CN109886127A - Fingerprint identification method and terminal device - Google Patents
Fingerprint identification method and terminal device Download PDFInfo
- Publication number
- CN109886127A CN109886127A CN201910064710.3A CN201910064710A CN109886127A CN 109886127 A CN109886127 A CN 109886127A CN 201910064710 A CN201910064710 A CN 201910064710A CN 109886127 A CN109886127 A CN 109886127A
- Authority
- CN
- China
- Prior art keywords
- point
- fingerprint
- restored
- fingerprint image
- breaking point
- 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.)
- Pending
Links
Abstract
The present invention is suitable for technical field of biometric identification, provides a kind of fingerprint identification method and terminal device, which comprises obtains fingerprint image to be identified, and the fingerprint image after being refined to fingerprint image to be identified；If there are breaking points for the fingerprint in fingerprint image after refinement, the fingerprint image after refinement is restored, the fingerprint image after being restored；Based on preset convolutional neural networks model, the characteristic value of the fingerprint image after extracting reduction；The Hamming distance value of the characteristic value of fingerprint image after calculating reduction and the characteristic value of the fingerprint image prestored；If Hamming distance value is less than or equal to pre-determined distance value, fingerprint recognition success can improve the accuracy rate of fingerprint recognition to there are the fingerprint of breaking point portraits to carry out reparation reduction.
Description
Technical field
The invention belongs to technical field of biometric identification more particularly to a kind of fingerprint identification methods and terminal device.
Background technique
Since fingerprint has unchangeable property, uniqueness and convenience, fingerprint, which has almost become biological characteristic, to be known
Other synonym.With the development of technology, fingerprint recognition is applied to every field, is especially widely used in mobile phone unlock field.
Existing fingerprint recognition is to compare the finger print data of acquisition with the finger print data prestored, if the two phase
Match, then fingerprint recognition success, if the two mismatches, fingerprint recognition failure.But this fingerprint identification method requires acquisition
Finger print data must be clear, if finger have dust or have it is water stain, even if acquisition be correct finger print data, it is also possible to exist
The case where fingerprint recognition fails causes fingerprint recognition result inaccurate.
Summary of the invention
The embodiment of the present invention provides a kind of fingerprint identification method and terminal device, to solve the finger that the prior art requires acquisition
Line data must be clear, if finger have dust or have it is water stain, even if acquisition be correct finger print data, it is also possible to there is finger
The case where line recognition failures, leads to the problem of fingerprint recognition result inaccuracy.
The first aspect of the embodiment of the present invention provides a kind of fingerprint identification method, comprising:
Fingerprint image to be identified is obtained, and the fingerprint image after being refined to fingerprint image to be identified
Picture；
If there are breaking points for the fingerprint in fingerprint image after refinement, the fingerprint image after refinement is restored, is obtained
Fingerprint image after to reduction；
Based on preset convolutional neural networks model, the characteristic value of the fingerprint image after extracting reduction；
The Hamming distance value of the characteristic value of fingerprint image after calculating reduction and the characteristic value of the fingerprint image prestored；
If Hamming distance value is less than or equal to pre-determined distance value, fingerprint recognition success.
The second aspect of the embodiment of the present invention provides a kind of fingerprint recognition system, comprising:
Fingerprint image refinement module for obtaining fingerprint image to be identified, and carries out fingerprint image to be identified thin
Change the fingerprint image after being refined；
Fingerprint image recovery module, if there are breaking points for the fingerprint in the fingerprint image after refining, after refinement
Fingerprint image restored, the fingerprint image after being restored；
Characteristics extraction module, for being based on preset convolutional neural networks model, the fingerprint image after extracting reduction
Characteristic value；
Hamming distance value computing module, for calculating the characteristic value of the fingerprint image after restoring and the fingerprint image prestored
The Hamming distance value of characteristic value；
Fingerprint identification module, if being less than or equal to pre-determined distance value, fingerprint recognition success for Hamming distance value.
The third aspect of the embodiment of the present invention provides a kind of terminal device, including memory, processor and is stored in
In memory and the computer program that can run on a processor, processor realize following steps when executing computer program:
Fingerprint image to be identified is obtained, and the fingerprint image after being refined to fingerprint image to be identified
Picture；
If there are breaking points for the fingerprint in fingerprint image after refinement, the fingerprint image after refinement is restored, is obtained
Fingerprint image after to reduction；
Based on preset convolutional neural networks model, the characteristic value of the fingerprint image after extracting reduction；
The Hamming distance value of the characteristic value of fingerprint image after calculating reduction and the characteristic value of the fingerprint image prestored；
If Hamming distance value is less than or equal to pre-determined distance value, fingerprint recognition success.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, and fingerprint recognition as described in relation to the first aspect is realized when the computer program is executed by processor
The step of method.
Existing beneficial effect is the embodiment of the present invention compared with prior art: fingerprint recognition provided in an embodiment of the present invention
Method and terminal device by obtaining fingerprint image to be identified, and refine fingerprint image to be identified
Fingerprint image afterwards, if refinement after fingerprint image in fingerprint there are breaking points, the fingerprint image after refinement is gone back
Original, the fingerprint image after being restored are based on preset convolutional neural networks model, the feature of the fingerprint image after extracting reduction
Value, the Hamming distance value of the characteristic value of the fingerprint image after calculating reduction and the characteristic value of the fingerprint image prestored, if Hamming distance
It is less than or equal to pre-determined distance value from value, then fingerprint recognition success, it can be to there are the fingerprint of breaking point portraits repair also
Original improves the accuracy rate of fingerprint recognition.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is a kind of schematic flow diagram for fingerprint identification method that one embodiment of the invention provides；
Fig. 2 is the structural schematic diagram for the convolutional neural networks model that one embodiment of the invention provides；
Fig. 3 be another embodiment of the present invention provides a kind of fingerprint identification method schematic flow diagram；
Fig. 4 is a kind of schematic flow diagram for fingerprint identification method that yet another embodiment of the invention provides；
Fig. 5 is a kind of structural schematic diagram for fingerprint recognition system that one embodiment of the invention provides；
Fig. 6 is the structural schematic diagram for the terminal device that one embodiment of the invention provides.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
Referring to Fig. 1, Fig. 1 is a kind of schematic flow diagram for fingerprint identification method that one embodiment of the invention provides.Such as Fig. 1
Shown, in this embodiment, fingerprint identification method may comprise steps of:
S101: obtaining fingerprint image to be identified, and the finger after being refined to fingerprint image to be identified
Print image.
In embodiments of the present invention, fingerprint image to be identified can be acquired by fingerprint capturer.It can use existing
Fingerprint thinning algorithm fingerprint image to be identified is refined after fingerprint image.
S102: if refinement after fingerprint image in fingerprint there are breaking points, the fingerprint image after refinement is gone back
Original, the fingerprint image after being restored.
In embodiments of the present invention, if having on finger dust or have it is water stain, then will be showed in fingerprint image
There are breaking points for fingerprint.It is to judge fingerprint image with the presence or absence of breaking point by the fingerprint in the fingerprint image after judgement refinement
It is no to need to restore.
If breaking point is not present in the fingerprint in fingerprint image after refinement, without being carried out to the fingerprint image after the refinement
Reduction can be directly based upon preset convolutional neural networks model, the characteristic value of the fingerprint image after extracting refinement.
If there are breaking points for the fingerprint in fingerprint image after refinement, the fingerprint image after refinement is restored, is obtained
Fingerprint image after to reduction.
S103: being based on preset convolutional neural networks model, the characteristic value of the fingerprint image after extracting reduction.
In embodiments of the present invention, characteristic value of the convolutional neural networks model for the image that takes the fingerprint.As shown in Fig. 2,
Convolutional neural networks model includes two 5*5 convolutional layers, three pond layers, 13 residual blocks, two 1*1 convolutional layers and one
Tanh layers.Wherein, it is used to carry out binarization operation for Tanh layers.The size of the input picture of convolutional neural networks model is 64*64,
Export the characteristic pattern of 128 8*8, i.e., total length be 8192 binary feature.
The training process of convolutional neural networks model specifically: sample is inputted in the form of a triple, ternary
Group is three samples, is respectively as follows: and randomly selects a reference sample A；Choosing one, with reference sample to belong to the same finger same
The positive sample B of one characteristic point；Choose one and the inhomogeneous negative sample C of reference sample.Training every time, is input to structure for triple
In the convolutional neural networks model built, three groups of characteristic value f are obtainedA、fBAnd fC, solve error function and with back-propagation method tune
Save entire convolutional neural networks model.Error function are as follows:
Wherein,Indicate the Euclidean distance measurement between reference sample and positive sample,It indicates
Euclidean distance measurement between reference sample and negative sample, thre is preset threshold, (x)+If indicating, x is greater than or equal to zero,
Value is x, if x less than zero, value zero.
S104: the Hamming distance of the characteristic value of the fingerprint image after calculating reduction and the characteristic value of the fingerprint image prestored
Value.
In embodiments of the present invention, by the characteristic value of the fingerprint image after reduction and the characteristic value of fingerprint image that prestores into
Row XOR operation obtains exclusive or as a result, 1 number is the Hamming distance value of the two in exclusive or result.
In one embodiment of the invention, before step S104, can also include:
Based on the convolutional neural networks model, the characteristic value of the fingerprint image prestored is extracted and preserved.
S105: if Hamming distance value is less than or equal to pre-determined distance value, fingerprint recognition success.
Wherein, pre-determined distance value can be configured according to the actual situation.
If Hamming distance value is less than or equal to pre-determined distance value, illustrate that the similarity of the two is higher, then fingerprint recognition success；
If Hamming distance value is greater than pre-determined distance value, illustrate that the similarity of the two is lower, then fingerprint recognition fails.
Since characteristic value length is 8192, characteristic value can be segmented, for example, each corresponding 8*8 is individually calculated the Chinese
Prescribed distance illustrates that the two similarity is lower, no longer needs to calculate remaining if the Hamming distance that corresponding 8*8 is calculated is greater than 3
Characteristic value Hamming distance, can save the time.
It is evidenced from the above discussion that the fingerprint identification method of the embodiment of the present invention, by obtaining fingerprint image to be identified, and
Fingerprint image after being refined to fingerprint image to be identified, if refinement after fingerprint image in fingerprint exist
Breaking point then restores the fingerprint image after refinement, the fingerprint image after being restored, and is based on preset convolutional Neural net
Network model, the characteristic value of the fingerprint image after extracting reduction, the characteristic value of the fingerprint image after calculating reduction and the fingerprint prestored
The Hamming distance value of the characteristic value of image, if Hamming distance value is less than or equal to pre-determined distance value, fingerprint recognition success can
To there are the fingerprint of breaking point portraits to carry out reparation reduction, the accuracy rate of fingerprint recognition is improved.
Referring to Fig. 3, Fig. 3 be another embodiment of the present invention provides a kind of fingerprint identification method schematic flow diagram.?
On the basis of above-described embodiment, " fingerprint image after refinement is restored, the fingerprint image after being restored in step S102
Picture ", details are as follows:
S301: choosing a unreduced breaking point as breaking point to be restored, determine the normal at breaking point to be restored,
And normal and other fingerprint lines are judged with the presence or absence of intersection point, other fingerprint lines are in addition to fingerprint line where breaking point to be restored
Fingerprint lines other than item.
In embodiments of the present invention, a unreduced breaking point is chosen first as breaking point to be restored, is then determined
Normal at breaking point to be restored.
Wherein, the normal at breaking point referred to the breaking point, and with fingerprint lines where the breaking point in the breaking point
The vertical straight line of the tangent line at place.Normal is divided into exterior normal and inter normal.Inter normal, which refers to, is directed toward breaking point place fingerprint lines
The normal in enclosed region, the normal contrary with inter normal are exterior normal.
In step S301, the normal at breaking point to be restored refers to the exterior normal at breaking point to be restored.That is, choosing one
Unreduced breaking point determines the exterior normal at breaking point to be restored as breaking point to be restored, and judges lid exterior normal and its
Its fingerprint lines whether there is intersection point, and other fingerprint lines are in fingerprint image, in addition to fingerprint lines where breaking point to be restored
Fingerprint lines in addition.
S302: if normal is with other fingerprint lines, there are intersection points, and breaking point to be restored is less than or waits at a distance from intersection point
In pre-determined distance, then centered on breaking point to be restored, the fingerprint image after refining is scanned, obtains other non-reduction fracture point sets
It closes, other non-reduction fracture point sets are combined into the set of the unreduced breaking point other than breaking point to be restored.
Wherein, pre-determined distance can be configured according to actual needs, for example, can be set to 10 pixels.
If normal and other fingerprint lines are chosen and are made with breaking point to be restored apart from nearest intersection point there are multiple intersection points
For the corresponding intersection point of the breaking point to be restored.Even there are multiple intersection points with other fingerprint lines for normal, then need to only judge to also
Whether it is less than or equal to pre-determined distance at a distance from former breaking point and the intersection point nearest with its.
If normal and other fingerprint lines there are intersection point, and breaking point to be restored be less than or equal at a distance from intersection point it is default
Distance, the then fingerprint image after scanning refinement, obtains the set of all non-reduction fracture points in addition to breaking point to be restored.
S303: choosing candidate fracture point set from other non-reduction fracture point sets, every in candidate's fracture point set
The distance of the corresponding intersection point of a candidate's breaking point is less than or equal to pre-determined distance, and the corresponding intersection point of candidate breaking point is candidate
Normal and the intersection point of the fingerprint lines other than fingerprint lines where candidate breaking point at breaking point.
In embodiments of the present invention, from other non-reduction fracture point sets choose be less than at a distance from corresponding intersection point or
Equal to the set of the breaking point of pre-determined distance as candidate fracture point set, wherein will in other non-reduction fracture point sets,
With the referred to as candidate breaking point of breaking point for being less than or equal to pre-determined distance at a distance from corresponding intersection point.The corresponding friendship of candidate breaking point
Point is the exterior normal and the intersection point of the fingerprint lines other than fingerprint lines where candidate breaking point at candidate breaking point, if depositing
In multiple intersection points, then choose with candidate's breaking point apart from nearest intersection point as the corresponding intersection point of candidate's breaking point.
S304: being based on preset selection standard, chooses and the matched mesh of breaking point to be restored from candidate's fracture point set
Breaking point is marked, and breaking point to be restored is connect with targeted fractured point curve.
Wherein, targeted fractured point will be known as with the matched breaking point of breaking point to be restored.
In embodiments of the present invention, it is based on preset selection standard, selects a target from candidate's fracture point set
Breaking point, and breaking point to be restored is connect with targeted fractured point curve.
In one embodiment of the invention, preset selection standard includes:
The corresponding intersection point of breaking point to be restored intersection point corresponding with targeted fractured point is in same fingerprint lines；
Be not communicated between breaking point to be restored and targeted fractured point, and breaking point to be restored with targeted fractured point same
Fingerprint lines it is ipsilateral；
The difference of the distance of the corresponding intersection point of the distance and targeted fractured point of the corresponding intersection point of breaking point to be restored
Less than preset difference value；
By the fingerprint line in the fingerprint image after the curve being connected between breaking point to be restored and targeted fractured point and refinement
Item is non-intersecting.
Wherein, be not communicated between breaking point to be restored and targeted fractured point refer to breaking point to be restored and targeted fractured point it
Between any fingerprint lines are not present, both make to be connected.
Preset difference value can be configured according to actual needs, can be by the size of setting preset difference value, to ensure to select
The targeted fractured point taken only one, even select multiple targeted fractured points, then the size of adjustable preset difference value, makes to select
The targeted fractured point taken only one.
By the fingerprint line in the fingerprint image after the curve being connected between breaking point to be restored and targeted fractured point and refinement
Item is non-intersecting, can be by one or two pixel of the curvilinear translation, to remove tangent shape if non-intersecting but just tangent
State.
S305: breaking point to be restored and targeted fractured point are marked as reduction fracture point, and continue to execute selection one
The step of a unreduced breaking point is as breaking point to be restored, until unreduced breaking point is not present.
It is after connecting breaking point to be restored with targeted fractured point curve, breaking point to be restored and targeted fractured point is equal
Labeled as the point of reduction fracture, and continue to restore other non-reduction fracture points, until non-reduction fracture point is not present.
As can be seen from the above description, the fingerprint identification method of the embodiment of the present invention, it is ensured that the accuracy of fingerprint reduction, into
The accuracy of one step raising fingerprint recognition.
Referring to Fig. 4, Fig. 4 is a kind of schematic flow diagram for fingerprint identification method that yet another embodiment of the invention provides.?
On the basis of above-described embodiment, " connecting breaking point to be restored with targeted fractured point curve " in step S304, details are as follows；
S401: the intersection point of the normal at the normal and targeted fractured point at breaking point to be restored is obtained.
In embodiments of the present invention, the normal at breaking point to be restored refers to that inter normal, the normal at targeted fractured point refer to interior
Normal.That is, obtaining the intersection point of the inter normal at the inter normal and targeted fractured point at breaking point to be restored.
S402: being half with the intersection point and the distance between breaking point to be restored or targeted fractured point using the intersection point as the center of circle
Diameter obtains a circle.
In embodiments of the present invention, with the intersection point of the inter normal at the inter normal and targeted fractured point at breaking point to be restored
For the center of circle, with the distance between the intersection point and breaking point to be restored or with the distance between the intersection point and targeted fractured point for radius
Work is justified, and a circle is obtained.
S403: the circular most short circular sliding slopes breaking point to be restored of breaking point to be restored and the interception of targeted fractured point is used
With targeted fractured point.
In embodiments of the present invention, if the circle only passes through breaking point to be restored or targeted fractured point, slightly adjustment should
Circular position makes the circle by breaking point to be restored and targeted fractured point.At this point, breaking point to be restored and targeted fractured
The circle is divided into two parts circular arc by point, and it is disconnected to choose circular sliding slopes breaking point to be restored and target shorter in two parts circular arc
Knick point, that is, the circular most short circular arc for using breaking point to be restored and targeted fractured point to intercept are used as to junction curve, connect to
Reduction fracture point and targeted fractured point.
In one embodiment of the invention, after step S301, can also include:
If intersection point is not present in normal and other fingerprint lines, or, there are intersection points and to be restored for normal and other fingerprint lines
Breaking point is greater than pre-determined distance at a distance from intersection point, then by breaking point to be restored labeled as reduction fracture point, and continues to execute
A step of unreduced breaking point is as breaking point to be restored is chosen, until unreduced breaking point is not present.
In embodiments of the present invention, if intersection point is not present in exterior normal and other fingerprint lines at breaking point to be restored, or,
There are be greater than at a distance from intersection point and breaking point to be restored and the intersection point with other fingerprint lines for exterior normal at breaking point to be restored
Pre-determined distance, then by breaking point to be restored labeled as reduction fracture point, and return step S301 is continued to execute, and reduction is other not
Reduction fracture point, until non-reduction fracture point is not present.
In one embodiment of the invention, after step S303, can also include:
The non-reduction fracture point other than candidate breaking point in other non-reduction fracture point sets is labeled as having gone back
Former breaking point.
In embodiments of the present invention, it after choosing candidate fracture point set in other non-reduction fracture point sets, incites somebody to action
In other non-reduction fracture point sets, the non-reduction fracture point other than candidate breaking point is labeled as reduction fracture point.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Corresponding to fingerprint identification method described in foregoing embodiments, Fig. 5 shows a kind of finger provided in an embodiment of the present invention
The structural schematic diagram of line identifying system.For ease of description, only the parts related to this embodiment are shown.
In one embodiment of the invention, fingerprint recognition system may include:
Fingerprint image refinement module 501 is carried out for obtaining fingerprint image to be identified, and to fingerprint image to be identified
Fingerprint image after being refined；
Fingerprint image recovery module 502, if there are breaking points for the fingerprint in the fingerprint image after refining, to refinement
Fingerprint image afterwards is restored, the fingerprint image after being restored；
Characteristics extraction module 503, for being based on preset convolutional neural networks model, the fingerprint image after extracting reduction
Characteristic value；
Hamming distance value computing module 504, for calculating the characteristic value of the fingerprint image after restoring and the fingerprint image prestored
The Hamming distance value of the characteristic value of picture；
Fingerprint identification module 505, if being less than or equal to pre-determined distance value, fingerprint recognition success for Hamming distance value.
In one embodiment of the invention, fingerprint image recovery module 502 further include:
Intersection point judging unit determines to be restored disconnected for choosing a unreduced breaking point as breaking point to be restored
Normal at knick point, and normal and other fingerprint lines are judged with the presence or absence of intersection point, other fingerprint lines are in addition to be restored disconnected
Fingerprint lines other than fingerprint lines where knick point；
Non- reduction fracture point set acquiring unit, if for normal and other fingerprint lines there are intersection point, and it is to be restored disconnected
Knick point is less than or equal to pre-determined distance at a distance from intersection point, then the fingerprint image centered on breaking point to be restored, after scanning refinement
Picture, obtains other non-reduction fracture point sets, and other non-reduction fracture point sets are combined into not going back other than breaking point to be restored
The set of former breaking point；
Candidate's fracture point set selection unit, for choosing candidate fracture point set from other non-reduction fracture point sets
It closes, the distance of the corresponding intersection point of the candidate breaking point of each of candidate's fracture point set is less than or equal to pre-determined distance, waits
Selecting the corresponding intersection point of breaking point is the normal at candidate breaking point and the fingerprint other than fingerprint lines where candidate breaking point
The intersection point of lines；
Targeted fractured point selection unit, for be based on preset selection standard, from candidate fracture point set in choose with to
The matched targeted fractured point of reduction fracture point, and breaking point to be restored is connect with targeted fractured point curve；
First circulation execution unit, for marking breaking point to be restored and targeted fractured point as reduction fracture point,
And continue to execute and choose a step of unreduced breaking point is as breaking point to be restored, until unreduced fracture is not present
Point.
In one embodiment of the invention, preset selection standard includes:
The corresponding intersection point of breaking point to be restored intersection point corresponding with targeted fractured point is in same fingerprint lines；
Be not communicated between breaking point to be restored and targeted fractured point, and breaking point to be restored with targeted fractured point same
Fingerprint lines it is ipsilateral；
The difference of the distance of the corresponding intersection point of the distance and targeted fractured point of the corresponding intersection point of breaking point to be restored
Less than preset difference value；
By the fingerprint line in the fingerprint image after the curve being connected between breaking point to be restored and targeted fractured point and refinement
Item is non-intersecting.
In one embodiment of the invention, targeted fractured point selection unit can be also used for:
Obtain the intersection point of the normal at the normal and targeted fractured point at breaking point to be restored；
Using the intersection point as the center of circle, with the intersection point and the distance between breaking point to be restored or targeted fractured point for radius, obtain
To a circle；
Use the circular most short circular sliding slopes breaking point to be restored and mesh of breaking point to be restored and the interception of targeted fractured point
Mark breaking point.
In one embodiment of the invention, fingerprint image recovery module 502 further include:
Second circulation execution unit, if intersection point is not present for normal and other fingerprint lines, or, normal and other fingerprints
Lines are there are intersection point and breaking point to be restored is greater than pre-determined distance at a distance from intersection point, then are labeled as having gone back by breaking point to be restored
Former breaking point, and continue to execute and choose a step of unreduced breaking point is as breaking point to be restored, until there is no not
The breaking point of reduction.
In one embodiment of the invention, fingerprint image recovery module 502 further include:
Reduction fracture point marking unit, for by other non-reduction fracture point sets other than candidate breaking point
Non- reduction fracture point labeled as reduction fracture point.
Corresponding to fingerprint identification method described in foregoing embodiments, Fig. 6 shows terminal provided in an embodiment of the present invention and sets
Standby structural schematic diagram.For ease of description, only the parts related to this embodiment are shown.
In the present embodiment, fingerprint recognition program 600 is installed and is run in terminal device 60.The terminal device 60 can be with
It is mobile terminal, palm PC, server etc..The terminal device 60 may include, but be not limited only to, memory 601, processor
602 and display 603.Fig. 6 illustrates only the terminal device 60 with component 601-603, it should be understood that being not required for
Implement all components shown, the implementation that can be substituted is more or less component.
The memory 601 can be the internal storage unit of the terminal device 60 in some embodiments, such as should
The hard disk or memory of terminal device 60.The memory 601 is also possible to the terminal device 60 in further embodiments
The plug-in type hard disk being equipped on External memory equipment, such as the terminal device 60, intelligent memory card (Smart Media
Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card) etc..Further, described to deposit
Reservoir 601 can also both including the terminal device 60 internal storage unit and also including External memory equipment.The memory
601 for storing the application software and Various types of data for being installed on the terminal device 60, such as the fingerprint recognition program 600
Program code etc..The memory 601 can be also used for temporarily storing the data that has exported or will export.
The processor 602 can be a central processing unit (Central Processing in some embodiments
Unit, CPU), microprocessor or other data processing chips, for run the program code stored in the memory 601 or
Handle data, such as execute the fingerprint recognition program 600 etc..
The display 603 can be light-emitting diode display, liquid crystal display, touch control type LCD in some embodiments and show
Device and Organic Light Emitting Diode (Organic Light-Emitting Diode, OLED) touch device etc..The display 603
For being shown in the information handled in the terminal device 60 and for showing visual user interface, such as application menu
Interface, application icon interface etc..The component 601-603 of the terminal device 60 is in communication with each other by system bus.
In the present embodiment, the fingerprint recognition program 600 can be divided into one or more modules, one
Or multiple modules are stored in the memory 601, and (the present embodiment is the processor by one or more processors
602) performed, to complete the present invention.For example, the fingerprint recognition program 600 can be divided into fingerprint image in Fig. 5
As refinement module, fingerprint image recovery module, characteristics extraction module, Hamming distance value computing module and fingerprint identification module.
The so-called module of the present invention is the series of computation machine program instruction section for referring to complete specific function, than program more suitable for retouching
State implementation procedure of the fingerprint recognition program 600 in the terminal device 60.Modules will specifically be introduced by being described below
Function.
Wherein, fingerprint image refinement module, for obtaining fingerprint image to be identified, and to fingerprint image to be identified into
The fingerprint image gone after being refined；
Fingerprint image recovery module, if there are breaking points for the fingerprint in the fingerprint image after refining, after refinement
Fingerprint image restored, the fingerprint image after being restored；
Characteristics extraction module, for being based on preset convolutional neural networks model, the fingerprint image after extracting reduction
Characteristic value；
Hamming distance value computing module, for calculating the characteristic value of the fingerprint image after restoring and the fingerprint image prestored
The Hamming distance value of characteristic value；
Fingerprint identification module, if being less than or equal to pre-determined distance value, fingerprint recognition success for Hamming distance value.
Other modules or unit can refer to the description in embodiment shown in fig. 5, and details are not described herein.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.Each functional unit in embodiment, module can integrate in one processing unit, can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units, it is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.In addition, each function list
Member, the specific name of module are also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed device/terminal device and method, it can be with
It realizes by another way.For example, device described above/terminal device embodiment is only schematical, for example, institute
The division of module or unit is stated, only a kind of logical function partition, there may be another division manner in actual implementation, such as
Multiple units or components can be combined or can be integrated into another system, or some features can be ignored or not executed.Separately
A bit, shown or discussed mutual coupling or direct-coupling or communication connection can be through some interfaces, device
Or the INDIRECT COUPLING or communication connection of unit, it can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium
It may include: any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic that can carry the computer program code
Dish, CD, computer storage, read-only memory (Read-Only Memory, ROM), random access memory (Random
Access Memory, RAM), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that the meter
The content that calculation machine readable medium includes can carry out increase and decrease appropriate according to the requirement made laws in jurisdiction with patent practice,
It such as does not include electric carrier signal and telecommunications according to legislation and patent practice, computer-readable medium in certain jurisdictions
Signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of fingerprint identification method characterized by comprising
Fingerprint image to be identified is obtained, and the fingerprint image after being refined to the fingerprint image to be identified
Picture；
If there are breaking points for the fingerprint in fingerprint image after the refinement, the fingerprint image after the refinement is gone back
Original, the fingerprint image after being restored；
Based on preset convolutional neural networks model, the characteristic value of the fingerprint image after extracting the reduction；
The Hamming distance value of the characteristic value of fingerprint image after calculating the reduction and the characteristic value of the fingerprint image prestored；
If the Hamming distance value is less than or equal to pre-determined distance value, fingerprint recognition success.
2. fingerprint identification method according to claim 1, which is characterized in that the fingerprint image to after the refinement into
Row reduction, the fingerprint image after being restored, comprising:
It chooses a unreduced breaking point and determines the normal at the breaking point to be restored as breaking point to be restored, and sentence
The normal and the other fingerprint lines of breaking are with the presence or absence of intersection point, and other fingerprint lines is in addition to the breaking point institutes to be restored
Fingerprint lines other than fingerprint lines；
If the normal and other fingerprint lines there are intersection point, and the breaking point to be restored be less than at a distance from the intersection point or
Equal to pre-determined distance, then centered on the breaking point to be restored, fingerprint image after scanning the refinement, obtain it is other not also
Original fracture point set, other non-reduction fracture point sets are combined into the unreduced fracture other than the breaking point to be restored
The set of point；
Each of candidate fracture point set, the candidate fracture point set are chosen from other non-reduction fracture point sets
The distance of the corresponding intersection point of candidate breaking point is less than or equal to the pre-determined distance, the corresponding intersection point of candidate's breaking point
For the normal and the intersection point of the fingerprint lines other than fingerprint lines where the candidate breaking point at the candidate breaking point；
Based on preset selection standard, chosen and the matched target of breaking point to be restored from the candidate fracture point set
Breaking point, and the breaking point to be restored is connect with the targeted fractured point curve；
The breaking point to be restored and targeted fractured point are marked as reduction fracture point, and continue to execute the selection
The step of one unreduced breaking point is as breaking point to be restored, until unreduced breaking point is not present.
3. fingerprint identification method according to claim 2, which is characterized in that the preset selection standard includes:
The corresponding intersection point of the breaking point to be restored intersection point corresponding with the targeted fractured point is in same fingerprint lines；
It is not communicated between the breaking point to be restored and targeted fractured point, and the breaking point to be restored and the target are disconnected
Knick point is in the ipsilateral of the same fingerprint lines；
The distance of the corresponding intersection point of the distance and targeted fractured point of the corresponding intersection point of the breaking point to be restored
Difference be less than preset difference value；
It will be in the fingerprint image after the curve being connected between the breaking point to be restored and the targeted fractured point and the refinement
Fingerprint lines it is non-intersecting.
4. fingerprint identification method according to claim 2, which is characterized in that it is described by the breaking point to be restored with it is described
The connection of targeted fractured point curve, comprising:
Obtain the intersection point of the normal at the normal and the targeted fractured point at the breaking point to be restored；
It is half with the intersection point and the distance between the breaking point to be restored or targeted fractured point using the intersection point as the center of circle
Diameter obtains a circle；
To also described in the circular most short circular sliding slopes intercepted using the breaking point to be restored and the targeted fractured point
Former breaking point and targeted fractured point.
5. fingerprint identification method according to claim 2, which is characterized in that in the judgement normal and other fingerprints
Lines whether there is after intersection point, further includes:
If intersection point is not present in the normal and other fingerprint lines, or, the normal and other fingerprint lines exist
Intersection point and the breaking point to be restored are greater than the pre-determined distance at a distance from the intersection point, then by the breaking point mark to be restored
It is denoted as reduction fracture point, and continues to execute the step of one unreduced breaking point of the selection is as breaking point to be restored,
Until unreduced breaking point is not present.
6. fingerprint identification method according to claim 2, which is characterized in that described from other non-reduction fracture points
Candidate be broken after point set is chosen in set, further includes:
The non-reduction fracture point other than the candidate breaking point in other non-reduction fracture point sets is labeled as
Reduction fracture point.
7. a kind of fingerprint recognition system characterized by comprising
Fingerprint image refinement module for obtaining fingerprint image to be identified, and carries out the fingerprint image to be identified thin
Change the fingerprint image after being refined；
Fingerprint image recovery module, if there are breaking points for the fingerprint in the fingerprint image after the refinement, to described thin
Fingerprint image after change is restored, the fingerprint image after being restored；
Characteristics extraction module is used to be based on preset convolutional neural networks model, the fingerprint image after extracting the reduction
Characteristic value；
Hamming distance value computing module, for calculating the characteristic value of the fingerprint image after the reduction and the fingerprint image prestored
The Hamming distance value of characteristic value；
Fingerprint identification module, if being less than or equal to pre-determined distance value, fingerprint recognition success for the Hamming distance value.
8. a kind of terminal device, which is characterized in that in the memory and can be in institute including memory, processor and storage
The computer program run on processor is stated, the processor realizes following steps when executing the computer program:
Fingerprint image to be identified is obtained, and the fingerprint image after being refined to the fingerprint image to be identified
Picture；
If there are breaking points for the fingerprint in fingerprint image after the refinement, the fingerprint image after the refinement is gone back
Original, the fingerprint image after being restored；
Based on preset convolutional neural networks model, the characteristic value of the fingerprint image after extracting the reduction；
The Hamming distance value of the characteristic value of fingerprint image after calculating the reduction and the characteristic value of the fingerprint image prestored；
If the Hamming distance value is less than or equal to pre-determined distance value, fingerprint recognition success.
9. terminal device according to claim 8, which is characterized in that the fingerprint image to after the refinement is gone back
Original, the fingerprint image after being restored, comprising:
It chooses a unreduced breaking point and determines the normal at the breaking point to be restored as breaking point to be restored, and sentence
The normal and the other fingerprint lines of breaking are with the presence or absence of intersection point, and other fingerprint lines is in addition to the breaking point institutes to be restored
Fingerprint lines other than fingerprint lines；
If the normal and other fingerprint lines there are intersection point, and the breaking point to be restored be less than at a distance from the intersection point or
Equal to pre-determined distance, then centered on the breaking point to be restored, fingerprint image after scanning the refinement, obtain it is other not also
Original fracture point set, other non-reduction fracture point sets are combined into the unreduced fracture other than the breaking point to be restored
The set of point；
Each of candidate fracture point set, the candidate fracture point set are chosen from other non-reduction fracture point sets
The distance of the corresponding intersection point of candidate breaking point is less than or equal to the pre-determined distance, the corresponding intersection point of candidate's breaking point
For the normal and the intersection point of the fingerprint lines other than fingerprint lines where the candidate breaking point at the candidate breaking point；
Based on preset selection standard, chosen and the matched target of breaking point to be restored from the candidate fracture point set
Breaking point, and the breaking point to be restored is connect with the targeted fractured point curve；
The breaking point to be restored and targeted fractured point are marked as reduction fracture point, and continue to execute the selection
The step of one unreduced breaking point is as breaking point to be restored, until unreduced breaking point is not present.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In the step of realization fingerprint identification method as described in any one of claim 1 to 6 when the computer program is executed by processor
Suddenly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910064710.3A CN109886127A (en) | 2019-01-23 | 2019-01-23 | Fingerprint identification method and terminal device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910064710.3A CN109886127A (en) | 2019-01-23 | 2019-01-23 | Fingerprint identification method and terminal device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109886127A true CN109886127A (en) | 2019-06-14 |
Family
ID=66926651
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910064710.3A Pending CN109886127A (en) | 2019-01-23 | 2019-01-23 | Fingerprint identification method and terminal device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109886127A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889429A (en) * | 2019-10-22 | 2020-03-17 | 杭州效准智能科技有限公司 | Intelligent dish matching identification method based on deep learning |
| CN111753725A (en) * | 2020-06-24 | 2020-10-09 | 上海依图网络科技有限公司 | Fingerprint repairing method and device |
| CN112991232A (en) * | 2021-04-30 | 2021-06-18 | 深圳阜时科技有限公司 | Training method of fingerprint image restoration model, fingerprint identification method and terminal equipment |
| CN113312946A (en) * | 2020-02-27 | 2021-08-27 | 敦泰电子（深圳）有限公司 | Fingerprint image feature extraction method and device and computer readable storage medium |
| CN116311389A (en) * | 2022-08-18 | 2023-06-23 | 荣耀终端有限公司 | Fingerprint identification method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1421815A (en) * | 2001-11-29 | 2003-06-04 | 田捷 | Fingerprint image enhancement method based on knowledge |
| CN106778457A (en) * | 2015-12-11 | 2017-05-31 | 深圳市汇顶科技股份有限公司 | The fingerprint identification method and system of fingerprint recognition rate can be improved |
| CN107491727A (en) * | 2017-07-07 | 2017-12-19 | 广东欧珀移动通信有限公司 | Fingerprint identification method, device and terminal |
| US20180225495A1 (en) * | 2017-02-06 | 2018-08-09 | Fingerprint Cards Ab | Method for authenticating a finger of a user of an electronic device |
-
2019
- 2019-01-23 CN CN201910064710.3A patent/CN109886127A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1421815A (en) * | 2001-11-29 | 2003-06-04 | 田捷 | Fingerprint image enhancement method based on knowledge |
| CN106778457A (en) * | 2015-12-11 | 2017-05-31 | 深圳市汇顶科技股份有限公司 | The fingerprint identification method and system of fingerprint recognition rate can be improved |
| US20180225495A1 (en) * | 2017-02-06 | 2018-08-09 | Fingerprint Cards Ab | Method for authenticating a finger of a user of an electronic device |
| CN107491727A (en) * | 2017-07-07 | 2017-12-19 | 广东欧珀移动通信有限公司 | Fingerprint identification method, device and terminal |
Non-Patent Citations (1)
| Title |
|---|
| 陈沛华 等: "一种修复细化指纹图像中断裂线条的新方法", 《通信学报》, vol. 25, no. 6, pages 115 - 119 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889429A (en) * | 2019-10-22 | 2020-03-17 | 杭州效准智能科技有限公司 | Intelligent dish matching identification method based on deep learning |
| CN113312946A (en) * | 2020-02-27 | 2021-08-27 | 敦泰电子（深圳）有限公司 | Fingerprint image feature extraction method and device and computer readable storage medium |
| CN111753725A (en) * | 2020-06-24 | 2020-10-09 | 上海依图网络科技有限公司 | Fingerprint repairing method and device |
| CN112991232A (en) * | 2021-04-30 | 2021-06-18 | 深圳阜时科技有限公司 | Training method of fingerprint image restoration model, fingerprint identification method and terminal equipment |
| CN112991232B (en) * | 2021-04-30 | 2021-07-23 | 深圳阜时科技有限公司 | Training method of fingerprint image restoration model, fingerprint identification method and terminal equipment |
| CN116311389A (en) * | 2022-08-18 | 2023-06-23 | 荣耀终端有限公司 | Fingerprint identification method and device |
| CN116311389B (en) * | 2022-08-18 | 2023-12-12 | 荣耀终端有限公司 | Fingerprint identification method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109886127A (en) | Fingerprint identification method and terminal device | |
| CN107766809B (en) | Electronic device, bill information identification method, and computer-readable storage medium | |
| CN107274543B (en) | A kind of recognition methods of bank note, device, terminal device and computer storage medium | |
| CN107393118B (en) | A kind of recognition methods of bank note, device, terminal device and computer storage medium | |
| CN101149804A (en) | Self-adaptive hand-written discrimination system and method | |
| CN109800559B (en) | Method and device for generating slider verification code, computer equipment and storage medium | |
| CN107958230A (en) | Facial expression recognizing method and device | |
| CN110956263A (en) | Construction method of binarization neural network, storage medium and terminal equipment | |
| CN108241857A (en) | Face identification method and Related product | |
| CN112132812B (en) | Certificate verification method and device, electronic equipment and medium | |
| CN109918984A (en) | Insurance policy number identification method, device, electronic equipment and storage medium | |
| CN109302541A (en) | Electronic device, distribution method of attending a banquet and computer readable storage medium | |
| US20210390299A1 (en) | Techniques to determine document recognition errors | |
| CN109117704A (en) | Pressure identification device and electronic device including Pressure identification device | |
| CN110347789A (en) | Text is intended to intelligent method for classifying, device and computer readable storage medium | |
| CN110175500B (en) | Finger vein comparison method, device, computer equipment and storage medium | |
| CN108399025A (en) | A kind of method, apparatus and terminal device for correcting identification deviation | |
| CN111492407B (en) | System and method for map beautification | |
| CN107077617B (en) | Fingerprint extraction method and device | |
| CN104486475A (en) | One-key dialing method and device | |
| CN107679222A (en) | Image processing method, mobile terminal and computer-readable recording medium | |
| CN112036316A (en) | Finger vein identification method and device, electronic equipment and readable storage medium | |
| CN111753719A (en) | Fingerprint identification method and device | |
| CN109146495A (en) | Fast and safely start the method, apparatus and terminal device of payment | |
| CN107272989B (en) | Using starting method, apparatus and terminal device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |