CN105787451A - Fingerprint matching method based on multi-judgment point mode - Google Patents

Abstract

The invention provides a fingerprint matching method based on a multi-judgment point mode. The method comprises the steps of: constructing a local detail structure with the help of a center point of a fingerprint image, using a similar triangle theory to obtain a reference point on the structure; using a variable limit box method to perform secondary matching; and using a multi-condition judgment method to select a threshold and performing the final judgment. According to the invention, the reference point of matching can be basically and accurately positioned, the transformation parameters are calculated accurately, the rotation and translation problems of the fingerprint image to be recognized relative to a template fingerprint image are solved, the image matching is performed effectively, the matching speed is relatively high relative to a general point mode matching method, the FAR and FRR are lowered and the fingerprint recognition accuracy is increased.

Description

A kind of finger print matching method based on many determination points pattern

Technical field

The present invention relates to the finger print matching method based on many determination points pattern, belong to technical field of image processing.

Background technology

The final purpose of fingerprint recognition is to determine that two pieces of fingerprints are whether from same finger.Complete fingerprint recognition, it is necessary to the feature being currently entered fingerprint extraction is mated with the template characteristic preserved in advance, so can be only achieved the final purpose of fingerprint recognition, so matching algorithm is related to fingerprint recognition success, be the committed step of fingerprint recognition.Fingerprint matching is the final step in fingerprint recognition system, is also the main foundation evaluating whole fingerprint recognition system performance.Fingerprint matching is to judge whether two pieces of fingerprints come from same finger according to the fingerprint characteristic extracted.When fingerprint image quality is better, the result of matching algorithm is generally relatively good.But, fingerprint image of the prior art has translation, rotates and non-linear deformation, finger surface dry and wet situation, the difference of fingerprint collecting equipment when reading in, these all have impact on the effect of Finger print characteristic abstract, and then affects the result of fingerprint matching.So, fingerprint is carried out correct match cognization when fingerprint image quality is bad by key challenge is how of fingerprint matching.In order to judge whether two pieces of fingerprints come from same finger accurately and rapidly, fingerprint matching algorithm must also have certain fault-tolerance, and computational complexity can not be too high, and time cost is little and accuracy is high.

Difference according to detail characteristics of fingerprints, fingerprint matching algorithm mainly includes based on Point Pattern Matching algorithm, based on texture pattern matching algorithm with based on the matching algorithm of figure.Coupling based on texture can overcome the deficiency based on minutiae point method, is receiving publicity as a kind of new coupling thinking and is applying.The method of Texture Matching takes full advantage of abundant crestal line, and second-rate region details can be overcome to a certain extent to be difficult to the difficulty extracted.The defect of minutiae matching can be made up in some application.But image is made multiple convolution due to needs by this method, and operand is very big, and is difficult to process the coupling of relatively large deformation fingerprint image, is not suitable for the identification system of 1:N pattern.Figure coupling is a kind of method of configuration mode identification, it is possible to be applied to the classification of fingerprint, details index and coupling.There are many scholars to propose the fingerprint minutiae matching based on structural information, make use of the topology information in fingerprint image, to overcome the noise of fingerprint image, to rotate and the deformation interference to identifying.

Above-mentioned sorting technique is not absolute, and various methods connect each other, has a lot of algorithm intersected with each other simultaneously, and each algorithm has the feature of oneself, and for special application.Such as, the method for figure coupling is better to the noise capacity of resisting disturbance of fingerprint image of poor quality, but existing method is without the confirmation of large-scale experiment；Minutiae matching confronts the calculating of measured fingerprint image accurately, but the ga s safety degree of textural characteristics is not strong；Mixing matching process based on texture information and String matching improves discrimination to a certain extent, but calculation cost is very high；Non-thread sexual type can be solved based on triangle coupling and the mixing matching process of dynamic programming and become problem, but the feature extracted is excessive, it is difficult to meet the online requirement used.

It practice, judge that whether two fingerprints are very difficult from same finger.First, owing to finger cannot be made strict restriction with the contact position on collecting device surface, direction, finger by surging and pressing power thrusts etc. when gathering fingerprint, thus identical finger not only can be made incomplete same at the collected image-region of different time, and between image, it is inevitably present translation transformation, rotational deformation, dimension deformation and nonlinear deformation.Secondly, when picture quality is poor, minutiae extraction process can produce a lot of error, including producing false detail point, omitting true detail point and minutiae point position, the deviation of directivity.Even these factors cause the fingerprint image representing identical finger, wherein the quantity of minutiae point, position, direction etc. are also incomplete same, make fingerprint minutiae matching problem extremely difficult.And the present invention can solve problem above well.

Summary of the invention

Present invention aim at solving above-mentioned the deficiencies in the prior art, propose a kind of finger print matching method based on many determination points pattern, the method constructs local detail structure by the central point of fingerprint image, and utilize similar triangle theory to ask for datum mark on this structure, and utilize the method for variable gauge box to carry out second degree matches, finally utilize many condition decision method selected threshold finally to judge.

This invention address that its technical problem is adopted the technical scheme that: a kind of finger print matching method based on many determination points pattern, the method can the datum mark of position matching accurately, ask for transformation parameter accurately, solve the problem waiting to know the fingerprint image rotation relative to template fingerprint image and translation, being effectively taking place images match, relative to general Point Pattern Matching method, the matching speed of the present invention is very fast, reduce FAR and FRR, improve fingerprint recognition accuracy.

Method flow:

Step 1: utilize similar triangle theory to ask for datum mark, according to datum mark in input fingerprint image and template fingerprint image to asking for X, the position deviation in Y coordinate direction and the rotation transformation factor, so that it is determined that transformation factor collection；

Step 2: input fingerprint image and template fingerprint image are carried out first order coupling, calculates bifurcation and the end points number in input fingerprint image and template fingerprint interesting image district respectively, it is determined whether enter next stage coupling；

Step 3: utilize the method for variable gauge box to carry out second degree matches, the rectangular area around selected characteristic point is as gauge box, as long as the characteristic point of the fingerprint to be identified after conversion drops in this region, direction is consistent and type is identical, then it is assumed that be match point；

Step 4: set the some logarithm of successful match, pairing is counted and the threshold value such as discrepancy score summation of the ratio of corresponding fingerprint characteristic sum, each matching double points finally judges whether input fingerprint image mates with template fingerprint image.

The present invention adopts the fundamental property of triangle, it is determined that datum mark and transformation factor；Carry out second degree matches, introduce the concept of the gauge box of variable-size, the size of gauge box is determined by the distance between current signature point and central point, as long as the characteristic point of the fingerprint to be identified after conversion drops in this region, and type is identical, direction is basically identical, then it is believed that the two feature point pairs is the characteristic point of a pair coupling.

Beneficial effect:

1, the present invention can the datum mark of position matching accurately, ask for transformation parameter accurately, be effectively taking place images match, relative to general Point Pattern Matching method.

2, the matching speed of the present invention is very fast, reduces FAR and FRR, improves fingerprint recognition accuracy well.

3, the datum mark contrast locating that present invention determine that is relatively accurate, and shortening consuming time, improves discrimination and execution efficiency well.

Accompanying drawing explanation

Fig. 1 is variable gauge box schematic diagram when being the second degree matches of the present invention.

Fig. 2 is the method flow diagram of the present invention.

Detailed description of the invention

Below in conjunction with Figure of description, the invention is described in further detail.

One, the asking for of datum mark and transformation factor

As depicted in figs. 1 and 2, the present invention determines datum mark according to the mutual relation between three neighbour's characteristic points, asks for transformation parameter.The problems such as the coupling of two width fingerprint images mainly solves to rotate, translation and deformation, assume that the input of fingerprint matching is set P and the Q of two characteristic points, P extracts from the fingerprint image of input, another clicks Q then from fingerprint characteristic data storehouse, namely extracts from template fingerprint image.The two point set is expressed as:

P={p₁,p₂,...,p_m}={ (x_p1,y_p1,θ_p1,T_p1),(x_p2,y_p2,θ_p2,T_p2),...,(x_pm,y_pm,θ_pm,T_pm)}

Q={q₁,q₂,...,q_n}={ (x_q1,y_q1,θ_q1,T_q1),(x_q2,y_q2,θ_q2,T_q2),...,(x_qn,y_qn,θ_qn,T_qn)}

Wherein (x_pi,y_pi,θ_pi,T_pi) and (x_qj,y_qj,θ_qj,T_qj) have recorded in point set P 4 information of jth characteristic point in ith feature point and point set Q respectively: X-coordinate, Y coordinate, direction and characteristic point type.If two width fingerprint images mate completely, then can obtaining template characteristic point set by the fingerprint characteristic point set of input is done certain conversion (rotate, translation with flexible), therefore, point set P can pass through rotation, translate and stretching be approximated to point set Q.But in practical application, the finger-print region of twice collection can not be completely the same, and due to the reason such as deformation, noise, there is certain skew the position of some of which details, also some characteristic point is added or removed, and so needs to find the some coupling as much as possible that a kind of conversion makes two points concentrate.If when certain conversion, two characteristic point position is close, direction is basically identical, and type is identical, then it is assumed that the two point defines when this conversion and once mates.

In order to some characteristic point in input fingerprint image to be converted to the corresponding position in template fingerprint image according to certain mapping mode, it is necessary to know corresponding transformation factor.Due to all fingerprint images all by same fingerprint capturer typing, so putting aside the problem on deformation of fingerprint image herein, it is believed that be basically unchanged, additionally, characteristic point type also should not change before and after conversion, namely

Assume the certain point p in input point set P_iCharacteristic information be (x_pi,y_pi,θ_pi,T_pi), after fortran it isTemplate point set Q puts q accordingly_jCharacteristic information be (x_qj,y_qj,θ_qj,T_qj).IfThen think that transformation factor is (Δ x, Δ y, Δ θ), p_iWith q_jSimilar.

$\left[\begin{array}{c}{x}_{pi}^T\\ y_{pi}^T\\ {\mathrm{\θ}}_{pi}^T\\ T_{pi}^T\end{array}\right]=\left[\begin{array}{cccc}\cos \mathrm{\Δ}\mathrm{\θ}& -\sin \mathrm{\Δ}\mathrm{\θ}& 0& \mathrm{\Δ}x\\ \sin \mathrm{\Δ}\mathrm{\θ}& \cos \mathrm{\Δ}\mathrm{\θ}& 0& \mathrm{\Δ}y\\ 0& 0& 1& \mathrm{\Δ}\mathrm{\θ}\\ 0& 0& 0& 1\end{array}\right]\left[\begin{array}{c}{x}_{pi}\\ y_{pi}\\ {\mathrm{\θ}}_{pi}\\ T_{pi}\end{array}\right]$ Formula 1

Δ x and the parallel factor in Δ y respectively X, Y-direction in above formula, Δ θ is then twiddle factor.In order to mate two pieces of fingerprints exactly, it is thus necessary to determine that these 3 transformation factors.

Any one characteristic point p that input point is concentrated_iAny one characteristic point q with template point concentration_jForm point right.Input fingerprint image finds distance p_iNearest characteristic point, is designated as p₁, find distance p_iSecondary near characteristic point, is designated as p₂, in like manner, find q₁, q₂.So form 2 triangle (p at input fingerprint image and template fingerprint image_i,p₁,p₂) and (q_j,q₁,q₂).Judging two triangle similarity degrees, if similarity degree is high, then the coupling being possible is right, according to two stack features point subsets ask for transformation parameter is exactly the transformation parameter of this two width image.According to required transformation parameter, two width fingerprint images are converted (rotating and translation), determine whether the similarity of two width images.

Three limits may determine that a unique triangle, therefore can judge the similarity degree of the two triangle according to the distance between 3 characteristic points and the mutual alignment relation between them.

The similarity of triangle judge and transformation parameter to ask for step as follows:

(1) summit p is calculated respectively_iAnd q_jThe corresponding length of side | p₁p₂| with | q₁q₂|；

(2) if | | p₁p₂|-|q₁q₂||>D₁, then illustrating that triangle can not be congruent, this judgement terminates, and reselects the summit p needing to judge_iAnd q_jAnd apart from they 2 nearest characteristic point p₁, p₂And q₁, q₂, return step (1)；

(3) otherwise, p is calculated respectively_iAnd q_jTo p₁, p₂And q₁, q₂Distance | p_ip₁|, | p_ip₂| with | q_jq₁|, | q_jq₂|.If had | | p_ip₁|-|p_ip₂| |≤D₂And | | q_jq₁|-|q_jq₂| |≤D₂, then 3 limits of two trianglees approximately equal respectively, the approximate congruence of 2 trianglees is described.Otherwise reselect the summit p needing to judge_iAnd q_jAnd apart from they 2 nearest characteristic point p₁, p₂And q₁, q₂, return step (1)；

(4) according to the summit that 2 trianglees are corresponding, the direction difference between the characteristic point being likely to coupling is calculated respectivelyDirection mathematic interpolation formula:

Formula 2

If the angle difference approximately equal between corresponding vertex, namelyThen think these 2 characteristic point subset (p_i,p₁,p₂) and (q_j,q₁,q₂) between angle meet a kind of rotation transformation relation, the computing formula of the rotation transformation factor now is as follows:

$\mathrm{\Δ}\mathrm{\θ}=\frac{1}{3}({\mathrm{\Δ\θ}}_{p_i{q}_j}+{\mathrm{\Δ\θ}}_{p_1{q}_1}+{\mathrm{\Δ\θ}}_{p_2{q}_2})$ Formula 3

Otherwise judge between these 2 character subsets, to form a kind of matching relationship, reselect the summit p needing to judge_iAnd q_jAnd apart from they 2 nearest characteristic point p₁, p₂And q₁, q₂, return step (1)；

(5) (p is chosen_i,q_j) as the conversion initial point of rotation transformation, to (q_j,q₁,q₂) do rotation transformation, the value after conversion is (q_j,q′₁,q′₂), and calculate the position deviation in rotation transformation X, Y-direction later respectively Its computing formula is as follows:

Δx_pq=x_p-x_qFormula 4

Δy_pq=y_p-y_qFormula 5

Now, if hadAndThen think these 2 characteristic point subset (p_i,p₁,p₂) and (q_j,q₁,q₂) also meet a kind of conversion in the x, y direction.It is considered as this 2 characteristic point subset (p_i,p₁,p₂) and (q_j,q₁,q₂) between define a kind of matching relationship, translation now and the transformation factor of rotation respectively (Δ x, Δ y, Δ θ).Wherein, Δ x, Δ y, Δ θ is respectively as follows:

$\mathrm{\Δ}x=\frac{1}{3}({\mathrm{\Δx}}_{p_i{q}_j}+{\mathrm{\Δx}}_{p_1{q}_1^{\′}}+{\mathrm{\Δx}}_{p_2{q}_2^{\′}})$ Formula 6

$\mathrm{\Δ}y=\frac{1}{3}({\mathrm{\Δy}}_{p_i{q}_j}+{\mathrm{\Δy}}_{p_1{q}_1^{\′}}+{\mathrm{\Δy}}_{p_2{q}_2^{\′}})$ Formula 7

$\mathrm{\Δ}\mathrm{\θ}=\frac{1}{3}({\mathrm{\Δ\θ}}_{p_i{q}_j}+{\mathrm{\Δ\θ}}_{p_1{q}_1}+{\mathrm{\Δ\θ}}_{p_2{q}_2})$ Formula 8

Two, first order coupling

With the reference point circle of position heart, regular length is radius, marks an equal region of interest (ROI) respectively at template fingerprint image and input fingerprint image, as first order coupling interval.Choose ROI effect: one can resist fingerprint deformation；Two can conveniently mate.

(1) choosing ROI radius is 96, and unit is pixel.

(2) number of end points and bifurcation, the bifurcation number of logging template fingerprint image and end points number respectively M in search ROI_b, M_e, input fingerprint image characteristics point number is N_b, N_e。

(3) calculate | M_b-N_b|, | M_e-N_e|:

If | M_b-N_b| < ε₁And | M_e-N_e| < ε₂, then next stage coupling is entered.Otherwise directly not think and mate.Wherein ε₁=0.5min (M_b,N_b), ε₂=0.5min (M_e,N_e)。

Three, second level coupling

In order to overcome the impact of non-linear deformation, introduce the concept of gauge box of variable-size, to each characteristic point in template fingerprint feature point set, choose a rectangular area around it the gauge box as it.Such as Fig. 1, it can be seen that the size of gauge box is determined by the distance between current signature point and central point, should diminishing from the local polar radius close to central point, polar angle becomes big；On the contrary, polar radius should becoming big from the place away from central point, polar angle diminishes.As long as the characteristic point of the fingerprint to be identified after conversion drops in this region, and type is identical, and direction is basically identical, then it is believed that the two feature point pairs is the characteristic point of a pair coupling.

Four, based on the method for composite mode many condition judgement

The present invention is when match cognization, it is possible to extension three below aspect as judgment condition, including: 1) the some logarithm of successful match；2) ratio that pairing is counted and corresponding fingerprint characteristic is total；3) the discrepancy score summation of each matching double points, i.e. (weighted sum of direction difference and range difference), display, the more low matching degree of this mark is more high.

General dot pattern finger print matching method is improved by the present invention, the local detail structure of structure fingerprint image, and utilizing Similar Principle of Triangle to ask for datum mark and transformation factor on this structure, the method introducing gauge box is mated, and finally utilizes many condition judgement definition to identify thresholding.Compared with general dot pattern finger print matching method, the datum mark contrast locating that present invention determine that is relatively accurate, and shortening consuming time, can improve discrimination and execution efficiency.

Claims (5)

1. the finger print matching method based on many determination points pattern, it is characterised in that described method comprises the steps:

Step 1: utilize similar triangle theory to ask for datum mark, according to datum mark in input fingerprint image and template fingerprint image to asking for X, the position deviation in Y coordinate direction and the rotation transformation factor, so that it is determined that transformation factor collection；

Step 2: input fingerprint image and template fingerprint image are carried out first order coupling, calculates bifurcation and the end points number in input fingerprint image and template fingerprint interesting image district respectively, it is determined whether enter next stage coupling；

Step 3: utilize the method for variable gauge box to carry out second degree matches, the rectangular area around selected characteristic point is as gauge box, as long as the characteristic point of the fingerprint to be identified after conversion drops in this region, direction is consistent and type is identical, then it is assumed that be match point；

Step 4: set the some logarithm of successful match, pairing is counted and the threshold value such as discrepancy score summation of the ratio of corresponding fingerprint characteristic sum, each matching double points finally judges whether input fingerprint image mates with template fingerprint image.

2. a kind of finger print matching method based on many determination points pattern according to claim 1, it is characterised in that described method is to adopt the fundamental property of triangle, it is determined that datum mark and transformation factor；Carry out second degree matches, introduce the concept of the gauge box of variable-size, the size of gauge box is determined by the distance between current signature point and central point, as long as the characteristic point of the fingerprint to be identified after conversion drops in this region, and type is identical, direction is basically identical, then it is believed that the two feature point pairs is the characteristic point of a pair coupling.

3. a kind of finger print matching method based on many determination points pattern according to claim 1 and 2, it is characterized in that, described method determines datum mark according to the mutual relation between three neighbour's characteristic points, ask for transformation parameter, the problems such as the coupling of two width fingerprint images mainly solves to rotate, translation and deformation, assume that the input of fingerprint matching is set P and the Q of two characteristic points, P extracts from the fingerprint image of input, another clicks Q then from fingerprint characteristic data storehouse, namely extracting from template fingerprint image, the two point set is expressed as:

P={p₁,p₂,...,p_m}={ (x_p1,y_p1,θ_p1,T_p1),(x_p2,y_p2,θ_p2,T_p2),...,(x_pm,y_pm,θ_pm,T_pm)}

Q={q₁,q₂,...,q_n}={ (x_q1,y_q1,θ_q1,T_q1),(x_q2,y_q2,θ_q2,T_q2),...,(x_qn,y_qn,θ_qn,T_qn)}

Wherein (x_pi,y_pi,θ_pi,T_pi) and (x_qj,y_qj,θ_qj,T_qjnull) have recorded in point set P 4 information of jth characteristic point in ith feature point and point set Q respectively: X-coordinate、Y coordinate、Direction and characteristic point type，If two width fingerprint images mate completely，Then can by the fingerprint characteristic point set of input being done certain conversion，Namely (rotate、Translation is with flexible) obtain template characteristic point set，Therefore，Point set P can pass through to rotate、Translation and stretching are approximated to point set Q，But in practical application，The finger-print region of twice collection can not be completely the same，And due to deformation、The reasons such as noise，There is certain skew the position of some of which details，Also some characteristic point is added or removed，So need to find the some coupling as much as possible that a kind of conversion makes two points concentrate，If when certain conversion，Two characteristic point positions are close、Direction is basically identical，And type is identical，Then think that the two point defines when this conversion once to mate.

4. a kind of finger print matching method based on many determination points pattern according to claim 1 and 2, it is characterised in that the similarity of the triangle of described method judges and the step of asking for of transformation parameter includes:

(1) summit p is calculated respectively_iAnd q_jThe corresponding length of side | p₁p₂| with | q₁q₂|, specification error value D₁And D₂；

(2) if | | p₁p₂|-|q₁q₂||>D₁, then illustrating that triangle can not be congruent, this judgement terminates, and reselects the summit p needing to judge_iAnd q_jAnd apart from they 2 nearest characteristic point p₁, p₂And q₁, q₂, return step (1)；

(3) otherwise, p is calculated respectively_iAnd q_jTo p₁, p₂And q₁, q₂Distance | p_ip₁|, | p_ip₂| with | q_jq₁|, | q_jq₂|, if had | | p_ip₁|-|p_ip₂| |≤D₂And | | q_jq₁|-|q_jq₂| |≤D₂, then 3 limits of two trianglees approximately equal respectively, the approximate congruence of 2 trianglees is described, otherwise reselects the summit p needing to judge_iAnd q_jAnd apart from they 2 nearest characteristic point p₁, p₂And q₁, q₂, return step (1)；

(4) according to the summit that 2 trianglees are corresponding, the direction difference between the characteristic point being likely to coupling is calculated respectively Direction mathematic interpolation formula:

Formula 2

If the angle difference approximately equal between corresponding vertex, namelyThen think these 2 characteristic point subset (p_i,p₁,p₂) and (q_j,q₁,q₂) between angle meet a kind of rotation transformation relation, the computing formula of the rotation transformation factor now is as follows:

$\mathrm{\&Delta;}\mathrm{\&theta;}=\frac{1}{3}({\mathrm{\&Delta;\&theta;}}_{p_i{q}_j}+{\mathrm{\&Delta;\&theta;}}_{p_1{q}_1}+{\mathrm{\&Delta;\&theta;}}_{p_2{q}_2})$ Formula 3

Otherwise judge between these 2 character subsets, to form a kind of matching relationship, reselect the summit p needing to judge_iAnd q_jAnd apart from they 2 nearest characteristic point p₁, p₂And q₁, q₂, return step (1)；

(5) (p is chosen_i,q_j) as the conversion initial point of rotation transformation, to (q_j,q₁,q₂) do rotation transformation, the value after conversion is (q_j,q′₁,q'₂), and calculate the position deviation in rotation transformation X, Y-direction later respectively Its computing formula is as follows:

Δx_pq=x_p-x_qFormula 4

Δy_pq=y_p-y_qFormula 5

Now, if had ${\mathrm{\&Delta;x}}_{p_i{q}_j}\&ap;{\mathrm{\&Delta;x}}_{p_1{q}_1^{\&prime;}}\&ap;{\mathrm{\&Delta;x}}_{p_2{q}_2^{\&prime;}}$ And ${\mathrm{\&Delta;y}}_{p_i{q}_j}\&ap;{\mathrm{\&Delta;y}}_{p_1{q}_1^{\&prime;}}\&ap;{\mathrm{\&Delta;y}}_{p_2{q}_2^{\&prime;}},$ Then think these 2 characteristic point subset (p_i,p₁,p₂) and (q_j,q₁,q₂) also meet a kind of conversion in the x, y direction, it is considered as this 2 characteristic point subset (p_i,p₁,p₂) and (q_j,q₁,q₂) between define a kind of matching relationship, translation now and the transformation factor of rotation respectively (Δ x, Δ y, Δ θ), wherein, Δ x, Δ y, Δ θ is respectively as follows:

$\mathrm{\&Delta;}x=\frac{1}{3}({\mathrm{\&Delta;x}}_{p_i{q}_j}+{\mathrm{\&Delta;x}}_{p_1{q}_1^{\&prime;}}+{\mathrm{\&Delta;x}}_{p_2{q}_2^{\&prime;}})$ Formula 6

$\mathrm{\&Delta;}y=\frac{1}{3}({\mathrm{\&Delta;y}}_{p_i{q}_j}+{\mathrm{\&Delta;y}}_{p_1{q}_1^{\&prime;}}+{\mathrm{\&Delta;y}}_{p_2{q}_2^{\&prime;}})$ Formula 7

$\mathrm{\&Delta;}\mathrm{\&theta;}=\frac{1}{3}({\mathrm{\&Delta;\&theta;}}_{p_i{q}_j}+{\mathrm{\&Delta;\&theta;}}_{p_1{q}_1}+{\mathrm{\&Delta;\&theta;}}_{p_2{q}_2})$ Formula 8.

5. a kind of finger print matching method based on many determination points pattern according to claim 1, it is characterised in that described method is based on the judgement of composite mode many condition, and described judgment condition includes: the some logarithm of (1) successful match；(2) ratio that pairing is counted and corresponding fingerprint characteristic is total；(3) the discrepancy score summation of each matching double points, i.e. (weighted sum of direction difference and range difference), finally determine whether input fingerprint image mates with template fingerprint image.