CN105654025A - Fingerprint identification method, apparatus and electronic equipment thereof - Google Patents
Fingerprint identification method, apparatus and electronic equipment thereof Download PDFInfo
- Publication number
- CN105654025A CN105654025A CN201510337023.6A CN201510337023A CN105654025A CN 105654025 A CN105654025 A CN 105654025A CN 201510337023 A CN201510337023 A CN 201510337023A CN 105654025 A CN105654025 A CN 105654025A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- fingerprint characteristic
- matching degree
- characteristic
- user fingerprints
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000012549 training Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000001035 drying Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 19
- 238000005516 engineering process Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000013011 mating 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 invention discloses a fingerprint identification method, an apparatus and electronic equipment thereof. Based on a preset fingerprint characteristic database, matching and identification are performed on a user fingerprint characteristic to be identified and an optimal matching degree of the user fingerprint characteristic is acquired; and then when the optimal matching degree reaches a set threshold, the user is identified. The fingerprint characteristic database comprises at least one fingerprint template. The fingerprint template comprises P groups of characteristic point weights. Each group of the weights corresponds to a user fingerprint state and each group of the characteristic point weights is used for calculating a matching degree value of a user fingerprint under a corresponding state. In the invention, aiming at different states of the user fingerprint in advance, each fingerprint template in the database matches with the several groups of the different characteristic point weights. Therefore, when the extracted fingerprint characteristic changes because of factors of drying or decrustation and the like, the accurate matching degree can be calculated through using the characteristic point weight groups of an appropriate state so that fingerprint identification accuracy is increased.
Description
Technical field
The invention belongs to the intelligent identification technology field of biological characteristic, particularly relate to a kind of fingerprint identification method, device and electronics.
Background technology
Fingerprint identification technology is most widely used a kind of living things feature recognition technology, and this technology realizes fingerprint recognition based on the various unique point such as the destination node comprised in fingerprint, branch point, branching point, isolated point, ring point, short line. Current many high-end mobile phones have been integrated with fingerprint identification function.
Fingerprint identification technology comprises Finger print characteristic abstract, and two stages of match cognization of fingerprint characteristic. Traditional fingerprinting scheme, store in fingerprint characteristic data storehouse in advance gather such as, (can gather when user's registered fingerprint recognition function), for the fingerprint characteristic as fingerprint template. Thus inputted the fingerprint characteristic of fingerprint extraction user after, the each fingerprint template comprised in the user fingerprints feature of extraction and fingerprint characteristic data storehouse can be compared, if the matching degree of each unique point reaches the threshold value of setting in the fingerprint characteristic of user and a certain fingerprint template, then identify this user.
But, traditional fingerprinting scheme cannot for the different states of user fingerprints, it is effectively identified, such as, when user fingerprints because of the factor such as drying or decortication, and cause some unique point to be difficult to extract, and then when causing the fingerprint characteristic extracted temporarily to change, traditional fingerprinting scheme is utilized easily to produce the problem that cannot effectively identify.
Summary of the invention
In view of this, it is an object of the invention to provide a kind of fingerprint identification method, device and electronics, it is intended to solve traditional fingerprinting scheme and for the different states of user fingerprints, it cannot effectively be identified this problem, promote the accuracy of fingerprint recognition.
For this reason, the present invention's openly following technical scheme:
A kind of fingerprint identification method, comprising:
Obtain the fingerprint of user's input;
Described fingerprint is carried out feature point extraction, obtains the first fingerprint characteristic to be identified;
Based on default fingerprint characteristic data storehouse, described first fingerprint characteristic is carried out match cognization, and obtain the Optimum Matching degree of described first fingerprint characteristic; Wherein, described fingerprint characteristic data storehouse comprises at least one fingerprint template, fingerprint template described in each comprises the 2nd fingerprint characteristic and P stack features point weights, the corresponding user fingerprints state of every stack features point weights, and every stack features point weights are for calculating the matching degree numerical value of user fingerprints under the user fingerprints state of its correspondence, P be greater than 1 natural number;
If described Optimum Matching degree reaches the threshold value of setting, then fingerprint recognition success.
Aforesaid method, it is preferable that, described first fingerprint characteristic, described 2nd fingerprint characteristic comprise the unique point of corresponding number respectively, and described unique point comprises destination node, branch point, branching point, isolated point, ring point, short line.
Aforesaid method, it is preferable that, described based on default fingerprint characteristic data storehouse, described first fingerprint characteristic is carried out match cognization, and obtains the Optimum Matching degree of described first fingerprint characteristic, comprising:
By described first fingerprint characteristic, the 2nd fingerprint characteristic comprised with each fingerprint template in described fingerprint characteristic data storehouse mates, and obtains matching result;
Utilize each stack features point weights of described fingerprint template to be weighted by described matching result respectively, obtain the matching degree of described first fingerprint characteristic under various user fingerprints state;
Correspond to from described first fingerprint characteristic a series of matching degrees of each fingerprint template, each user fingerprints state, select the matching degree that numerical value is maximum, it can be used as the Optimum Matching degree of described first fingerprint characteristic.
Aforesaid method, it is preferable that, described matching result comprises n and ties up 0-1 vector (a1,a2,����,an), n be greater than 1 natural number, wherein,
aiI-th unique point in=1 described first fingerprint characteristic of expression, mates mutually with i-th unique point in described 2nd fingerprint characteristic;
aiI-th unique point in=0 described first fingerprint characteristic of expression, does not mate with i-th unique point in described 2nd fingerprint characteristic, i=1,2 ..., n.
Aforesaid method, it is preferable that, also comprise:
If fingerprint recognition success, then according to calculating the matching result adopted when described Optimum Matching is spent, adjust calculating the stack features point weights adopted when described Optimum Matching is spent.
Aforesaid method, it is preferable that, also comprise:
In advance under default P kind user fingerprints state, described fingerprint template is carried out unique point Weight Training, obtain and described P kind user fingerprints state P stack features point weights one to one.
Aforesaid method, it is preferable that, also comprise:
If described Optimum Matching degree does not reach the threshold value of setting, then fingerprint recognition failure.
A kind of fingerprint identification device, comprising:
Fingerprint acquisition module, for obtaining the fingerprint of user's input;
Characteristic extracting module, for described fingerprint is carried out feature point extraction, obtains the first fingerprint characteristic to be identified;
Match cognization module, for described first fingerprint characteristic being carried out match cognization based on default fingerprint characteristic data storehouse, and obtains the Optimum Matching degree of described first fingerprint characteristic; Wherein, described fingerprint characteristic data storehouse comprises at least one fingerprint template, fingerprint template described in each comprises the 2nd fingerprint characteristic and P stack features point weights, the corresponding user fingerprints state of every stack features point weights, and every stack features point weights are for calculating the matching degree numerical value of user fingerprints under the user fingerprints state of its correspondence, P be greater than 1 natural number;
First result judging module, for when described Optimum Matching degree reaches the threshold value of setting, judgement recognition result is fingerprint recognition success.
Said apparatus, it is preferable that, described match cognization module comprises:
Matching unit, for by described first fingerprint characteristic, the 2nd fingerprint characteristic comprised with each fingerprint template in described fingerprint characteristic data storehouse mates, and obtains matching result;
Calculate unit, for utilizing each stack features point weights of described fingerprint template to be weighted by described matching result respectively, obtain the matching degree of described first fingerprint characteristic under various user fingerprints state;
Choose unit, for, in a series of matching degrees corresponding to each fingerprint template, each user fingerprints state from described first fingerprint characteristic, selecting the matching degree that numerical value is maximum, it can be used as the Optimum Matching degree of described first fingerprint characteristic.
Said apparatus, it is preferable that, also comprise:
Weighed value adjusting module, for when fingerprint recognition success, according to calculating the matching result adopted when described Optimum Matching is spent, adjusting calculating the stack features point weights adopted when described Optimum Matching is spent.
Said apparatus, it is preferable that, also comprise:
Pre-processing module, for, in advance under default P kind user fingerprints state, described fingerprint template being carried out unique point Weight Training, obtains and described P kind user fingerprints state P stack features point weights one to one.
Said apparatus, it is preferable that, also comprise:
2nd result judging module, for when described Optimum Matching degree does not reach the threshold value of setting, judgement recognition result is fingerprint recognition failure.
A kind of electronics, comprises fingerprint identification device as above.
From above scheme, user fingerprints feature to be identified is carried out match cognization based on default fingerprint characteristic data storehouse by the present invention, and obtain the Optimum Matching degree of described user fingerprints feature, afterwards when described Optimum Matching degree reaches the threshold value of setting, identify this user. Wherein, described fingerprint characteristic data storehouse comprises at least one fingerprint template, this fingerprint template comprises the 2nd fingerprint characteristic and P stack features point weights, the corresponding user fingerprints state of every stack features point weights, and every stack features point weights are for calculating the matching degree numerical value of user fingerprints under its corresponding states. Visible, the present invention is in advance for the different states of user fingerprints, for each fingerprint template in database have matched the different unique point weights of many groups, thus work as user fingerprints because of factors such as dry or decortications, cause the fingerprint characteristic extracted when changing, by adopting the unique point weights group of proper states, calculate a matching degree comparatively accurately, solve traditional scheme Problems existing, improve the accuracy of fingerprint recognition.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, it is briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only embodiments of the invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, it is also possible to obtain other accompanying drawing according to the accompanying drawing provided.
Fig. 1 is the schema of the fingerprint identification method embodiment one that the application provides;
Fig. 2 is the schema of the fingerprint identification method embodiment two that the application provides;
Fig. 3 is the weights group training process schematic diagram that the embodiment of the present application two provides;
Fig. 4 is the schema of the fingerprint identification method embodiment three that the application provides;
Fig. 5 is the schema of the fingerprint identification method embodiment four that the application provides;
Fig. 6-Fig. 9 is the structural representation of the fingerprint identification device that the embodiment of the present application five provides.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only the present invention's part embodiment, instead of whole embodiments. Based on the embodiment in the present invention, those of ordinary skill in the art, not making other embodiments all obtained under creative work prerequisite, belong to the scope of protection of the invention.
Embodiment one
The open a kind of fingerprint identification method of the embodiment of the present invention one, this fingerprint identification method can be applicable in the electronics such as smart mobile phone, panel computer, such as, specifically can be applicable in the authenticating user identification of electronics respective service. With reference to figure 1, described method can comprise the following steps:
S101: the fingerprint obtaining user's input.
Specifically can obtain the fingerprint that user is inputted by fingerprint sensing device.
S102: described fingerprint is carried out feature point extraction, obtains the first fingerprint characteristic to be identified.
Fingerprint lines is not continuous print, smooth straight, but the features such as interruption, bifurcated or turnover often occur, the unique point produced by these features provides the confirmation of fingerprint uniqueness, wherein the most typical unique point is destination node and branch point, other unique points also comprise branching point, isolated point, ring point, short line etc., and the parameter of unique point comprises direction, curvature, position.
Thus after fingerprint user inputted carries out feature point extraction, can obtain comprising the user fingerprints feature of the various unique points such as destination node, branch point, branching point, isolated point, ring point, short line.
S103: described first fingerprint characteristic is carried out match cognization based on default fingerprint characteristic data storehouse, and obtain the Optimum Matching degree of described first fingerprint characteristic; Wherein, described fingerprint characteristic data storehouse comprises at least one fingerprint template, fingerprint template described in each comprises the 2nd fingerprint characteristic and P stack features point weights, the corresponding user fingerprints state of every stack features point weights, and every stack features point weights are for calculating the matching degree numerical value of user fingerprints under the user fingerprints state of its correspondence, P be greater than 1 natural number.
In daily life, often there are the situations such as too dry, too moistening or decortication in user fingerprints, some fingerprint characteristic is caused to be difficult to be extracted, and then affect the accuracy of fingerprint recognition, based on this, the present embodiment first by user fingerprints state demarcation be normal, dry, moistening and decortication four kinds of states.
Meanwhile, by learning extraction, the identification situation of fingerprint characteristic under various state, for each fingerprint template in fingerprint characteristic data storehouse gives 4 stack features point weights, the corresponding corresponding user fingerprints state of every stack features point weights.
Assume to comprise n unique point altogether in a fingerprint template, then the fingerprint characteristic that fingerprint template comprises can represent to be a n-dimensional vector comprising n eigenwert: (c1,c2,����,cn), wherein, eigenwert ciFor the concrete expression of i-th unique point in fingerprint template; And corresponding to the normal, dry, moistening of user fingerprints and decortication 4 kinds of states, fingerprint template comprises 4 stack features point weights: (w11,w12,......,w1n)��(w21,w22,......,w2n)��(w31,w32,......,w3n) and (w41,w42,......,w4n)��
Unique point weight wjiMore big, the unique point characterizing its correspondence is more easily extracted under i-th kind of state and identifies, otherwise, unique point weight wjiMore little, the unique point characterizing its correspondence under i-th kind of state more difficulty or ease be extracted and identify, the i.e. weights of unique point of the present invention by being easily extracted under increasing corresponding fingerprint state, identify, reduce the weights of unique point being difficult to be extracted, identifying, it is achieved regulated by the matching degree numerical value of fingerprint characteristic under this state, guarantee a matching degree numerical value more accurately, wherein, j=1,2,3,4;I=1,2 ..., n.
Carry out feature point extraction at fingerprint user inputted, obtain user fingerprints feature being mated with each fingerprint template comprised in fingerprint characteristic data storehouse successively by after the user fingerprints feature to be identified that multiple unique point is formed. Specifically, carrying out in the process mated with each fingerprint template, first, each unique point comprised in user fingerprints feature is being mated with each unique point comprised in this fingerprint template, then can obtain an employing n and tie up 0-1 vector (a1,a2,......,an) matching result that represents, wherein,
On this basis, utilize following formulae discovery user fingerprints feature corresponding to the matching degree under often kind of fingerprint state:
Thus, the matching degree numerical value under normal, dry, moistening and decortication 4 kinds of fingerprint states can be obtained respectively: p1��p2��p3��p4��
After calculating the matching degree of user fingerprints feature corresponding to each fingerprint state in each fingerprint template, under comprehensive each fingerprint template, for the matching degree that each fingerprint state calculates, and therefrom select the Optimum Matching degree of the maximum matching degree of numerical value as user fingerprints feature, wherein, the fingerprint state corresponding to Optimum Matching degree, is the most proper states corresponding to user fingerprints, that is, fingerprint state corresponding to Optimum Matching degree reflects the virtual condition of user fingerprints.
S104: if described Optimum Matching degree reaches the threshold value of setting, then fingerprint recognition success.
On the basis of above each step, the Optimum Matching degree of user fingerprints feature is specifically compared by this step with the threshold value of mating set in advance, if described Optimum Matching degree reaches the threshold value of setting, then the match is successful to characterize user fingerprints, thus, this user can be identified.
Wherein, threshold value t can be set to the real number that meets 0 < t < 1, and in actual identification scene, t value is too high easily causes nonrecognition, and therefore threshold value t is generally set to the numerical value being less than 0.2.
It should be noted that, the application is to the division of user fingerprints state, and the unique point weights of the respective sets number given for fingerprint template on this basis, it is only the exemplary illustration of the application's scheme, during practical application the application, the various states that technician more often can occur according to user fingerprints in actual life, carry out the group number of user fingerprints state and unique point weights dividing voluntarily or setting.
From above scheme, user fingerprints feature to be identified is carried out match cognization based on default fingerprint characteristic data storehouse by the present invention, and obtain the Optimum Matching degree of described user fingerprints feature, afterwards when described Optimum Matching degree reaches the threshold value of setting, identify this user. Wherein, described fingerprint characteristic data storehouse comprises at least one fingerprint template, this fingerprint template comprises the 2nd fingerprint characteristic and P stack features point weights, the corresponding user fingerprints state of every stack features point weights, and every stack features point weights are for calculating the matching degree numerical value of user fingerprints under its corresponding states. Visible, the present invention is in advance for the different states of user fingerprints, for each fingerprint template in database have matched the different unique point weights of many groups, thus work as user fingerprints because of factors such as dry or decortications, cause the fingerprint characteristic extracted when changing, by adopting the unique point weights group of proper states, calculate a matching degree comparatively accurately, solve traditional scheme Problems existing, improve the accuracy of fingerprint recognition.
Embodiment two
Many stack features point this preprocessing process of weights under acquisition different states is specifically described by the present embodiment.As shown in Figure 2, described fingerprint identification method can comprise following preprocessing process:
S101 ': in advance under default P kind user fingerprints state, described fingerprint template is carried out unique point Weight Training, obtains and described P kind user fingerprints state P stack features point weights one to one.
For each fingerprint template in fingerprint characteristic data storehouse, all need in advance according to the unique point weights that the number of user fingerprints state is its imparting respective sets number. The present embodiment practises the extraction of fingerprint characteristic, recognition process especially by finishing classes and leave school often kind of fingerprint state, trains the unique point weights group corresponding to this state, and the acquisition often organizing weights all needs to perform corresponding training process separately.
Hereafter to obtain certain fingerprint template weights group corresponding in the dry state, the training process of weights group is described. With reference to figure 3, the training process of weights group can comprise the following steps:
S301: initial weight and threshold value are set.
Assume that this fingerprint template comprises n unique point altogether, represent for (c1,c2,����,cn), first the initial weight arranging each unique point is 1/n, thus obtain initial weight group (1/n, 1/n, ..., 1/n), the threshold value t of setting coupling simultaneously is a real number meeting 0 < t < 1, easily causing nonrecognition owing to t value is too high, therefore t is specifically set to the numerical value being less than 0.2 by the present embodiment.
S302: obtain user fingerprints, and extract user fingerprints feature.
Next, the fingerprint that under acquisition fingerprint drying regime, user is inputted by fingerprint sensing device, and extract its fingerprint characteristic.
S303: identify user fingerprints feature, and judge whether to identify successfully. If identifying successfully, then perform step S304, otherwise, proceed to step S305.
On this basis, utilize the threshold value of above-mentioned fingerprint template, weights group and setting, the fingerprint characteristic of user identified, concrete recognition process can the description of reference example one, no longer describe in detail herein.
S304: amendment weights.
If identifying successfully, then according to the match condition of user fingerprints feature and fingerprint template, the individual features point weights in weights group are adjusted, it is achieved the calculation formula that adjustment adopts is as follows:
wi'=�� vi(3)
Wherein, wi' it is the unique point weights after amendment, adjustment, wiFor the unique point weights adopted when this coupling, identification user fingerprints, viFor calculating wi' an intermediate value in process; �� is normalizing factor, its role is to keep the rear each weights sum of adjustment to be 1, i.e. ��iwi'=1.
If by above-mentioned training process it will be seen that eigenwert c in i-th unique point of user fingerprints and fingerprint templateiMate mutually, then the weights of its correspondence increase, otherwise reduce, and all weights remain between interval (0,1) simultaneously, and each weights sum is 1. The i.e. weights of unique point of the present invention by being easily extracted under increasing corresponding fingerprint state, identify, reduce the weights of unique point being difficult to be extracted, identifying, realize the matching degree of fingerprint characteristic under this state being regulated, it is ensured that a matching degree numerical value more accurately under this state, can be obtained.
S305: whether training of judgement process is enough, if enough, then terminates training process; Otherwise go to and perform step S302, enter next and take turns training.
The present invention, by the continuous execution to unique point weights iterative modifications process, after carrying out fully training, finally can draw needed for this state correspondence, weights distribution comparatively reasonably unique point weights group.
Thus, in pretreatment stage, the present invention, after the feature that takes the fingerprint forms fingerprint template, continues through the training of the repeatedly fingerprint under different states, realize the weights to fingerprint template to adjust, the many groups weights accurately identifying various state fingerprint after convergence, can be formed.
Embodiment three
In the present embodiment three, with reference to figure 4, described fingerprint identification method can also comprise the following steps:
S105: if fingerprint recognition success, then according to calculating the matching result adopted when described Optimum Matching is spent, adjust calculating the stack features point weights adopted when described Optimum Matching is spent.
Namely specifically, in the process adopting many stack features point weights of fingerprint template and correspondence thereof to carry out fingerprint recognition, if user fingerprints identification success, then can also according to characteristic matching situation when successfully identifying, the fingerprint template weights group adopted corresponding when successfully identifying is carried out weighed value adjusting, to adapt to the subtle change of fingerprint, the calculating formula of concrete adjustment process and employing can the description of reference example two.
Embodiment four
In the present embodiment three, with reference to figure 5, described fingerprint identification method can also comprise the following steps:
S106: if described Optimum Matching degree does not reach the threshold value of setting, then fingerprint recognition failure.
The Optimum Matching degree corresponding in user fingerprints feature is less, and when not reaching the threshold value of setting, the match condition characterizing fingerprint template in user fingerprints and database is poor, thus fingerprint recognition failure, this user of nonrecognition.
Embodiment five
The open a kind of fingerprint identification device of the present embodiment five, fingerprint identification method disclosed in this device and embodiment one to embodiment four is corresponding.
Corresponding to embodiment one, with reference to figure 6, described device comprises fingerprint acquisition module 100, characteristic extracting module 200, match cognization module 300 and the first result judging module 400.
Fingerprint acquisition module 100, for obtaining the fingerprint of user's input.
Characteristic extracting module 200, for described fingerprint is carried out feature point extraction, obtains the first fingerprint characteristic to be identified.
Match cognization module 300, for described first fingerprint characteristic being carried out match cognization based on default fingerprint characteristic data storehouse, and obtains the Optimum Matching degree of described first fingerprint characteristic; Wherein, described fingerprint characteristic data storehouse comprises at least one fingerprint template, fingerprint template described in each comprises the 2nd fingerprint characteristic and P stack features point weights, the corresponding user fingerprints state of every stack features point weights, and every stack features point weights are for calculating the matching degree numerical value of user fingerprints under the user fingerprints state of its correspondence, P be greater than 1 natural number.
Wherein, described match cognization module 300 comprise matching unit, calculate unit,
Matching unit, for by described first fingerprint characteristic, the 2nd fingerprint characteristic comprised with each fingerprint template in described fingerprint characteristic data storehouse mates, obtains matching result and chooses unit.
Calculate unit, for utilizing each stack features point weights of described fingerprint template to be weighted by described matching result respectively, obtain the matching degree of described first fingerprint characteristic under various user fingerprints state;
Choose unit, for, in a series of matching degrees corresponding to each fingerprint template, each user fingerprints state from described first fingerprint characteristic, selecting the matching degree that numerical value is maximum, it can be used as the Optimum Matching degree of described first fingerprint characteristic.
First result judging module 400, for when described Optimum Matching degree reaches the threshold value of setting, judgement recognition result is fingerprint recognition success.
Corresponding to embodiment two, with reference to figure 7, described device also comprises pre-processing module 500, in advance under default P kind user fingerprints state, described fingerprint template is carried out unique point Weight Training, obtains and described P kind user fingerprints state P stack features point weights one to one.
Corresponding to embodiment three, with reference to figure 8, described device also comprises weighed value adjusting module 600, for when fingerprint recognition success, according to calculating the matching result adopted when described Optimum Matching is spent, adjust calculating the stack features point weights adopted when described Optimum Matching is spent.
Corresponding to embodiment three, with reference to figure 9, described device also comprises the 2nd result judging module 700, for when described Optimum Matching degree does not reach the threshold value of setting, judgement recognition result is fingerprint recognition failure.
For fingerprint identification device disclosed in the embodiment of the present invention five, due to its with embodiment one to embodiment four disclosed in fingerprint identification method corresponding, so what describe is fairly simple, relevant similarity refers to the explanation of fingerprint identification method part in embodiment one to embodiment four, no longer describes in detail herein.
Embodiment six
The open a kind of electronics of the present embodiment, described electronics comprises fingerprint identification device as described in embodiment five.
By described fingerprint identification device, the electronics of the present embodiment can more adequately identify various state (as normally, the state such as too dry, too moistening, decortication) under user fingerprints, can not change because of the state of user fingerprints, and the problem being difficult to identification occurs, the accuracy rate identified is higher, improves Consumer's Experience.
It should be noted that, each embodiment in this specification sheets all adopts the mode gone forward one by one to describe, each embodiment emphasis illustrate be the difference with other embodiments, between each embodiment identical similar part mutually see.
For convenience of description, it is divided into various module or unit to describe respectively with function when describing above system or device. Certainly, the function of each unit can be realized in same or multiple software and/or hardware when implementing the application.
As seen through the above description of the embodiments, the technician of this area can be well understood to the application and can realize by the mode that software adds required general hardware platform. Based on such understanding, the technical scheme of the application in essence or says that part prior art contributed can embody with the form of software product, this computer software product can be stored in storage media, such as ROM/RAM, magnetic disc, CD etc., comprise some instructions with so that a computer equipment (can be Personal Computer, server, or the network equipment etc.) perform the method described in some part of each embodiment of the application or embodiment.
Finally, also it should be noted that, herein, the relational terms of such as first, second, third and fourth etc. and so on is only used for separating an entity or operation with another entity or operational zone, and not necessarily requires or imply to there is any this kind of actual relation or sequentially between these entities or operation. And, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, so that comprise the process of a series of key element, method, article or equipment not only comprise those key elements, but also comprise other key elements clearly do not listed, or also comprise the key element intrinsic for this kind of process, method, article or equipment. When not more restrictions, the key element limited by statement " comprising ... ", and be not precluded within process, method, article or the equipment comprising described key element and also there is other identical element.
The above is only the preferred embodiment of the present invention; it is noted that for those skilled in the art, under the premise without departing from the principles of the invention; can also making some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.
Claims (13)
1. a fingerprint identification method, it is characterised in that, comprising:
Obtain the fingerprint of user's input;
Described fingerprint is carried out feature point extraction, obtains the first fingerprint characteristic to be identified;
Based on default fingerprint characteristic data storehouse, described first fingerprint characteristic is carried out match cognization, and obtain the Optimum Matching degree of described first fingerprint characteristic; Wherein, described fingerprint characteristic data storehouse comprises at least one fingerprint template, fingerprint template described in each comprises the 2nd fingerprint characteristic and P stack features point weights, the corresponding user fingerprints state of every stack features point weights, and every stack features point weights are for calculating the matching degree numerical value of user fingerprints under the user fingerprints state of its correspondence, P be greater than 1 natural number;
If described Optimum Matching degree reaches the threshold value of setting, then fingerprint recognition success.
2. method according to claim 1, it is characterised in that, described first fingerprint characteristic, described 2nd fingerprint characteristic comprise the unique point of corresponding number respectively, and described unique point comprises destination node, branch point, branching point, isolated point, ring point, short line.
3. method according to claim 2, it is characterised in that, described based on default fingerprint characteristic data storehouse, described first fingerprint characteristic is carried out match cognization, and obtain the Optimum Matching degree of described first fingerprint characteristic, comprising:
By described first fingerprint characteristic, the 2nd fingerprint characteristic comprised with each fingerprint template in described fingerprint characteristic data storehouse mates, and obtains matching result;
Utilize each stack features point weights of described fingerprint template to be weighted by described matching result respectively, obtain the matching degree of described first fingerprint characteristic under various user fingerprints state;
Correspond to from described first fingerprint characteristic a series of matching degrees of each fingerprint template, each user fingerprints state, select the matching degree that numerical value is maximum, it can be used as the Optimum Matching degree of described first fingerprint characteristic.
4. method according to claim 3, it is characterised in that, described matching result comprises n and ties up 0-1 vector (a1,a2,����,an), n be greater than 1 natural number, wherein,
aiI-th unique point in=1 described first fingerprint characteristic of expression, mates mutually with i-th unique point in described 2nd fingerprint characteristic;
aiI-th unique point in=0 described first fingerprint characteristic of expression, does not mate with i-th unique point in described 2nd fingerprint characteristic, i=1,2 ..., n.
5. method according to claim 4, it is characterised in that, also comprise:
If fingerprint recognition success, then according to calculating the matching result adopted when described Optimum Matching is spent, adjust calculating the stack features point weights adopted when described Optimum Matching is spent.
6. method according to claim 1, it is characterised in that, also comprise:
In advance under default P kind user fingerprints state, described fingerprint template is carried out unique point Weight Training, obtain and described P kind user fingerprints state P stack features point weights one to one.
7. method according to claim 1, it is characterised in that, also comprise:
If described Optimum Matching degree does not reach the threshold value of setting, then fingerprint recognition failure.
8. a fingerprint identification device, it is characterised in that, comprising:
Fingerprint acquisition module, for obtaining the fingerprint of user's input;
Characteristic extracting module, for described fingerprint is carried out feature point extraction, obtains the first fingerprint characteristic to be identified;
Match cognization module, for described first fingerprint characteristic being carried out match cognization based on default fingerprint characteristic data storehouse, and obtains the Optimum Matching degree of described first fingerprint characteristic; Wherein, described fingerprint characteristic data storehouse comprises at least one fingerprint template, fingerprint template described in each comprises the 2nd fingerprint characteristic and P stack features point weights, the corresponding user fingerprints state of every stack features point weights, and every stack features point weights are for calculating the matching degree numerical value of user fingerprints under the user fingerprints state of its correspondence, P be greater than 1 natural number;
First result judging module, for when described Optimum Matching degree reaches the threshold value of setting, judgement recognition result is fingerprint recognition success.
9. device according to claim 8, it is characterised in that, described match cognization module comprises:
Matching unit, for by described first fingerprint characteristic, the 2nd fingerprint characteristic comprised with each fingerprint template in described fingerprint characteristic data storehouse mates, and obtains matching result;
Calculate unit, for utilizing each stack features point weights of described fingerprint template to be weighted by described matching result respectively, obtain the matching degree of described first fingerprint characteristic under various user fingerprints state;
Choose unit, for, in a series of matching degrees corresponding to each fingerprint template, each user fingerprints state from described first fingerprint characteristic, selecting the matching degree that numerical value is maximum, it can be used as the Optimum Matching degree of described first fingerprint characteristic.
10. device according to claim 9, it is characterised in that, also comprise:
Weighed value adjusting module, for when fingerprint recognition success, according to calculating the matching result adopted when described Optimum Matching is spent, adjusting calculating the stack features point weights adopted when described Optimum Matching is spent.
11. devices according to claim 8, it is characterised in that, also comprise:
Pre-processing module, for, in advance under default P kind user fingerprints state, described fingerprint template being carried out unique point Weight Training, obtains and described P kind user fingerprints state P stack features point weights one to one.
12. devices according to claim 8, it is characterised in that, also comprise:
2nd result judging module, for when described Optimum Matching degree does not reach the threshold value of setting, judgement recognition result is fingerprint recognition failure.
13. 1 kinds of electronicss, it is characterised in that, comprise the fingerprint identification device as described in claim 8-12 any one.
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 true CN105654025A (en) | 2016-06-08 |
| CN105654025B 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) |
Cited By (7)
| 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 |
| CN106909900A (en) * | 2017-02-27 | 2017-06-30 | 努比亚技术有限公司 | fingerprint identification method and device |
| CN107330388A (en) * | 2017-06-21 | 2017-11-07 | 青岛海信电器股份有限公司 | Fingerprint recognition processing method and terminal |
| CN107480641A (en) * | 2017-08-16 | 2017-12-15 | 联想(北京)有限公司 | A kind of fingerprint identification method and electronic equipment |
| WO2018213945A1 (en) * | 2017-05-20 | 2018-11-29 | 深圳信炜科技有限公司 | Image sensor and electronic device |
| 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 |
| US11651580B2 (en) | 2020-06-22 | 2023-05-16 | Samsung Display Co., Ltd. | Fingerprint authentication device, display device including the same, and method of authenticating fingerprint |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106843987B (en) * | 2017-02-18 | 2019-10-11 | 珠海格力电器股份有限公司 | Method and device based on fingerprint recognition starting associated application |
| 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 |
|---|---|---|---|---|
| JP4919118B2 (en) * | 2008-01-21 | 2012-04-18 | 日本電気株式会社 | Pattern matching system, pattern matching method, and program for pattern matching |
| 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 |
Cited By (8)
| 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 |
| 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 |
| CN107330388A (en) * | 2017-06-21 | 2017-11-07 | 青岛海信电器股份有限公司 | Fingerprint recognition processing method and terminal |
| 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 |
| CN107480641A (en) * | 2017-08-16 | 2017-12-15 | 联想(北京)有限公司 | A kind of 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 |
| US11651580B2 (en) | 2020-06-22 | 2023-05-16 | Samsung Display Co., Ltd. | Fingerprint authentication device, display device including the same, and method of authenticating fingerprint |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105654025B (en) | 2019-01-25 |
| WO2016201731A1 (en) | 2016-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105654025A (en) | Fingerprint identification method, apparatus and electronic equipment thereof | |
| CN110188641A (en) | Image recognition and the training method of neural network model, device and system | |
| CN107015983A (en) | A kind of method and apparatus for being used in intelligent answer provide knowledge information | |
| CN107591155A (en) | Audio recognition method and device, terminal and computer-readable recording medium | |
| CN105447473A (en) | PCANet-CNN-based arbitrary attitude facial expression recognition method | |
| CN110659573B (en) | Face recognition method and device, electronic equipment and storage medium | |
| CN110781298A (en) | Medicine classification method and device, computer equipment and storage medium | |
| CN109086423A (en) | A kind of text matching technique and device | |
| CN106909625A (en) | A kind of image search method and system based on Siamese networks | |
| CN104820983A (en) | Image matching method | |
| CN103761515A (en) | Human face feature extracting method and device based on LBP | |
| CN110110049A (en) | Service consultation method, apparatus, system, service robot and storage medium | |
| CN114970560A (en) | Dialog intention recognition method and device, storage medium and intelligent device | |
| CN110390107A (en) | Hereafter relationship detection method, device and computer equipment based on artificial intelligence | |
| CN105045927A (en) | Automatic coding method and system for data of labor, materials and machines of construction project | |
| CN107871103A (en) | Face authentication method and device | |
| CN111932396A (en) | Automatic identification method for power distribution network topology network | |
| CN112632248A (en) | Question answering method, device, computer equipment and storage medium | |
| CN111563161A (en) | Sentence recognition method, sentence recognition device and intelligent equipment | |
| CN110119880A (en) | A kind of automatic measure grading method, apparatus, storage medium and terminal device | |
| CN109471927A (en) | A kind of knowledge base and its foundation, answering method and application apparatus | |
| CN104077524A (en) | Training method used for virus identification and virus identification method and device | |
| CN110162769A (en) | Text subject output method and device, storage medium and electronic device | |
| CN110851577A (en) | Knowledge graph expansion method and device in electric power field | |
| CN112738724B (en) | Method, device, equipment and medium for accurately identifying regional target crowd |
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 |