. disconnected line extracts the intermediate result of each step;

5 (1), the former figure of fingerprint;

5 (2), the effective coverage;

5 (3), original disconnected line extracts the result;

5 (4), the result after the disconnected line parametrization;

Fig. 6. utilize disconnected line to detect the process flow diagram of removing false minutiae point;

Fig. 7. the minutiae point synoptic diagram;

Fig. 8 .Sobel operator

8a, horizontal operator;

8b, vertical operator;

Fig. 9. the neighborhood calculation specifications;

Figure 10. the refinement table;

Figure 11. eight examples of refinement;

Figure 12. minutiae point is extracted the intermediate result of each step:

12 (1), the former figure of fingerprint;

12 (2), the effective coverage;

12 (3), the field of direction;

12 (4), strengthen figure;

12 (5), the background refinement;

12 (6), the prospect refinement;

12 (7), minutiae point is extracted the result;

Figure 13. utilize disconnected line to remove false minutiae point synoptic diagram.

Embodiment:

Our invention can realize on common PC computing machine, operating system not required.

(1) disconnected line detects

Along with the increase at age, people's fingerprint can cause very big influence to fingerprint recognition because disconnected line appears in the crowfoot cracks of skin.Fingerprint identification method does not in the past have disposal route targetedly.We then adopt brand-new thinking, propose by false minutiae point is removed in the detection of disconnected line.Present technique is very beneficial for the fingerprint recognition of elderly population and uses.

We mainly consider disconnected significantly line, and they satisfy: 1) enough big length breadth ratio is arranged, make people's naked eyes promptly can observe disconnected line and be belt-like zone, rather than some spherical noises; 2) there is certain angle between disconnected line and the normal grain direction of fingerprint.

Fig. 5 provides a concrete example, describes and resolves the intermediate result that line extracts each step, and concrete testing process is seen Fig. 1, the steps include:

The detection of fingerprint effective coverage:

Refer to that by getting fingerprint partly is not to be full of full figure among the original fingerprint figure that device collects, the parts of images that contains fingerprint is just meaningful in fingerprint recognition, is called the effective coverage.Original image is divided into the grid that size is 4 * 4 pixels,, calculates the average and the variance of gray-scale value of all pixels in this zone, think that just this point is in the effective coverage when having only both all to satisfy separately condition each such grid.Formula below wherein the calculating of average and variance relies on:

$I_{\mathrm{avg}}(i,j)=\frac{1}{16}\underset{x=0}{\overset{3}{\mathrm{\&Sigma;}}}\underset{y=0}{\overset{3}{\mathrm{\&Sigma;}}}I(i+x,j+y)$

$\mathrm{Var}(i,j)=\frac{1}{16}\underset{x=0}{\overset{3}{\mathrm{\&Sigma;}}}\underset{y=0}{\overset{3}{\mathrm{\&Sigma;}}}{(I(i+x,j+y)-I_{\mathrm{avg}}(i,j))}^2;$

Here, I _Avg(i, j), (i j) is illustrated respectively in that (i j) is the gray average and the variance of the grid in the upper left corner, and (i+x j+y) is (i+x, gradation of image value j+y) to I with point to Var.Require as th1＜I _Avg(i, j)＜th2 and Var (i, j)＞during th3, this grid of mark is effectively, is labeled as 1.Wherein, threshold value is chosen as: th1=20; Th2=220; Th3=6.

Grids all on the image is carried out aforesaid operations,, need carry out aftertreatment in order to remove noise effect:

1,3 * 3 filtering, specific practice are exactly to check to comprise 9 points of tested measuring point in its interior 3 * 3 neighborhood, are that effectively other all are invalid, think that so this point is a noise if having only this point, and change is labeled as 0 (it is invalid to show); If it is invalid having only this point, other all are effectively, think that so this point is an available point, and change was labeled as for 1 (showing effectively).

2, remove effective coverage middle " hole ", method is to line by line scan, and fills up all Null Spots between Far Left and the rightmost available point, and it is labeled as effective 1; By column scan, fill up topmost and all Null Spots between the available point bottom, it is labeled as effective 1.

So just obtained effective coverage (length and width be respectively former figure 1/4).As shown in Figure 2, the intermediate result in whole flow process is seen Fig. 5 (2).

Multi-channel filter:

It is the mode that adopts filtering that disconnected line detects.Designing filter is as follows: when needing the detection side when the angle with the x axle is the disconnected line of γ, make u=xcos γ+ysin γ, v=-xsin γ+ycos γ, wave filter F (γ, x, y| σ ², η) be

$F(\mathrm{\&gamma;},x,y|{\mathrm{\&sigma;}}^2,\mathrm{\&eta;})=G(\mathrm{\&gamma;},u(x,y),v(x,y)|{\mathrm{\&sigma;}}^2,\mathrm{\&eta;})$

$=\exp \{-\frac{{\mathrm{<figure-callout\; id="2"\; label="u"\; filenames="A200410062256.100281.png,A200410062256.100291.png"\; state="\{\{state\}\}">u</figure-callout>}}^2+{\mathrm{\&eta;<figure-callout\; id="2"\; label="v"\; filenames="A200410062256.100281.png,A200410062256.100291.png"\; state="\{\{state\}\}">v</figure-callout>}}^2}{{2\mathrm{\&sigma;}}^2}\}({\mathrm{\&sigma;}}^2-u^2);$

σ wherein, η, γ represent the variance of Gaussian function, the reach of wave filter and the direction of wave filter respectively.Recommend to adopt η=1/4, σ=30.X, y represent that each point is with respect to the coordinate at mask center in the wave filter mask.

Because disconnected line occurs in fingerprint image randomly, disconnected line has a lot of different directions, and promptly angle γ may get a lot of different values.Therefore, in order to detect the disconnected line of all directions, we need construct a wave filter respectively to different angle direction γ.In fact, can not all design a wave filter to all directions, calculated amount can be very big like this, so we turn to 12 directions with direction is discrete.All wave filters can represent that wherein γ gets 12 directions with following formula.

F(γ，x，y|σ ²，η)γ＝0，π/12，π/6，…，11π/12；

For each γ, respective filter mask size is 81 * 81.Because for identical γ, mask is identical.Can be before filtering the spatial domain mask be once asked for and finish and store, to reduce unnecessary double counting.

Make I (x, y) point (x, the gray-scale value of y) locating, the F in the former fingerprint image of the expression effective coverage _{γ i}(x, y) expression is γ through direction _iThe filtered fingerprint image of optimal filter in point (then the formula of filtering is as follows for x, the value of y) locating:

$I_i^{\&prime;}(x,y)=F_{{\mathrm{\&gamma;}}_i}(x,y)=\underset{k=-40}{\overset{40}{\mathrm{\&Sigma;}}}\underset{l=-40}{\overset{40}{\mathrm{\&Sigma;}}}I(x+k,y+l)\&times;F({\mathrm{\&gamma;}}_i,k,l|{\mathrm{\&sigma;}}^2,\mathrm{\&eta;});$

In Fig. 1, the wave filter of 12 different directions carries out filtering to fingerprint image, and filtered image is used I respectively ₁', I ₂' ..., I ₁₂' represent.Filtered these images have been listed among Fig. 3.

Binaryzation

Each image that filtering is obtained carries out binaryzation with 200 as threshold value, is about to part bright among Fig. 3 (be gray-scale value greater than 200 part) and remains.

Wherein, k=1,2 ..., 12, the sequence number of the wave filter of respectively corresponding 12 different directions, I _k' (i, j) expression is passed through the result images of i anisotropic filter at coordinate (i, the gray-scale value of j) locating, I _k" (i, j) gray-scale value of expression corresponding point after binaryzation.

The result of this flow process is corresponding to Fig. 5 (3) in the example.

Disconnected line parametrization

It all is banded (see figure 4) that the binary image that obtains previously interrupts the line zone.For each the banded disconnected line zone on the different directions, estimate the direction of this belt-like zone with the pca method in the matrix analysis (PCA), length and width, and then be similar to this belt-like zone with a rectangle.Be implemented as follows:

In the image of binaryzation, the pixel in each belt-like zone can be used $S=\left[\begin{array}{cccc}{x}_1& x_2& & x_M\\ & & \&hellip;& \\ y_1& y_2& & y_M\end{array}\right]$ Represent that wherein first row is the each point horizontal ordinate, second row is the each point ordinate, and M is the number of pixel in the belt-like zone.

The average of all point coordinate is $\stackrel{\&OverBar;}{m}=\left[\begin{array}{c}\stackrel{\&OverBar;}{x}\\ \stackrel{\&OverBar;}{y}\end{array}\right]=\frac{1}{M}\underset{l=1}{\overset{M}{\mathrm{\&Sigma;}}}\left[\begin{array}{c}{x}_l\\ y_l\end{array}\right],$

Variance matrix is $\mathrm{var}=\frac{1}{M}\underset{\mathrm{<figure-callout\; id="1"\; label="l"\; filenames="A200410062256.100281.png,A200410062256.100291.png"\; state="\{\{state\}\}">l</figure-callout>}1=1}{\overset{M}{\mathrm{\&Sigma;}}}\underset{\mathrm{<figure-callout\; id="2"\; label="l"\; filenames="A200410062256.100281.png,A200410062256.100291.png"\; state="\{\{state\}\}">l</figure-callout>}2=1}{\overset{M}{\mathrm{\&Sigma;}}}\left(\right(\left[\begin{array}{c}{x}_{l1}\\ y_{l1}\end{array}\right]-\stackrel{\&OverBar;}{m})\&CenterDot;{(\left[\begin{array}{c}{x}_{l2}\\ y_{l2}\end{array}\right]-\stackrel{\&OverBar;}{m})}^T).$

Obtain all eigenwerts of variance matrix var, select two maximum eigenvalue ₁, λ ₂(require λ ₁〉=λ ₂) and their characteristics of correspondence vector q ₁, q ₂So we can obtain the following Several Parameters of rectangle:

Center (the C of rectangle _x, C _y): i.e. mean value of areas m (C _x=x, C _y=y);

The direction θ of rectangle: corresponding major axis (the pairing proper vector q of big eigenwert ₁);

The long l of rectangle and wide ω can obtain specific implementation by calculating along the mean breadth of two feature axis respectively: the image basis in binaryzation (is I _kOn "), in belt-like zone, travel through along the direction perpendicular to direction θ, the average length of this belt-like zone of statistics on direction θ is as the long l of rectangle; And then travel through along the direction of the direction θ of rectangle, statistics is perpendicular to the average length of this belt-like zone on the θ direction wide ω as rectangle.

By top parameter (C _x, C _y), θ, l and ω, we can represent all disconnected lines with the different a lot of rectangles of parameter.

Fig. 4 has listed long axis direction that binary image under all passages, each belt-like zone try to achieve by PCA and last rectangle is represented.

The result of this flow process is corresponding to Fig. 5 (4) in the example.

Merge

Each figure (corresponding different directions) of all binaryzations is merged the disconnected line that just can obtain in the whole fingerprint image, each figure (corresponding different directions) of parametrization (promptly describing with rectangle) is merged the parametrization just can obtain the disconnected line of whole fingerprint represent, see result last among Fig. 4.

Fig. 5 provides the intermediate result figure of the flow process of introducing previously.

(2) utilize disconnected line to detect and remove false minutiae point

When having a large amount of disconnected lines in the fingerprint image, use traditional fingerprint disposal route and produce false minutiae point (being called for short false point) easily at disconnected line place.We can add the step that disconnected line detects in traditional algorithm, get rid of the false minutiae point that disconnected line place occurs.

Algorithm flow such as Fig. 6.The whole algorithm flow process mainly comprises processed offline and ONLINE RECOGNITION two parts.Processed offline can be carried out the extraction and the storage of minutiae point to the fingerprint of all registrations; ONLINE RECOGNITION be the fingerprint to new input carry out minutiae point extraction and and database in the fingerprint minutiae stored compare, matching degree is the highest thinks and imports fingerprint and derive from same finger.Feature extraction comprises two steps: traditional before this minutiae point is extracted, and then detects by disconnected line and removes false minutiae point.

Extracting flow process with a traditional minutiae point below is how the example explanation utilizes disconnected line to detect the false minutiae point of removal.

Minutiae point can be divided into two kinds, and a kind of is the end points of crestal line, and another kind is the bifurcation point of crestal line.As shown in Figure 7.The method that is based on refinement figure of our employing of the extracting method of minutiae point.Respectively prospect and background are carried out refinement, obtain two refinement figure.Net result is shown in Figure 12 (5), 12 (6).

Concrete details point extraction step is as follows:

1, extract the effective coverage.This step is the same with above-mentioned flow process.Result's signal is as Figure 12 (2);

2, the field of direction is estimated.The field of direction is the piece image of expression fingerprint ridge line trend, and wherein every numerical value has been represented the local crestal line direction of corresponding point in the fingerprint image.Directional diagram has been portrayed the global information of fingerprint, plays an important role in fingerprint recognition.The pyramid algorithm that is based on the gradient statistics that adopts in this method, effect is shown in Figure 12 (3).Algorithm is as follows:

I, utilize the horizontal direction operator S of Soble operator _xWith vertical direction operator S _y(see figure 8) ask for point (x, shade of gray y):

Horizontal direction: $G_x(x,y)=\frac{1}{8}{\mathrm{\&Sigma;}}_{j=y-1}^{y+1}{\mathrm{\&Sigma;}}_{i=x-1}^{x+1}{S}_x(x-i,y-j)I(i,j),$

Vertical direction: $G_y(x,y)=\frac{1}{8}{\mathrm{\&Sigma;}}_{j=y-1}^{y+1}{\mathrm{\&Sigma;}}_{i=x-1}^{x+1}{S}_y(x-i,y-j)I(i,j),$

Wherein (i j) is (i, gray-scale value j) to I.

II, fingerprint image be divided into the size be the grid of W * W, W=7, carry out following steps more successively:

(a) ask for the local direction θ of each grid correspondence with following formula

$\mathrm{\&theta;}(i,j)=\frac{1}{2}{\tan }^{-1}\left(\frac{{\mathrm{\&Sigma;}}_{i=1}^{\stackrel{\&OverBar;}{W}}{\mathrm{\&Sigma;}}_{j=1}^{\stackrel{\&OverBar;}{W}}2G_x(i,j)G_y(i,j)}{{\mathrm{\&Sigma;}}_{i=1}^{\stackrel{\&OverBar;}{W}}{\mathrm{\&Sigma;}}_{j=1}^{\stackrel{\&OverBar;}{W}}(G_x^2(i,j)-G_y^2(i,j))}\right);$

(b) calculated direction field consistency level:

${\mathrm{<figure-callout\; id="0"\; label="E"\; filenames="A200410062256.100291.png"\; state="\{\{state\}\}">E</figure-callout>}}_0=\frac{1}{N}\sqrt{\underset{(i^{\&prime;},j^{\&prime;})\&Element;\mathrm{\&Omega;}}{\mathrm{\&Sigma;}}{|\mathrm{\&theta;}(i^{\&prime;},j^{\&prime;})-\mathrm{\&theta;}(i,j)|}^2},$

Wherein, Ω is that (i, the j) neighborhood of grid are taken as 5 * 5, and N is the number of contained grid among the Ω, N=25.θ (i ' j ') and θ (i, j) be respectively (i ', j ') and (i, j) local direction of grid;

If E ₀＞T _c, then make W=1.5 W, reappraise the direction of each grid among the Ω, repeating step I and II.Until E ₀≤ T _cHere T _c=1.5.

3, figure image intensifying

Algorithm for image enhancement adopts the Gabor filtering method, promptly according to each point field of direction value, carries out filtering with the Gabor wave filter.Effect is as Figure 12-4 after the filtering) shown in.Filtering algorithm is as follows:

I, ask for the spatial domain mask of specifying size:

Gabor wave filter spatial domain expression-form is

$G(x,y,\mathrm{\&theta;})=\exp \left\{\frac{-1}{2}\right[\frac{x^{\&prime;2}}{{\mathrm{\&delta;}}_{x^{\&prime;}}^2}+\frac{y^{\&prime;2}}{{\mathrm{\&delta;}}_{y^{\&prime;}}^2}\left]\right\}\cos \left(2\mathrm{\&pi;f}{x}^{\&prime;}\right),$ Wherein

Here θ ∈ [0,180) be the field of direction vertical direction of current point, x, y be in the mask each point with respect to the coordinate of mask central point.Each parameter is got δ _{X '}=δ _{Y '}=5.0, f=0.6, spatial domain mask size is 7 * 7 pixels.Because for identical θ, the spatial domain mask is identical.Finish and store so can be before filtering the spatial domain mask be once asked for, to reduce unnecessary double counting.

II, auto adapted filtering:

For the point in the fingerprint image (i, j), suppose input fingerprint gray level image be I (x, j), θ be (i j) puts the vertical direction of field of direction direction, then uses above-mentioned filter filtering as follows:

$F(i,j)=\frac{{\mathrm{\&Sigma;}}_{x=-w}^w{\mathrm{\&Sigma;}}_{y=-w}^{w}G(x,y,\mathrm{\&theta;})I(i+x,j+y)}{{\mathrm{\&Sigma;}}_{x=-w}^w{\mathrm{\&Sigma;}}_{y=-w}^{w}G(x,y,\mathrm{\&theta;})},$ W=3 wherein;

Ask for a numerical value by following formula then:

$\mathrm{flag}(i,j)=\frac{{\mathrm{\&Sigma;}}_{x=-\frac{L}{2}}^{\frac{L}{2}-D}|F(i+x\cos \mathrm{\&theta;},j+x\sin \mathrm{\&theta;})-F(i+(x+D)\cos \mathrm{\&theta;},j+(x+D)\sin \mathrm{\&theta;})|}{{\mathrm{\&Sigma;}}_{x=-\frac{L}{2}}^{\frac{L}{2}-D}\left[\begin{array}{c}|F(i+x\cos \mathrm{\&theta;},j+x\sin \mathrm{\&theta;})-F(i+(x+D)\cos \mathrm{\&theta;},j+(x+D)\sin \mathrm{\&theta;})|\\ \&times;F[i+(x+\frac{D}{2})\cos \mathrm{\&theta;},j+(x+\frac{D}{2})\sin \mathrm{\&theta;}]\end{array}\right]},$

Wherein L=12 is the statistics zone length, and D=2 is the statistics step-length, carries out crestal line and extracts: if F (i, j)＞(i, j), then (i j) is positioned at paddy (background) to flag, otherwise is positioned at ridge (prospect).

4, crestal line refinement

To the fingerprint image after strengthening, we are with its binaryzation (directly select threshold value be 128 get final product).Each some value is 1 or 0,1 expression prospect; 0 expression background.The target of refinement is exactly that to investigate each value be 1 point, the point that this is to be investigated is changed to 0 (be about to this point and become background) when deciding according to the value of its 8 neighborhood, by traversal several times to full figure, constantly the point with some prospects (value is 1) becomes background dot, thereby reaches the purpose of refinement.

We decide tested point " going " or " staying " according to the different conditions of tested point 8 neighborhoods.The institute of these 8 neighborhood points might the value combination have 2 ⁸=256 kinds (each point can only get 1 or 0).We may be set at a corresponding result of rule with every kind and be " 1 " (reservation) or " 0 " (removal), and the principle that rule is set is the skeleton that keeps former figure.For the fingerprint ridge line refinement, the skeleton of our definition, can be understood as the axis of image, for example rectangular skeleton is the axis on its length direction, the skeleton of circle is its center of circle, the skeleton of ring is the closed curve of similar circle, and the skeleton of straight line is it self, and the skeleton of isolated point also is self.The different application occasion has difference to the definition of skeleton, and we have provided several examples by several examples explanations among Figure 11, and wherein: (1) can not delete, because it is an internal point, if leave out, has not just had skeleton; (2) can not delete, this is a specific (special) requirements, keeps straight line as far as possible; (3) can not delete, this point is a skeleton, after deleting, changes topological structure; (4) can not delete, because after deleting, originally the part that links to each other disconnects, and changes topological structure; (5) can not delete, because it is the end points of straight line; (6) can delete, this point is not a skeleton; (7) can not delete, this point is a skeleton; (8) can delete, this point is not a skeleton.Our simplified summary once, following criterion is arranged: (1) straight line end points can not be deleted; (2) point that changes topological structure can not be deleted, and for example internal point can not be deleted, isolated point can not be deleted etc.

All situations is summed up according to top example, can obtain 256 rules, it (is exactly one 1 dimension group in fact that its result is encoded to a table, mark 0～255, totally 256 elements), the number that the value of 8 neighborhoods of each tested point is corresponding 0 to 255, with this number as index, the value of correspondence in tabling look-up is if 1 expression keeps; 0 this point of expression is removed (value that is about to this tested point is changed to 0).

Indexing means such as Fig. 9, Aij represent the point in 8 neighborhoods, and index is defined as:

index＝A32×2 ⁰+A31×2 ¹+A21×2 ²+A11×2 ³

+A12×2 ⁴+A13×2 ⁵+A23×2 ⁶+A33×2 ⁷；

Find corresponding element table[index among the table table according to index value], wherein the span of index value index is at [0,255] interior integer, if table[index] be 1, then keep this point (value is constant); If be 0, then this point is put 0.The table that we adopt as shown in figure 10.We select two figure as example from Figure 11:

Figure 11 (2): center (to be measured) point can not be deleted, because:

index＝1×2 ⁰+0×2 ¹+0×2 ²+0×2 ³+1×2 ⁴+0×2 ⁵+1×2 ⁶+0×2 ⁷＝81，

Table[81]=1, can not remove so represent this point.

Figure 11 (8): center (to be measured) point can be deleted, because:

index＝1×2 ⁰+1×2 ¹+0×2 ²+0×2 ³+0×2 ⁴+0×2 ⁵+0×2 ⁶+0×2 ⁷＝3，

Table[3]=0, can remove so represent this point.

We sum up the step of refinement:

The first step provides indexing means, for example according to the method for setting among Fig. 9;

In second step, provide concordance list according to rule, for example according to the table of setting among Figure 10;

In the 3rd step, traversal full figure all values is 1 point, and computation index judges whether to keep;

In the 4th step, if the 3rd step was not removed any point, then next step otherwise repeated for the 3rd step.

The 5th step, aftertreatment, we will be described in detail below:

The operation of obtaining behind the refinement figure is as follows:

I according to refinement figure, tentatively determines end points (this is as 1 and to have and only have a point in 8 points on every side be 1) in the minutiae point and bifurcation point (basis is as 1 and to have and only have three points in 8 points on every side be 1).

II, along the minutiae point growth, carry out aftertreatment to minutiae point:

(a), for end points, if the direction that another end points is arranged in its neighborhood of 12 * 12 is then all removed these two end points with it near (differential seat angle is less than the Tha=30 degree);

(b), the adjacent sub crunode that forms annular is coupled together, for a bifurcation, if the direction that another bifurcation is arranged in its neighborhood of 12 * 12 is then all removed these two end points with it near (differential seat angle is less than the Tha=30 degree);

(c), remove two end points of some little stub correspondences, for an end points, if along its place crestal line through just meeting another end points within 12 pixels, then two end points are all removed;

III screens out direction and this field of direction differential seat angle unique point greater than 30 degree.

All registered fingerprints are carried out above-mentioned feature extraction operation and deposit the gained feature in database.

Each flow process intermediate result is seen Figure 12.

5. remove based on the false minutiae point of disconnected line

Can finish minutiae point by the step of front extracts, though in extraction, also removed the false point of part, but false greatly point still can not be removed, we propose passes through the step that disconnected line removes false point and is: investigate for the small neighbourhood of each minutiae point (generally be 7 * 7 wicket), if certain in the neighborhood a bit drops in the detected disconnected line, just judge that this minutiae point is false point, it is removed.As shown in figure 13.

(3) minutiae point comparison

We carry out above operation (can off-line) to all registered fingerprints, and the full details point that will be left at last all is kept in the database.After fingerprint to be measured gathered, carry out aforesaid operations (online, off-line all can) equally, then the data in its result (minutiae point) and the database are carried out the minutiae point comparison, it is the highest to find out matching degree, as the output result.The minutiae point comparison process is divided into minutiae point registration and two steps of minutiae point coupling.

Owing to have rotation and translation between two pieces of fingerprints that are used to compare, must utilize the method compensation rotation and the shifting deviation of minutiae point registration.The method for registering that is based on the Hough conversion that we adopt.Simplicity of explanation is: the minutiae point separately of two fingerprints is constituted two point sets (a M and N minutiae point is respectively arranged) respectively, concentrate from two points and respectively select a minutiae point to be expressed as (x respectively ₁, y ₁, θ ₁) and (x ₂, y ₂, θ ₂), utilize coordinate, direction between them can obtain a translational movement and rotation amount: ${\mathrm{\&Delta;}}_t=\left[\begin{array}{c}{\mathrm{\&Delta;}}_x\\ {\mathrm{\&Delta;}}_y\end{array}\right]=\left[\begin{array}{c}{x}_2-x_1\\ y_2-{\mathrm{<figure-callout\; id="1"\; label="y"\; filenames="A200410062256.100281.png,A200410062256.100291.png"\; state="\{\{state\}\}">y</figure-callout>}}_1\end{array}\right];$ Δ _θ＝θ ₂-θ ₁。Travel through all minutiae point to (altogether M * N to), all translations and rotation amount are voted, be i.e. statistics (Δ _x, Δ _y, Δ _θ) number of times that occurs, the highest translation rotation amount of win the vote is exactly the translation rotation amount of final use, writes down number of votes obtained vote simultaneously.

Carry out a little rotation translation transformation according to following formula:

x″＝x′×cos(Δ _θ)-y′×sin(Δ _θ)+Δ _x；

y″＝x′×sin(Δ _θ)-y′×cos(Δ _θ)+Δ _y；

Wherein (x ', y ') be the coordinate before the rotation translation, (x ", y ") is the coordinate after the rotation translation.

Draw rotation and just can calculate public effective coverage between two pieces of fingerprints (be designated as r, t, and suppose that r is a benchmark, t rotates translation to r) after the translational movement.Acquiring method is as follows: good fingerprint effective coverage is respectively R to establish two width of cloth registrations _r, R _t, according to the parameter of trying to achieve above, to R _tBe rotated translation, then public effective coverage is R=R _r∩ R _t

For these two pieces good fingerprints of registration, carry out the minutiae point comparison.What finally draw is a number between 0～1, represents the similarity of two pieces of fingerprint minutiaes set.When the distance of two minutiae point in the good fingerprint image of two width of cloth registrations during less than a certain threshold value (being taken as 8 pixels), think that these two somes compares successfully, the match is successful puts counting is added 1.Finally can obtain:

$M_{\mathrm{rt}}=\frac{\mathrm{count}}{\max ({\mathrm{count}}_t,\mathrm{coun}{t}_r)}\&times;\min (\frac{\mathrm{vote}}{\mathrm{Th}},1),$

Wherein count represents to compare successful minutiae point logarithm, count _rThe minutiae point number of expression fingerprint r in the public effective coverage of two width of cloth fingerprints, count _tThe minutiae point number of expression fingerprint t in the public effective coverage of two width of cloth fingerprints.Th is an empirical value, is taken as 12.

According to the difference that we require error rate, a given threshold value Th_M _n=0.4, if M _n＞Th_M _n, think that then two width of cloth fingerprints are from same finger; Otherwise, think that then two width of cloth fingerprints are not from same finger.

Claims (1)

1, the fingerprint identification method that detects based on disconnected line is characterized in that it contains following two stages successively:

One, learning phase, computing machine carry out extraction, the storage of minutiae point to the fingerprint of all registrations under off-line state, successively minutiae point is broken after line detects, removes fake minutiae again, set up database; It contains following steps successively:

(1) computing machine is carried out initialization

Set following each initial value:

In the detection step of fingerprint effective coverage, for being divided into the original fingerprint image of grid that size is 4 * 4 pixels, when (i j) is the gray average I of each grid in the upper left corner with point _Avg(i, j) and variance Var (i, when j) being in the following ranges, this grid be effective, is labeled as 1; Otherwise be invalid, be labeled as 0;

Th1＜I _Avg(i, j)＜th2 and Var (i, j)＞th3, wherein th is expressed as threshold value: th1=20; Th2=220; Th3=6;

When disconnected line detection-phase carries out multi-channel filter, set variances sigma=30 of Gaussian function, the reach η of wave filter=1/4;

(2) computing machine is gathered the original image and the storage of all registered fingerprints by getting the finger device;

(3) effective coverage of COMPUTER DETECTION fingerprint, it comprises following steps successively:

(3.1) original image is divided into the grid that size is 4 * 4 pixels;

(3.2) computing machine is calculated as follows that (i j) is the gray average I of each grid in the upper left corner with point _Avg(i, j) and variance Var (i, j):

$I_{\mathrm{avg}}(i,j)=\frac{1}{16}\underset{x=0}{\overset{3}{\mathrm{\&Sigma;}}}\underset{y=0}{\overset{3}{\mathrm{\&Sigma;}}}I(i+x,j+y),$

$\mathrm{Var}(i,j)=\frac{1}{16}\underset{x=0}{\overset{3}{\mathrm{\&Sigma;}}}\underset{y=0}{\overset{3}{\mathrm{\&Sigma;}}}I(i+x,j+y)-I_{\mathrm{avg}}{(i,j))}^2,$

Wherein, (i+x j+y) is (i+x, gradation of image value j+y) to I;

(3.3) computing machine is pressed following formula and is judged whether above-mentioned each grid is effective:

If th1＜I _Avg(i, j)＜th2 and Var (i, j)＞th3, then this grid significant notation is 1;

(3.4) denoising is handled

(3.4.1) above-mentioned image being carried out 3 * 3 filtering, promptly check with the tested point to be 9 points in 3 * 3 neighborhoods at center, is effectively if having only this tested point, thinks that then this point is a noise, changes and is labeled as 0, and the grid that to show with this point be the upper left corner is invalid; If to have only this tested point is invalid, think that then this point is an available point, to change and be labeled as 1, the grid that to show with this point be the upper left corner is effective;

(3.4.2) remove effective coverage middle " hole ",, fill up all Null Spots between Far Left and the rightmost available point, it is labeled as effectively promptly line by line to above-mentioned image scanning; By column scan, fill up topmost and all Null Spots between the available point bottom, it is labeled as effectively, thereby obtains the effective coverage, long and wide 1/4 of the former figure that is respectively;

(4) use the pyramid algorithm travel direction field of adding up based on gradient to estimate that it comprises following steps successively:

(4.1) utilize the horizontal direction operator S of Soble operator _xWith vertical direction operator S _yAsk for point (x, shade of gray y):

Horizontal direction: $G_x(x,y)=\frac{1}{8}{\mathrm{\&Sigma;}}_{j=y-1}^{y+1}{\mathrm{\&Sigma;}}_{i=x-1}^{x+1}{S}_x(x-i,y-j)I(i,j),$

Vertical direction: $G_y(x,y)=\frac{1}{8}{\mathrm{\&Sigma;}}_{j=y-1}^{y+1}{\mathrm{\&Sigma;}}_{i=x-1}^{x+1}{S}_y(x-i,y-j)I(i,j),$

Wherein (i j) is (i, gray-scale value j), S to I _x(x-i, y-j), S _y(x-i y-j) represents the Soble operator of level and vertical direction respectively, in that (operator is that 3 * 3 mask is represented with a size respectively for x-i, value y-j);

(4.2) fingerprint image is divided into size and is the grid of W * W, W=7, carry out following steps more successively:

(4.2.1) ask for the local direction θ of each grid correspondence with following formula:

$\mathrm{\&theta;}(i,j)=\frac{1}{2}{\tan }^{-1}\left(\frac{{\mathrm{\&Sigma;}}_{i=1}^{\stackrel{\&OverBar;}{W}}{\mathrm{\&Sigma;}}_{j=1}^{\stackrel{\&OverBar;}{W}}{2G}_x(i,j)G_y(i,j)}{{\mathrm{\&Sigma;}}_{i=1}^{\stackrel{\&OverBar;}{W}}{\mathrm{\&Sigma;}}_{j=1}^{\stackrel{\&OverBar;}{W}}(G_x^2(i,j)-G_y^2(i,j))}\right);$

(4.2.2) calculated direction field consistency level:

$E_0=\frac{1}{N}\sqrt{\underset{(i^{\&prime;},j^{\&prime;})\&Element;\mathrm{\&Omega;}}{\mathrm{\&Sigma;}}|\mathrm{\&theta;}(i^{\&prime;},j^{\&prime;})-\mathrm{\&theta;}(i,j){|}^2};$

Wherein, Ω is that (i, the j) neighborhood of grid are taken as 5 * 5, and N is the number of contained grid among the Ω, N=25; θ (i ', j ') and θ (i, j) be respectively (i ', j ') and (i, j) local direction of grid;

If E ₀＞T _c, then make W=1.5 W, reappraise the direction of each grid among the Ω, repeating step (4.2.1) and (4.2.2); Until E ₀≤ T _c, T here _c=1.5;

(5) adopt the Gabor filtering method to carry out the figure image intensifying, it comprises following steps successively:

(5.1) Gabor wave filter spatial domain expression-form is:

$G(x,y,\mathrm{\&theta;})=\exp \left\{\frac{-1}{2}\right[\frac{x^{\&prime;2}}{{\mathrm{\&delta;}}_{x\&prime;}^2}+\frac{y^{\&prime;2}}{{\mathrm{\&delta;}}_{y\&prime;}^2}\left]\right\}\cos \left(2\mathrm{\&pi;}{\mathrm{fx}}^{\&prime;}\right),$ Wherein

θ ∈ [0,180) be the field of direction vertical direction of current point, x, y be in the mask each point with respect to the coordinate of mask central point, δ _{X '}=δ _{Y '}=5.0, f=0.6, spatial domain mask size is 7 * 7 pixels;

(5.2) auto adapted filtering:

Suppose input fingerprint gray level image be I (x, y), θ be (i j) puts the vertical direction of field of direction direction, then uses above-mentioned filter filtering as follows:

$F(i,j)=\frac{{\mathrm{\&Sigma;}}_{x=-w}^w{\mathrm{\&Sigma;}}_{y=-w}^{w}G(x,y,\mathrm{\&theta;})I(i+x,j+y)}{{\mathrm{\&Sigma;}}_{x=-w}^w{\mathrm{\&Sigma;}}_{y=-w}^{w}G(x,y,\mathrm{\&theta;})};$ W=3 wherein;

Ask for a numerical value by following formula then:

$\mathrm{flag}(i,j)=\frac{{\mathrm{\&Sigma;}}_{x=\frac{L}{2}}^{\frac{L}{2}-D}\left|F\right(i+x\cos \mathrm{\&theta;},j+x\sin \mathrm{\&theta;})-F(i+(x+D)\cos \mathrm{\&theta;},j+(x+D)\sin \mathrm{\&theta;}\left)\right|}{{\mathrm{\&Sigma;}}_{x=-\frac{L}{2}}^{\frac{L}{2}-D}\left(\right|F(i+x\cos \mathrm{\&theta;},j+x\sin \mathrm{\&theta;})-F(i+(x+D)\cos \mathrm{\&theta;},j+(x+D\left)\sin \mathrm{\&theta;}\right)|\&times;F[i+(x+\frac{D}{2})\cos \mathrm{\&theta;},j+(x+\frac{D}{2})\sin \mathrm{\&theta;}\left]\right)},$

Wherein L=12 is the statistics zone length, and D=2 is the statistics step-length, carries out crestal line and extracts: if F (i, j)＞flag (i, j), then (i, j) being positioned at paddy is background, is prospect otherwise be positioned at ridge;

(6) crestal line refinement, it comprises following steps successively:

(6.1) promptly do not change topological structure and do not delete under the prerequisite of straight line end points at the skeleton that keeps former figure, decide tested point " going " or " staying " according to the different conditions that with the tested point is 8 neighborhoods at center, " go " usefulness " 0 " expression, " staying " usefulness " 1 " expression;

(6.2) set up 1 dimension concordance list table, marked index is 0～255, totally 256 elements, and each element is got 1 expression and is kept, and 0 expression is removed;

(6.3) have a few in the traversal effective coverage, investigate its 8 neighborhood, all permutation and combination are mapped between 0～255 by following formula:

index＝A32×2 ⁰+A31×2 ¹+A21×2 ²+A11×2 ³

+A12×2 ⁴+A13×2 ⁵+A23×2 ⁶+A33×2 ⁷；

Wherein, Aij represents the value of the point in 8 neighborhoods, is that the element of index is table[index by index value in the search index table then], determine this tested point whether to keep or remove;

(6.4) repeating (6.3) occurs up to the point that is not removed;

(6.5) refinement aftertreatment:

(6.5.1), according to refinement figure, tentatively determine the end points in the minutiae point, promptly this is as 1 and to have and only have a point in 8 points on every side be 1, and bifurcation point, and promptly this is as 1 and to have and only have three points in 8 points on every side be 1;

(6.5.2), along the minutiae point growth, minutiae point is carried out aftertreatment:

(a), for end points, if there is the direction of another end points approaching with it in its neighborhood of 12 * 12, promptly differential seat angle then all removes these two end points less than the Tha=30 degree;

(b), the adjacent sub crunode that forms annular is coupled together, for a bifurcation, if there is the direction of another bifurcation approaching with it in its neighborhood of 12 * 12, promptly differential seat angle then removes the both less than the Tha=30 degree;

(c), remove two end points of some little stub correspondences, for an end points, if along its place crestal line through just meeting another end points within 12 pixels, then two end points are all removed;

(6.5.3), screen out direction and this field of direction differential seat angle unique point greater than 30 degree;

(7) disconnected line detects, and it comprises following steps successively:

(7.1) to the point in the former fingerprint image (x, the gray-scale value I that y) goes out (x y) carries out multi-channel filter, and it comprises following steps successively:

(7.1.1) the angle γ of disconnected line direction and x axle is dispersed turn to 12 directions, the angle between every adjacent both direction is 15 °, thereby γ gets 12 direction: γ=0, π/12, and π/6 ..., 11 π/12;

(7.1.2) for each γ, respective filter mask size is 81 * 81, is γ through direction then _iThe filtered fingerprint image of optimal filter in point (x, the value F that y) locates _{γ i}(x, y) expression:

$F_{\mathrm{\&gamma;i}}(x,y)=\underset{k=-40}{\overset{40}{\mathrm{\&Sigma;}}}\underset{l=-40}{\overset{40}{\mathrm{\&Sigma;}}}I(x+k,y+l)\&times;F({\mathrm{\&gamma;}}_i,k,l|{\mathrm{\&sigma;}}^2,\mathrm{\&eta;}),$

Wherein, (x+k is at point (x+k, gray-scale value y+l), F (γ, x, y| σ at image y+l) to I ², η) express formula for wave filter:

$F(\mathrm{\&gamma;},x,y|{\mathrm{\&sigma;}}^2,\mathrm{\&eta;})=G(\mathrm{\&gamma;},u(x,y),v(x,y){|\mathrm{\&sigma;}}^2,\mathrm{\&eta;})$

$=\exp \{-\frac{u^2+{\mathrm{\&eta;v}}^2}{{2\mathrm{\&sigma;}}^2}\}({\mathrm{\&sigma;}}^2-u^2),$

Wherein, u=xcos γ+ysin γ, v=-xsin γ+ycos γ;

(7.1.3) each figure that obtains by wave filter is carried out binaryzation with 200 as threshold value:

(7.1.4) disconnected line parametrization is for each the banded disconnected line zone on the different directions, with the pca method in the matrix analysis, it is the direction that PCA estimates this belt-like zone, length and width, and then be similar to this belt-like zone with a rectangle, it comprises following steps successively:

(7.1.4.1) in the image of binaryzation, the pixel in each belt-like zone can be used $S=\left[\begin{array}{cccccc}{x}_1& x_2& & & & x_M\\ & & .& .& .& \\ y_1& y_2& & & & y_M\end{array}\right]$ Represent that wherein first row is the each point horizontal ordinate, second row is the each point ordinate, and M is the number of pixel in the belt-like zone;

(7.1.4.2) obtain average m and the variance var of S:

$\stackrel{\&OverBar;}{m}=\left[\begin{array}{c}\stackrel{\&OverBar;}{x}\\ \stackrel{\&OverBar;}{y}\end{array}\right]=\frac{1}{M}\underset{l=1}{\overset{M}{\mathrm{\&Sigma;}}}\left[\begin{array}{c}{x}_l\\ y_l\end{array}\right],$

$\mathrm{var}=\frac{1}{M}\underset{l1=1}{\overset{M}{\mathrm{\&Sigma;}}}\underset{l2=1}{\overset{M}{\mathrm{\&Sigma;}}}\left(\right(\left[\begin{array}{c}{x}_{l1}\\ y_{l1}\end{array}\right]-\stackrel{\&OverBar;}{m})\&CenterDot;(\left[\begin{array}{c}{x}_{l2}\\ y_{l2}\end{array}\right]-\stackrel{\&OverBar;}{m}{)}^T);$

(7.1.4.3) obtain all eigenwerts of variance matrix var, select two maximum eigenvalue ₁, λ ₂, require λ ₁〉=λ ₂And their characteristics of correspondence vector q ₁, q ₂

(7.1.4.4) can obtain by (7.1.4.3):

Center (the C of rectangle _x, C _y): i.e. mean value of areas m, i.e. C _x=x, C _y=y;

The direction θ of rectangle: corresponding major axis, it is the big pairing proper vector q of eigenwert ₁

The long l of rectangle and wide ω can obtain by calculating along the mean breadth of two feature axis respectively, specific implementation: in the image basis of binaryzation, in belt-like zone, travel through along the direction perpendicular to direction θ, the average length of this belt-like zone of statistics on direction θ is as the long l of rectangle; And then travel through along the direction of the direction θ of rectangle, statistics is perpendicular to the average length of this belt-like zone on the θ direction wide ω as rectangle;

(7.1.4.5) merge: the figure merging corresponding to all binaryzations of different directions obtains the disconnected line in the whole fingerprint image; All parameterized figure corresponding to different directions are merged, and the parametrization that obtains the disconnected line in the whole fingerprint image is represented;

(8) remove based on the false minutiae point of disconnected line: for the small neighbourhood of each minutiae point, generally be 7 * 7 wicket, investigate,, just judge that this minutiae point is false point, it is removed if certain in the neighborhood a bit drops in the detected disconnected line;

(9) full details of remainder point is sent into database, canned data comprises the total number of minutiae point, minutiae point coordinate and direction;

Two, cognitive phase

Computing machine to the fingerprint of each input according to above-mentioned (2)-(7) carry out minutiae point at line drawing, and and database in the fingerprint minutiae stored compare that to find out matching degree the highest, comparison and coupling contain following steps successively:

(1) use based on the method for Hough conversion and carry out the minutiae point registration:

Calculate compensation rotation and shifting deviation, calculate: two fingerprints minutiae point is separately constituted the point set that contains M and N minutiae point separately respectively, concentrate from two points and respectively select a minutiae point to be expressed as (x respectively according to following method ₁, y ₁, θ ₁) and (x ₂, y ₂, θ ₂), utilize coordinate, direction between them to obtain a translational movement: ${\mathrm{\&Delta;}}_t=\left[\begin{array}{c}{\mathrm{\&Delta;}}_x\\ {\mathrm{\&Delta;}}_y\end{array}\right]=\left[\begin{array}{c}{x}_2-x_1\\ y_2-y_1\end{array}\right],$ Rotation amount: Δ _θ=θ ₂-θ ₁, it is right to minutiae point to travel through all M * N, statistics (Δ _x, Δ _y, Δ _θ) number of times that occurs, the highest translation rotation amount of win the vote is exactly the translation rotation amount of final use, writes down number of votes obtained vote simultaneously;

The coordinate transform of using below can be realized by following formula:

x″＝x′×cos(Δ _θ)-y′×sin(Δ _θ)+Δ _x；

y″＝x′×sin(Δ _θ)-y′×cos(Δ _θ)+Δ _y；

Wherein (x ', y ') be the coordinate before the rotation translation, (x ", y ") is the coordinate after the rotation translation

(2) extract public effective coverage:

Remember two pieces of fingerprint r, the effective coverage behind the t registration is respectively R _r, R _t, according to the parameter of trying to achieve above, to R _tBe rotated translation, then public effective coverage is R=R _r∩ R _t

(3) comparison fingerprint r, all minutiae point among the t, the minutiae point logarithm that the record comparison is successful;

(4) calculated fingerprint r, the similarity M of t minutiae point set _Rt, 0＜M _Rt＜1:

$M_{\mathrm{rt}}=\frac{\mathrm{count}}{\max ({\mathrm{count}}_t,{\mathrm{count}}_r)}\&times;\min (\frac{\mathrm{vote}}{\mathrm{Th}},1);$

Wherein count represents to compare successful minutiae point logarithm, count _rThe minutiae point number of expression fingerprint r in the public effective coverage of two width of cloth fingerprints, count _tThe minutiae point number of expression fingerprint t in the public effective coverage of two width of cloth fingerprints; Th is an empirical value, is taken as 12;

(5) difference that error rate is required according to us, a given threshold value Th_M _n=0.4, if M _n＞Th_M _n, think that then two width of cloth fingerprints are from same finger; Otherwise, think that then two width of cloth fingerprints are not from same finger.

Images