CN105654025B - A kind of fingerprint identification method, device and electronic equipment - Google Patents
A kind of fingerprint identification method, device and electronic equipment Download PDFInfo
- Publication number
- CN105654025B CN105654025B CN201510337023.6A CN201510337023A CN105654025B CN 105654025 B CN105654025 B CN 105654025B CN 201510337023 A CN201510337023 A CN 201510337023A CN 105654025 B CN105654025 B CN 105654025B
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- characteristic
- user fingerprints
- matching degree
- group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000000605 extraction Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 17
- 230000006870 function Effects 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 239000000284 extract Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1365—Matching; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The present invention discloses a kind of fingerprint identification method, device and electronic equipment, it is based on preset fingerprint characteristic data library and carries out match cognization to user fingerprints feature to be identified, and obtain the Optimum Matching degree of the user fingerprints feature, later when the Optimum Matching degree reaches the threshold value of setting, the user is identified.Wherein, the fingerprint characteristic data library includes at least one fingerprint template, which includes P group characteristic point weight, and every group of weight corresponds to a user fingerprints state, and every group of characteristic point weight is used to calculate the matching degree numerical value of user fingerprints under its corresponding states.It can be seen that, the present invention is directed to the different conditions of user fingerprints in advance, the different characteristic point weight of multiple groups is had matched for each fingerprint template in database, to when user fingerprints are because of factors such as dry or decortications, when the fingerprint characteristic extracted being caused to change, the accuracy of fingerprint recognition can be improved to calculate an accurate matching degree by using the characteristic point weight group of proper states.
Description
Technical field
The invention belongs to the intelligent identification technology field of biological characteristic more particularly to a kind of fingerprint identification method, device and
Electronic equipment.
Background technique
Fingerprint identification technology is a kind of most widely used biometrics identification technology, and the technology based on including in fingerprint
The various characteristic points such as destination node, bifurcation, ramification point, isolated point, circling point, short grain realize fingerprint recognition.Current many high-end hands
Fingerprint identification function has been integrated in machine.
Fingerprint identification technology includes two stages of match cognization of Finger print characteristic abstract and fingerprint characteristic.Traditional finger
Line identifying schemes are stored with acquisition in advance (for example, can adopt in user's registration fingerprint identification function in fingerprint characteristic data library
Collection), for the fingerprint characteristic as fingerprint template.To can mention after the fingerprint characteristic for extracting the inputted fingerprint of user
The user fingerprints feature taken and each fingerprint template for including in fingerprint characteristic data library are compared, if the fingerprint characteristic of user
The threshold value for reaching setting with the matching degree of characteristic point each in a certain fingerprint template, then identify the user.
However, traditional fingerprinting scheme can not be directed to the different conditions of user fingerprints, it is effectively identified, example
Such as, when user fingerprints are because of factors such as dry or decortications, and certain characteristic points are caused to be difficult to extract, and then cause the fingerprint extracted special
When sign temporarily changes, the problem of can not effectively identifying is also easy to produce using traditional fingerprinting scheme.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of fingerprint identification method, device and electronic equipments, it is intended to solve
Traditional fingerprinting scheme can not be directed to the different conditions of user fingerprints, this problem effectively be identified to it, promotion refers to
The accuracy of line identification.
For this purpose, the present invention is disclosed directly below technical solution:
A kind of fingerprint identification method, comprising:
Obtain the fingerprint of user's input；
Feature point extraction is carried out to the fingerprint, obtains the first fingerprint characteristic to be identified；
Match cognization is carried out to first fingerprint characteristic based on preset fingerprint characteristic data library, and obtains described first
The Optimum Matching degree of fingerprint characteristic；Wherein, the fingerprint characteristic data library includes at least one fingerprint template, each fingerprint
Template includes the second fingerprint characteristic and P group characteristic point weight, the corresponding user fingerprints state of every group of characteristic point weight, and every group of spy
Sign point weight is used to calculate the matching degree numerical value of user fingerprints under its corresponding user fingerprints state, and P is the natural number greater than 1；
If the Optimum Matching degree reaches the threshold value of setting, fingerprint recognition success.
The above method, it is preferred that first fingerprint characteristic, second fingerprint characteristic separately include the spy of corresponding number
Point is levied, the characteristic point includes destination node, bifurcation, ramification point, isolated point, circling point, short grain.
The above method, it is preferred that described to be based on preset fingerprint characteristic data library to first fingerprint characteristic progress
With identification, and obtain the Optimum Matching degree of first fingerprint characteristic, comprising:
By the second fingerprint that each fingerprint template is included in first fingerprint characteristic, with the fingerprint characteristic data library
Feature is matched, and matching result is obtained；
The matching result is weighted in each group characteristic point weight for being utilized respectively the fingerprint template, obtains institute
State matching degree of first fingerprint characteristic under various user fingerprints states；
From first fingerprint characteristic correspond to each fingerprint template, each user fingerprints state a series of matching degrees in, choosing
The maximum matching degree of numerical value is taken out, as the Optimum Matching degree of first fingerprint characteristic.
The above method, it is preferred that the matching result includes n dimension 0-1 vector (a1,a2,……,an), n is oneself greater than 1
So number, wherein
ai=1 indicates the ith feature point in first fingerprint characteristic, with i-th in second fingerprint characteristic
Characteristic point matches；
ai=0 indicates the ith feature point in first fingerprint characteristic, with i-th in second fingerprint characteristic
Characteristic point mismatches, i=1,2 ... ..., n.
The above method, it is preferred that further include:
If fingerprint recognition success, according to used matching result when the Optimum Matching is spent is calculated, to calculating
Used one group of characteristic point weight is adjusted when the Optimum Matching is spent out.
The above method, it is preferred that further include:
In advance under preset P kind user fingerprints state, to the fingerprint template carry out characteristic point Weight Training, obtain with
The one-to-one P group characteristic point weight of P kind user fingerprints state.
The above method, it is preferred that further include:
If the Optimum Matching degree is not up to the threshold value set, fingerprint recognition failure.
A kind of fingerprint identification device, comprising:
Fingerprint obtains module, for obtaining the fingerprint of user's input；
Characteristic extracting module obtains the first fingerprint characteristic to be identified for carrying out feature point extraction to the fingerprint；
Match cognization module, for carrying out matching knowledge to first fingerprint characteristic based on preset fingerprint characteristic data library
Not, and the Optimum Matching degree of first fingerprint characteristic is obtained；Wherein, the fingerprint characteristic data library includes at least one fingerprint
Template, each fingerprint template include the second fingerprint characteristic and P group characteristic point weight, the corresponding user of every group of characteristic point weight
Fingerprint state, and every group of characteristic point weight is used to calculate the matching degree numerical value of user fingerprints under its corresponding user fingerprints state, P
For the natural number greater than 1；
First result judging module, for when the Optimum Matching degree reaches the threshold value of setting, judgement recognition result is
Fingerprint recognition success.
Above-mentioned apparatus, it is preferred that the match cognization module includes:
Matching unit is used for fingerprint template each in first fingerprint characteristic, with fingerprint characteristic data library institute
The second fingerprint characteristic for including is matched, and matching result is obtained；
Computing unit, each group characteristic point weight for being utilized respectively the fingerprint template add the matching result
Power calculates, and obtains matching degree of first fingerprint characteristic under various user fingerprints states；
Selection unit, for corresponding to a system of each fingerprint template, each user fingerprints state from first fingerprint characteristic
In column matching degree, the maximum matching degree of numerical value is selected, as the Optimum Matching degree of first fingerprint characteristic.
Above-mentioned apparatus, it is preferred that further include:
Weighed value adjusting module, in fingerprint recognition success, foundation to calculate used when the Optimum Matching is spent
Matching result is adjusted to used one group of characteristic point weight when the Optimum Matching is spent is calculated.
Above-mentioned apparatus, it is preferred that further include:
Preprocessing module, under preset P kind user fingerprints state, carrying out characteristic point to the fingerprint template in advance
Weight Training obtains and the one-to-one P group characteristic point weight of the P kind user fingerprints state.
Above-mentioned apparatus, it is preferred that further include:
Second result judging module, for adjudicating recognition result when the Optimum Matching degree is not up to the threshold value set
For fingerprint recognition failure.
A kind of electronic equipment, including fingerprint identification device as described above.
As it can be seen from the above scheme the present invention is based on preset fingerprint characteristic data library to user fingerprints feature to be identified into
Row match cognization, and the Optimum Matching degree of the user fingerprints feature is obtained, reach setting in the Optimum Matching degree later
When threshold value, the user is identified.Wherein, the fingerprint characteristic data library includes at least one fingerprint template, which includes
Second fingerprint characteristic and P group characteristic point weight, the corresponding user fingerprints state of every group of characteristic point weight, and every group of characteristic point weight
For calculating the matching degree numerical value of user fingerprints under its corresponding states.As it can be seen that the present invention is directed to the different shapes of user fingerprints in advance
State has matched the different characteristic point weight of multiple groups for each fingerprint template in database, thus when user fingerprints because dry or
The factors such as decortication can be by using the characteristic point weight group of proper states, to count when the fingerprint characteristic extracted being caused to change
An accurate matching degree is calculated, solves the problems, such as that traditional scheme exists, improves the accuracy of fingerprint recognition.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is the flow chart of fingerprint identification method embodiment one provided by the present application；
Fig. 2 is the flow chart of fingerprint identification method embodiment two provided by the present application；
Fig. 3 is the weight group training process schematic diagram that the embodiment of the present application two provides；
Fig. 4 is the flow chart of fingerprint identification method embodiment three provided by the present application；
Fig. 5 is the flow chart of fingerprint identification method example IV provided by the present application；
Fig. 6-Fig. 9 is the structural schematic diagram for the fingerprint identification device that the embodiment of the present application five provides.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Embodiment one
The embodiment of the present invention one discloses a kind of fingerprint identification method, which can be applied to smart phone, puts down
In the electronic equipments such as plate computer, for example, being particularly applicable in the user identity authentication of electronic equipment respective service.With reference to Fig. 1,
The method may include following steps:
S101: the fingerprint of user's input is obtained.
User can specifically be obtained and pass through the fingerprint that fingerprint sensor is inputted.
S102: feature point extraction is carried out to the fingerprint, obtains the first fingerprint characteristic to be identified.
Fingerprint lines is not continuous, smooth straight, but the features such as interruption, bifurcated or turnover often occurs, by
The characteristic point that these features generate provides the confirmation message of fingerprint uniqueness, wherein most typical characteristic point is destination node and divides
Crunode, other characteristic points further include ramification point, isolated point, circling point, short grain etc., and the parameter of characteristic point includes direction, curvature, position
It sets.
To obtain including destination node, bifurcation, disagreement after the fingerprint for inputting user carries out feature point extraction
The user fingerprints feature of the various characteristic points such as point, isolated point, circling point, short grain.
S103: match cognization is carried out to first fingerprint characteristic based on preset fingerprint characteristic data library, and obtains institute
State the Optimum Matching degree of the first fingerprint characteristic；Wherein, the fingerprint characteristic data library includes at least one fingerprint template, Mei Gesuo
Stating fingerprint template includes the second fingerprint characteristic and P group characteristic point weight, and every group of characteristic point weight corresponds to a user fingerprints state, and
Every group of characteristic point weight is used to calculate the matching degree numerical value of user fingerprints under its corresponding user fingerprints state, and P is oneself greater than 1
So number.
In daily life, user fingerprints often will appear the situations such as excessively dry, excessively wet or decortication, lead to certain fingers
Line feature is difficult to be extracted, and then influences the accuracy of fingerprint recognition, is based on this, and the present embodiment first draws user fingerprints state
It is divided into normal, dry, wet and four kinds of states of decortication.
It at the same time, is in fingerprint characteristic data library by learning extraction, the identification situation of fingerprint characteristic under various states
Each fingerprint template assign 4 groups of characteristic point weights, the corresponding corresponding user fingerprints state of every group of characteristic point weight.
Assuming that altogether including n characteristic point in a fingerprint template, then the fingerprint characteristic that fingerprint template includes is represented by one
N-dimensional vector comprising n characteristic value: (c1,c2,……,cn), wherein characteristic value ciFor ith feature point in fingerprint template
It is specific to indicate；And corresponding to 4 kinds of states of the normal, dry, wet of user fingerprints and decortication, fingerprint template includes 4 groups of characteristic points
Weight: (w11,w12,......,w1n)、(w21,w22,......,w2n)、(w31,w32,......,w3n) and (w41,
w42,......,w4n)。
Characteristic point weight wjiIt is bigger, it characterizes its corresponding characteristic point and is more easily extracted and identifies under i-th kind of state, it is no
Then, characteristic point weight wjiIt is smaller, it characterizes its corresponding characteristic point more difficulty or ease under i-th kind of state and is extracted and identifies, is i.e. this hair
The weight of the characteristic point be easily extracted under the bright corresponding fingerprint state by increase, identified, reduction are difficult to be extracted, know another characteristic
The matching degree numerical value of fingerprint characteristic under the state is adjusted in the weight of point, realization, it is ensured that an accurate matching degree numerical value,
Wherein, j=1,2,3,4；I=1,2 ..., n.
Feature point extraction is carried out in the fingerprint inputted to user, the user to be identified for obtaining being made of multiple characteristic points refers to
After line feature, user fingerprints feature is successively matched with each fingerprint template for including in fingerprint characteristic data library.Specifically
Ground, during carrying out matched with each fingerprint template, firstly, by each characteristic point for including in user fingerprints feature and being somebody's turn to do
Each characteristic point for including in fingerprint template is matched, then can be obtained one and tie up 0-1 vector (a using n1,a2,......,an) indicate
Matching result, wherein
On this basis, the matching degree that user fingerprints feature corresponds under every kind of fingerprint state is calculated using following formula:
To which the matching degree numerical value under normal, dry, wet and 4 kinds of fingerprint states of decortication: p can be respectively obtained1、p2、p3、
p4。
It is comprehensive each after calculating matching degree of the user fingerprints feature corresponding to each fingerprint state in each fingerprint template
Under fingerprint template, for each calculated matching degree of fingerprint state, and the maximum matching degree of numerical value is therefrom selected as user
The Optimum Matching degree of fingerprint characteristic, wherein fingerprint state corresponding to Optimum Matching degree, as most conjunction corresponding to user fingerprints
Suitable state, that is to say, that fingerprint state corresponding to Optimum Matching degree reflects the virtual condition of user fingerprints.
S104: if the Optimum Matching degree reaches the threshold value of setting, fingerprint recognition success.
On the basis of above each step, this step specifically by the Optimum Matching degree of user fingerprints feature with it is preset
Matching threshold is compared, if the Optimum Matching degree reaches the threshold value of setting, characterizes user fingerprints successful match, from
And it can recognize the user.
Wherein, threshold value t may be configured as the real number of satisfaction 0 < t < 1, and practical to identify in scene, excessively high easily lead to of t value is failed to see
Not, therefore generally the numerical value less than 0.2 is set by threshold value t.
It should be noted that division of the application to user fingerprints state, and assigned on this basis for fingerprint template
Respective sets number characteristic point weight, the only exemplary illustration of application scheme, when practical application the application, technical staff can
With the various states more often occurred according to user fingerprints in actual life, to the group number of user fingerprints state and characteristic point weight into
Row is voluntarily divided or is set.
As it can be seen from the above scheme the present invention is based on preset fingerprint characteristic data library to user fingerprints feature to be identified into
Row match cognization, and the Optimum Matching degree of the user fingerprints feature is obtained, reach setting in the Optimum Matching degree later
When threshold value, the user is identified.Wherein, the fingerprint characteristic data library includes at least one fingerprint template, which includes
Second fingerprint characteristic and P group characteristic point weight, the corresponding user fingerprints state of every group of characteristic point weight, and every group of characteristic point weight
For calculating the matching degree numerical value of user fingerprints under its corresponding states.As it can be seen that the present invention is directed to the different shapes of user fingerprints in advance
State has matched the different characteristic point weight of multiple groups for each fingerprint template in database, thus when user fingerprints because dry or
The factors such as decortication can be by using the characteristic point weight group of proper states, to count when the fingerprint characteristic extracted being caused to change
An accurate matching degree is calculated, solves the problems, such as that traditional scheme exists, improves the accuracy of fingerprint recognition.
Embodiment two
The present embodiment is specifically illustrated multiple groups characteristic point weight this preprocessing process obtained under different conditions.Such as
Shown in Fig. 2, the fingerprint identification method may include preprocessing process below:
S101 ': in advance under preset P kind user fingerprints state, carrying out characteristic point Weight Training to the fingerprint template,
It obtains and the one-to-one P group characteristic point weight of the P kind user fingerprints state.
For each fingerprint template in fingerprint characteristic data library, all need to be in advance it according to the number of user fingerprints state
Assign the characteristic point weight of respective sets number.The present embodiment especially by every kind of fingerprint state finish classes and leave school practise fingerprint characteristic extraction,
Identification process, to train characteristic point weight group corresponding to the state, the acquisition of every group of weight is both needed to be individually performed corresponding
Training process.
Hereafter to obtain certain fingerprint template in the dry state for corresponding weight group, to the training process of weight group into
Row description.With reference to Fig. 3, the training process of weight group be may comprise steps of:
S301: setting initial weight and threshold value.
Assuming that the fingerprint template includes n characteristic point altogether, it is expressed as (c1,c2,……,cn), each characteristic point is set first
Initial weight is 1/n, to obtain initial weight group (1/n, 1/n ..., 1/n), concurrently setting matching threshold t is one full
The real number of foot 0 < t < 1, nonrecognition is easy to cause since t value is excessively high, the present embodiment specifically sets one less than 0.2 for t
Numerical value.
S302: user fingerprints are obtained, and extract user fingerprints feature.
Next, obtaining the fingerprint that user is inputted by fingerprint sensor under fingerprint drying regime, and extract its fingerprint spy
Sign.
S303: identification user fingerprints feature, and judge whether to identify successfully.If identified successfully, S304 is thened follow the steps,
Otherwise, it is transferred to step S305.
On this basis, using the threshold value of above-mentioned fingerprint template, weight group and setting, the fingerprint characteristic of user is known
Not, specific identification process can refer to the description of embodiment one, and and will not be described here in detail.
S304: modification weight.
If identified successfully, according to the match condition of user fingerprints feature and fingerprint template, to corresponding in weight group
Characteristic point weight is adjusted, and realizes that calculation formula used by adjusting is as follows:
wi'=δ vi (3)
Wherein, wi' it is modification, characteristic point weight adjusted, wiFor this matching, identification user fingerprints when it is used
Characteristic point weight, viTo calculate wi' a median in the process；δ is normalization factor, and its role is to respectively weigh after keeping adjustment
The sum of value is 1, i.e. ∑iwi'=1.
By above-mentioned training process it is found that if the ith feature point of user fingerprints and the characteristic value c in fingerprint templateiPhase
Matching, then its corresponding weight increases, and otherwise reduces, while all weights remain between section (0,1), and each weight
The sum of be 1.That is the present invention by increasing the weight of characteristic point for being easily extracted, identifying under corresponding fingerprint state, reduction be difficult to by
It extracts, the weight of the characteristic point of identification, the matching degree of fingerprint characteristic under the state is adjusted in realization, it is ensured that can under the state
Obtain an accurate matching degree numerical value.
S305: whether training of judgement process is enough, if enough, terminating training process；Otherwise execution step is gone to
S302, into next round training.
The present invention finally may be used after being trained up by the continuous execution to characteristic point weight iterative modifications process
Show that the state corresponds to required, weight and distributes relatively reasonable characteristic point weight group.
To which in pretreatment stage, the present invention continues through different conditions after the feature that takes the fingerprint forms fingerprint template
Under the training of multiple fingerprint, realization is adjusted the weight of fingerprint template, is capable of forming after convergence and accurately identifying various shapes
The multiple groups weight of state fingerprint.
Embodiment three
In the present embodiment three, with reference to Fig. 4, the fingerprint identification method can with the following steps are included:
S105: if fingerprint recognition success, foundation calculates used matching result when the Optimum Matching is spent, right
Used one group of characteristic point weight when the Optimum Matching is spent is calculated to be adjusted.
I.e. specifically, during carrying out fingerprint recognition using fingerprint template and its corresponding multiple groups characteristic point weight,
If user fingerprints identify successfully, correspondence when successfully identifying can also be adopted according to characteristic matching situation when successfully identifying
Fingerprint template weight group carries out weighed value adjusting, to adapt to the minor change of fingerprint, the specific calculating for adjusting process and use
Formula can refer to the description of embodiment two.
Example IV
In the present embodiment three, with reference to Fig. 5, the fingerprint identification method can with the following steps are included:
S106: if the Optimum Matching degree is not up to the threshold value set, fingerprint recognition failure.
It is smaller in the corresponding Optimum Matching degree of user fingerprints feature, when the threshold value not up to set, characterization user fingerprints with
The match condition of fingerprint template is poor in database, so that fingerprint recognition fails, the nonrecognition user.
Embodiment five
The present embodiment five discloses a kind of fingerprint identification device, and the device and embodiment one to fingerprint disclosed in example IV are known
Other method is corresponding.
Corresponding to embodiment one, with reference to Fig. 6, described device include fingerprint obtain module 100, characteristic extracting module 200,
With identification module 300 and the first result judging module 400.
Fingerprint obtains module 100, for obtaining the fingerprint of user's input.
It is special to obtain the first fingerprint to be identified for carrying out feature point extraction to the fingerprint for characteristic extracting module 200
Sign.
Match cognization module 300, for being based on preset fingerprint characteristic data library to first fingerprint characteristic progress
With identification, and obtain the Optimum Matching degree of first fingerprint characteristic；Wherein, the fingerprint characteristic data library includes at least one
Fingerprint template, each fingerprint template include the second fingerprint characteristic and P group characteristic point weight, every group of characteristic point weight corresponding one
User fingerprints state, and every group of characteristic point weight is used to calculate the matching degree of user fingerprints under its corresponding user fingerprints state
Value, P are the natural number greater than 1.
Wherein, the match cognization module 300 include matching unit, computing unit,
Matching unit is used for fingerprint template each in first fingerprint characteristic, with fingerprint characteristic data library institute
The second fingerprint characteristic for including is matched, and matching result and selection unit are obtained.
Computing unit, each group characteristic point weight for being utilized respectively the fingerprint template add the matching result
Power calculates, and obtains matching degree of first fingerprint characteristic under various user fingerprints states；
Selection unit, for corresponding to a system of each fingerprint template, each user fingerprints state from first fingerprint characteristic
In column matching degree, the maximum matching degree of numerical value is selected, as the Optimum Matching degree of first fingerprint characteristic.
First result judging module 400, for adjudicating recognition result when the Optimum Matching degree reaches the threshold value of setting
For fingerprint recognition success.
Corresponding to embodiment two, with reference to Fig. 7, described device further includes preprocessing module 500, in advance in preset P
Under kind user fingerprints state, characteristic point Weight Training is carried out to the fingerprint template, is obtained and the P kind user fingerprints state one
One corresponding P group characteristic point weight.
Corresponding to embodiment three, with reference to Fig. 8, described device further includes weighed value adjusting module 600, for fingerprint recognition at
When function, according to used matching result when the Optimum Matching is spent is calculated, adopted to calculating when the Optimum Matching is spent
One group of characteristic point weight is adjusted.
Corresponding to embodiment three, with reference to Fig. 9, described device further includes the second result judging module 700, for it is described most
When excellent matching degree is not up to the threshold value set, recognition result is adjudicated as fingerprint recognition failure.
For the fingerprint identification device disclosed in the embodiment of the present invention five, due to itself and embodiment one to example IV public affairs
The fingerprint identification method opened is corresponding, so being described relatively simple, related similarity refers to embodiment one to embodiment
The explanation of fingerprint identification method part in four, and will not be described here in detail.
Embodiment six
The present embodiment discloses a kind of electronic equipment, and the electronic equipment includes the fingerprint identification device as described in embodiment five.
By the fingerprint identification device, the electronic equipment of the present embodiment can relatively accurately identify various states (as just
Often, excessively dry, the excessively wet, states such as peel) under user fingerprints, will not change because of the state of user fingerprints, and
The accuracy rate of the problem of being difficult to, identification is higher, and the user experience is improved.
It should be noted that all the embodiments in this specification are described in a progressive manner, each embodiment weight
Point explanation is the difference from other embodiments, and the same or similar parts between the embodiments can be referred to each other.
For convenience of description, it describes to be divided into various modules when system above or device with function or unit describes respectively.
Certainly, the function of each unit can be realized in the same or multiple software and or hardware when implementing the application.
As seen through the above description of the embodiments, those skilled in the art can be understood that the application can
It realizes by means of software and necessary general hardware platform.Based on this understanding, the technical solution essence of the application
On in other words the part that contributes to existing technology can be embodied in the form of software products, the computer software product
It can store in storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions are used so that a computer equipment
(can be personal computer, server or the network equipment etc.) executes the certain of each embodiment of the application or embodiment
Method described in part.
Finally, it is to be noted that, herein, such as first, second, third and fourth or the like relational terms
It is only used to distinguish one entity or operation from another entity or operation, without necessarily requiring or implying these
There are any actual relationship or orders between entity or operation.Moreover, the terms "include", "comprise" or its is any
Other variants are intended to non-exclusive inclusion, so that including the process, method, article or equipment of a series of elements
Include not only those elements, but also including other elements that are not explicitly listed, or further includes for this process, side
Method, article or the intrinsic element of equipment.In the absence of more restrictions, limited by sentence "including a ..."
Element, it is not excluded that there is also other identical elements in the process, method, article or apparatus that includes the element.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (11)
1. a kind of fingerprint identification method characterized by comprising
Obtain the fingerprint of user's input；
Feature point extraction is carried out to the fingerprint, obtains the first fingerprint characteristic to be identified；
Match cognization is carried out to first fingerprint characteristic based on preset fingerprint characteristic data library, and obtains first fingerprint
The Optimum Matching degree of feature；Wherein, the fingerprint characteristic data library includes at least one fingerprint template, each fingerprint template
Comprising the second fingerprint characteristic and P group characteristic point weight, the corresponding user fingerprints state of every group of characteristic point weight, and every group of characteristic point
Weight is used to calculate the matching degree numerical value of user fingerprints under its corresponding user fingerprints state, and P is the natural number greater than 1, described
Fingerprint state includes at least: at least one of normal, dry, wet and four kinds of states of decortication；
If the Optimum Matching degree reaches the threshold value of setting, fingerprint recognition success；
It is described that match cognization is carried out to first fingerprint characteristic based on preset fingerprint characteristic data library, and obtain described first
The Optimum Matching degree of fingerprint characteristic, comprising:
By the second fingerprint characteristic that each fingerprint template is included in first fingerprint characteristic, with the fingerprint characteristic data library
It is matched, obtains matching result；
The matching result is weighted in each group characteristic point weight for being utilized respectively the fingerprint template, obtains described
Matching degree of one fingerprint characteristic under various user fingerprints states；
From first fingerprint characteristic correspond to each fingerprint template, each user fingerprints state a series of matching degrees in, select
The maximum matching degree of numerical value, as the Optimum Matching degree of first fingerprint characteristic.
2. the method according to claim 1, wherein first fingerprint characteristic, second fingerprint characteristic point
Not Bao Han corresponding number characteristic point, the characteristic point includes destination node, bifurcation, ramification point, isolated point, circling point, short grain.
3. the method according to claim 1, wherein the matching result includes n dimension 0-1 vector (a1,
a2,......,an), n is the natural number greater than 1, wherein
ai=1 indicates the ith feature point in first fingerprint characteristic, with the ith feature point in second fingerprint characteristic
Match；
ai=0 indicates the ith feature point in first fingerprint characteristic, with the ith feature point in second fingerprint characteristic
It mismatches, i=1,2 ..., n.
4. according to the method described in claim 3, it is characterized by further comprising:
If fingerprint recognition success, according to used matching result when the Optimum Matching is spent is calculated, to calculating
Used one group of characteristic point weight when Optimum Matching is spent is stated to be adjusted.
5. the method according to claim 1, wherein further include:
In advance under preset P kind user fingerprints state, to the fingerprint template carry out characteristic point Weight Training, obtain with it is described
The one-to-one P group characteristic point weight of P kind user fingerprints state.
6. the method according to claim 1, wherein further include:
If the Optimum Matching degree is not up to the threshold value set, fingerprint recognition failure.
7. a kind of fingerprint identification device characterized by comprising
Fingerprint obtains module, for obtaining the fingerprint of user's input；
Characteristic extracting module obtains the first fingerprint characteristic to be identified for carrying out feature point extraction to the fingerprint；
Match cognization module, for carrying out match cognization to first fingerprint characteristic based on preset fingerprint characteristic data library,
And obtain the Optimum Matching degree of first fingerprint characteristic；Wherein, the fingerprint characteristic data library includes at least one fingerprint mould
Plate, each fingerprint template include the second fingerprint characteristic and P group characteristic point weight, and the corresponding user of every group of characteristic point weight refers to
Line state, and every group of characteristic point weight is used to calculate the matching degree numerical value of user fingerprints under its corresponding user fingerprints state, P is
Natural number greater than 1, the fingerprint state include at least: at least one of normal, dry, wet and four kinds of states of decortication；
First result judging module, for when the Optimum Matching degree reaches the threshold value of setting, judgement recognition result to be fingerprint
It identifies successfully；
The match cognization module includes:
Matching unit, for being included by each fingerprint template in first fingerprint characteristic, with the fingerprint characteristic data library
The second fingerprint characteristic matched, obtain matching result；
Computing unit, based on each group characteristic point weight by being utilized respectively the fingerprint template is weighted the matching result
It calculates, obtains matching degree of first fingerprint characteristic under various user fingerprints states；
Selection unit, for corresponding to each fingerprint template, a series of of each user fingerprints state from first fingerprint characteristic
With the maximum matching degree of numerical value in degree, is selected, as the Optimum Matching degree of first fingerprint characteristic.
8. device according to claim 7, which is characterized in that further include:
Weighed value adjusting module, in fingerprint recognition success, foundation to calculate used matching when the Optimum Matching is spent
As a result, being adjusted to used one group of characteristic point weight when the Optimum Matching is spent is calculated.
9. device according to claim 7, which is characterized in that further include:
Preprocessing module, under preset P kind user fingerprints state, carrying out characteristic point weight to the fingerprint template in advance
Training, obtains and the one-to-one P group characteristic point weight of the P kind user fingerprints state.
10. device according to claim 7, which is characterized in that further include:
Second result judging module, for when the Optimum Matching degree is not up to the threshold value set, judgement recognition result to be to refer to
Line recognition failures.
11. a kind of fingerprint recognition electronic equipment, which is characterized in that know including the fingerprint as described in claim 7-10 any one
Other device.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510337023.6A CN105654025B (en) | 2015-06-17 | 2015-06-17 | A kind of fingerprint identification method, device and electronic equipment |
| PCT/CN2015/082900 WO2016201731A1 (en) | 2015-06-17 | 2015-06-30 | Fingerprint recognition method and apparatus, and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510337023.6A CN105654025B (en) | 2015-06-17 | 2015-06-17 | A kind of fingerprint identification method, device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105654025A CN105654025A (en) | 2016-06-08 |
| CN105654025B true CN105654025B (en) | 2019-01-25 |
Family
ID=56481588
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510337023.6A Active CN105654025B (en) | 2015-06-17 | 2015-06-17 | A kind of fingerprint identification method, device and electronic equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105654025B (en) |
| WO (1) | WO2016201731A1 (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682618A (en) * | 2016-12-27 | 2017-05-17 | 努比亚技术有限公司 | Fingerprint identification method and mobile terminal |
| CN106843987B (en) * | 2017-02-18 | 2019-10-11 | 珠海格力电器股份有限公司 | Method and device for starting associated application based on fingerprint identification |
| CN106909900A (en) * | 2017-02-27 | 2017-06-30 | 努比亚技术有限公司 | fingerprint identification method and device |
| WO2018213945A1 (en) * | 2017-05-20 | 2018-11-29 | 深圳信炜科技有限公司 | Image sensor and electronic device |
| CN107330388B (en) * | 2017-06-21 | 2020-12-22 | 海信视像科技股份有限公司 | Fingerprint identification processing method and terminal |
| CN107480641B (en) * | 2017-08-16 | 2020-08-25 | 联想(北京)有限公司 | Fingerprint identification method and electronic equipment |
| CN109344594A (en) * | 2018-11-15 | 2019-02-15 | Oppo（重庆）智能科技有限公司 | A kind of method and relevant device based on fingerprint control equipment |
| KR20210157951A (en) | 2020-06-22 | 2021-12-30 | 삼성디스플레이 주식회사 | Fingerprint authentication device, display device including the same, and method of authenticatiing fingerprint |
| CN114915566B (en) * | 2021-01-28 | 2024-05-17 | 腾讯科技（深圳）有限公司 | Application identification method, device, equipment and computer readable storage medium |
| CN114237383B (en) * | 2021-11-09 | 2024-03-12 | 浙江迈联医疗科技有限公司 | Multi-state identification method based on forehead single-lead electroencephalogram signals |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604384A (en) * | 2009-07-17 | 2009-12-16 | 周易 | Individualized fingerprint identification method |
| CN101499130B (en) * | 2008-01-30 | 2012-06-27 | 深圳市普罗巴克科技股份有限公司 | Fingerprint recognition method and fingerprint recognition system |
| CN103065134A (en) * | 2013-01-22 | 2013-04-24 | 江苏超创信息软件发展股份有限公司 | Fingerprint identification device and method with prompt information |
| CN103136517A (en) * | 2013-03-04 | 2013-06-05 | 杭州景联文科技有限公司 | Rolling fingerprint image sequence real-time mosaic method based on key column selection |
| CN103324944A (en) * | 2013-06-26 | 2013-09-25 | 电子科技大学 | Fake fingerprint detecting method based on SVM and sparse representation |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8605962B2 (en) * | 2008-01-21 | 2013-12-10 | Nec Corporation | Pattern matching system, pattern matching method, and pattern matching program |
| CN104050406A (en) * | 2014-07-03 | 2014-09-17 | 南昌欧菲生物识别技术有限公司 | Method and terminal equipment for carrying out authentication through fingerprint combinations |
| CN104376245A (en) * | 2014-10-16 | 2015-02-25 | 上海嘉炽自动化系统工程有限公司 | Operating authority determination method and system for industrial human-machine interface |
| CN104392162A (en) * | 2014-12-08 | 2015-03-04 | 北京大唐智能卡技术有限公司 | Authentication method and smart card |
-
2015
- 2015-06-17 CN CN201510337023.6A patent/CN105654025B/en active Active
- 2015-06-30 WO PCT/CN2015/082900 patent/WO2016201731A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101499130B (en) * | 2008-01-30 | 2012-06-27 | 深圳市普罗巴克科技股份有限公司 | Fingerprint recognition method and fingerprint recognition system |
| CN101604384A (en) * | 2009-07-17 | 2009-12-16 | 周易 | Individualized fingerprint identification method |
| CN103065134A (en) * | 2013-01-22 | 2013-04-24 | 江苏超创信息软件发展股份有限公司 | Fingerprint identification device and method with prompt information |
| CN103136517A (en) * | 2013-03-04 | 2013-06-05 | 杭州景联文科技有限公司 | Rolling fingerprint image sequence real-time mosaic method based on key column selection |
| CN103324944A (en) * | 2013-06-26 | 2013-09-25 | 电子科技大学 | Fake fingerprint detecting method based on SVM and sparse representation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105654025A (en) | 2016-06-08 |
| WO2016201731A1 (en) | 2016-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105654025B (en) | A kind of fingerprint identification method, device and electronic equipment | |
| CN105868695B (en) | A kind of face identification method and system | |
| CN102682302B (en) | Human body posture identification method based on multi-characteristic fusion of key frame | |
| EP3074918B1 (en) | Method and system for face image recognition | |
| CN104239858B (en) | A kind of method and apparatus of face characteristic checking | |
| Yue et al. | Orientation selection using modified FCM for competitive code-based palmprint recognition | |
| CN109766872A (en) | Image recognition method and device | |
| CN111563487A (en) | Dance scoring method based on gesture recognition model and related equipment | |
| JP6928206B2 (en) | Data identification method based on associative clustering deep learning neural network | |
| CN108717425A (en) | A kind of knowledge mapping people entities alignment schemes based on multi-data source | |
| CN103186774A (en) | Semi-supervised learning-based multi-gesture facial expression recognition method | |
| US20110249872A1 (en) | Image template masking | |
| CN106897700B (en) | Single-sample face recognition method and system | |
| Sayed | Biometric Gait Recognition Based on Machine Learning Algorithms. | |
| EP2492826A1 (en) | High-accuracy similarity search system | |
| CN113469002B (en) | Identity recognition method based on blockchain interaction, biological multi-feature recognition and multi-source data fusion | |
| Drishya et al. | Cyberbully image and text detection using convolutional neural networks | |
| CN108197667A (en) | Personal abnormal emotion detection method and device based on dialogue | |
| CN104951760B (en) | A kind of fingerprint classification method based on field of direction minutiae point description | |
| Parvin et al. | A new method for constructing classifier ensembles | |
| CN111124860A (en) | Method for identifying user by using keyboard and mouse data in uncontrollable environment | |
| Nilchiyan et al. | Statistical on-line signature verification using rotation-invariant dynamic descriptors | |
| CN113792683B (en) | Training method, training device, training equipment and training storage medium for text recognition model | |
| CN112270269B (en) | Method and device for evaluating quality of face image | |
| US20200387691A1 (en) | A quick match algorithm for biometric data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |