CN109815780A - A kind of high-precision fingerprint identification method and system based on image procossing - Google Patents
A kind of high-precision fingerprint identification method and system based on image procossing Download PDFInfo
- Publication number
- CN109815780A CN109815780A CN201811008189.3A CN201811008189A CN109815780A CN 109815780 A CN109815780 A CN 109815780A CN 201811008189 A CN201811008189 A CN 201811008189A CN 109815780 A CN109815780 A CN 109815780A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- image
- field
- precision
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 58
- 230000002708 enhancing effect Effects 0.000 claims abstract description 31
- 238000000605 extraction Methods 0.000 claims abstract description 19
- 238000006243 chemical reaction Methods 0.000 claims abstract description 12
- 230000007958 sleep Effects 0.000 claims abstract description 9
- 230000001960 triggered effect Effects 0.000 claims abstract description 6
- 238000009499 grossing Methods 0.000 claims description 7
- 230000009514 concussion Effects 0.000 claims description 6
- 230000002093 peripheral effect Effects 0.000 claims description 6
- 230000002787 reinforcement Effects 0.000 claims description 5
- 230000005059 dormancy Effects 0.000 claims 1
- 239000000428 dust Substances 0.000 abstract description 3
- 239000000284 extract Substances 0.000 description 4
- 239000002245 particle Substances 0.000 description 4
- 230000000638 stimulation Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000003709 image segmentation Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000000178 monomer Substances 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Collating Specific Patterns (AREA)
- Image Input (AREA)
Abstract
The invention discloses a kind of high-precision fingerprint identification method and system based on image procossing, this method comprises: behind the fingerprint collecting region of user's finger contacts Fingerprint Lock, fingerprint sensor in fingerprint collecting region, which is triggered, enters working condition by sleep state, and the information in fingerprint of user is acquired by the fingerprint sensor；Information in fingerprint collected is pre-processed to obtain image data, including image dividing processing, image intelligent enhancing processing, binary conversion treatment and the image thinning processing successively carried out；Fingerprint feature information extraction is carried out to the pretreated image data；Data in the fingerprint feature information of extraction and fingerprint base are subjected to matching verifying, and controls the Fingerprint Lock after matching is proved to be successful and opens.It effectively increases to the precision between the living body finger print and original fingerprint having under the complex environments such as dust on dry and wet finger, fingerprint incompleteness and fingerprint sensor, greatly improves the accuracy of fingerprint identification of Fingerprint Lock.
Description
Technical field
The present invention relates to fingerprint identification technology field more particularly to a kind of high-precision fingerprint recognitions based on image procossing
Method and system.
Background technique
In recent years, since internet development is swift and violent, while the convenience and interests for bringing people, gradually it is dissolved into people
Life in, many problems are thus brought, in terms of being mainly reflected in information security.At present in safety-security area, door lock is all
It is very important component part, it is impossible to meet increasingly increased safe demands for traditional identification mode.And
The fast development of fingerprint identification technology in recent years, make it possible Fingerprint Lock field of identity authentication extensive use, and by
In the uniqueness of fingerprint, so that Fingerprint Lock has extensive use value and application value.
Relative to traditional lockset, the application advantage of Fingerprint Lock and its series technique product is extremely obvious.Monomer Fingerprint Lock
Uniqueness substantially increase performance requirement of the user in security protection, and unique physiology subsidiarity of fingerprint, and thoroughly avoiding
The hidden danger lose, be stolen, being replicated, simultaneously because " fingerprint is carried ", easy to use, these big advantages to refer to
Line lock is increasingly accepted by people.Fingerprint identification technology is applied on door-control lock, can more effectively realize door lock product intelligence
Energyization and antitheft target, and the core of fingerprint lock function is then influenced by the accuracy of fingerprint recognition.
In realizing process of the present invention, at least there are the following problems in the prior art for inventor's discovery: in existing security protection
Field carries out one-to-one identification in the fingerprint image to different quality collected under varying environment especially for Fingerprint Lock
When accuracy it is not ideal enough, and for extensive fingerprint base discrimination and search time be far from satisfying and actually answer
Demand, it is also possible to the problem of cannot correctly identifying under such as fingerprint fracture, the unintelligible complex environment of fingerprint occur.
Therefore, currently urgently there is a kind of high-precision fingerprinting scheme.
Summary of the invention
In order to overcome the shortcomings of Related product in the prior art, the present invention proposes a kind of high-precision based on image procossing
Fingerprint identification method and system solve the problems, such as that the accuracy of fingerprint identification of current Fingerprint Lock is low.
The present invention provides a kind of high-precision fingerprint identification method based on image procossing is applied to Fingerprint Lock, comprising:
Behind the fingerprint collecting region of user's finger contacts Fingerprint Lock, the fingerprint sensor in fingerprint collecting region is touched
Hair enters working condition by sleep state, and the information in fingerprint of user is acquired by the fingerprint sensor；
Information in fingerprint collected is pre-processed to obtain image data, including the image segmentation successively carried out
Processing, image intelligent enhancing processing, binary conversion treatment and image thinning processing；
Fingerprint feature information extraction is carried out to the pretreated image data；
Data in the fingerprint feature information of extraction and fingerprint base are subjected to matching verifying, and matching verifying at
The Fingerprint Lock is controlled after function to open.
In some embodiments of the present invention, described image dividing processing specifically includes: calculating separately the fingerprint image
As the fingerprint image image field of information, including intensity field, gradient fields, the field of direction and frequency fields；According to the intensity field and gradient fields
It determines fingerprint object, the fingerprint object is split from background parts；The fingerprint object is successively equalized,
Convergence and smoothing processing.
In some embodiments of the present invention, described image intelligence enhancing processing specifically includes: according to the field of direction and
Frequency fields carry out intelligent enhancing to fingerprint object, wherein on fingerprint ridge direction, to fingerprint in the field of direction in the position
Streakline carries out convergence enhancing, in the vertical direction of fingerprint ridge, carries out concussion to image streakline in frequency fields in the position and adds
By force.
In some embodiments of the present invention, described that fingerprint characteristic letter is carried out to the pretreated image data
Breath is extracted and is specifically included: being traversed each pixel of image, and is judged whether it is triangulation point, central point or endpoint；If it is determined that being
Triangulation point, central point or endpoint then continue to judge whether it meets boundary threshold and whether peripheral direction field changes acutely,
It records the point if meeting to be characterized a little, if being unsatisfactory for ignoring, the collection of the characteristic point is combined into the fingerprint feature information.
In some embodiments of the present invention, the number in the fingerprint feature information by extraction and fingerprint base
It include: that the characteristic point that will be extracted is assembled into topological data structure, and successively carries out triangulation point, center according to matching verifying is carried out
Point, endpoint and topological data structure matching, match if meeting and are proved to be successful.
The high-precision fingerprint recognition system based on image procossing that the present invention also provides a kind of is applied to any of the above-described
The high-precision fingerprint identification method based on image procossing, comprising:
Image capture module, including the fingerprint sensor being arranged in the fingerprint collecting region of Fingerprint Lock, in user's finger
Contact fingerprint collecting region after, the fingerprint sensor in fingerprint collecting region is triggered working condition is entered by sleep state after,
Acquire the information in fingerprint of user；
Image processing module, for being pre-processed to obtain image data to information in fingerprint collected, including according to
Image dividing processing, image intelligent enhancing processing, binary conversion treatment and the image thinning processing of secondary progress, and to described
Pretreated image data carries out fingerprint feature information extraction；
Images match module, for match testing the fingerprint feature information extracted with the data in fingerprint base
Card, and control the Fingerprint Lock after matching is proved to be successful and open.
In some embodiments of the present invention, described image processing module is specifically used for: calculating separately the fingerprint image
As the fingerprint image image field of information, including intensity field, gradient fields, the field of direction and frequency fields；According to the intensity field and gradient fields
It determines fingerprint object, the fingerprint object is split from background parts；The fingerprint object is successively equalized,
Convergence and smoothing processing.
In some embodiments of the present invention, described image processing module is also used to: according to the field of direction and frequency fields
Intelligent enhancing is carried out to fingerprint object, wherein on fingerprint ridge direction, in the field of direction in the position to fingerprint ridge into
Row convergence enhancing, in the vertical direction of fingerprint ridge, carries out concussion reinforcement to image streakline in frequency fields in the position.
In some embodiments of the present invention, described image processing module is also used to: traversing each pixel of image
Point, and judge whether it is triangulation point, central point or endpoint；If it is determined that being triangulation point, central point or endpoint, then continue to judge it
Whether meet boundary threshold and whether peripheral direction field changes acutely, records the point if meeting and be characterized a little, if being unsatisfactory for
Then ignore, the collection of the characteristic point is combined into the fingerprint feature information.
In some embodiments of the present invention, described image matching module is used for: the characteristic point extracted is assembled into
Topological data structure, and triangulation point, central point, endpoint and topological data structure matching are successively carried out, it is matched if meeting
It is proved to be successful.
Compared with prior art, the present invention has the following advantages:
High-precision fingerprint identification method described in the embodiment of the present invention based on image procossing, passes through the fingerprint to acquisition
Image successively carries out pretreatment and fingerprint feature information extracts, and carries out matching verifying in the data in fingerprint base, especially pair
Image dividing processing, image intelligent enhancing processing, binary conversion treatment and the figure that information in fingerprint collected successively carries out
As micronization processes, the work to having under the complex environments such as dust on dry and wet finger, fingerprint incompleteness and fingerprint sensor is effectively increased
Precision between body fingerprint and original fingerprint greatly improves the accuracy of fingerprint identification of Fingerprint Lock.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to use required in embodiment
Attached drawing be briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is the flow diagram of the high-precision fingerprint identification method of the present invention based on image procossing；
Fig. 2 is the original fingerprint image that the present invention obtains；
Fig. 3 is that the present invention carries out image intelligent enhancing treated fingerprint image；
Fig. 4 is that the present invention carries out the fingerprint image after binary conversion treatment；
Fig. 5 is the fingerprint image that the present invention carries out image thinning processing；
Fig. 6 is that the present invention carries out the fingerprint image after fingerprint feature information extraction；
Fig. 7 is the principle assumption diagram of the high-precision fingerprint recognition system of the present invention based on image procossing.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described.Obviously, described embodiment is only
It is a part of the embodiment of the present invention, instead of all the embodiments, following present presently preferred embodiments of the present invention.The present invention
It can realize in many different forms, however it is not limited to embodiment described herein, on the contrary, providing these embodiments
Purpose be to make the disclosure of the present invention more thorough and comprehensive.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff it is identical.Term as used herein in the specification of the present invention is intended merely to retouch
State the purpose of specific embodiment, it is not intended that in the limitation present invention.There is the phrase not in each position in the description
Identical embodiment is centainly each meant, nor the independent or alternative embodiment with other embodiments mutual exclusion.This field skill
Art personnel explicitly and implicitly understand that embodiment described herein can be combined with other embodiments.
As shown in fig.1, the process for the high-precision fingerprint identification method of the present invention based on image procossing is illustrated
Figure, the high-precision fingerprint identification method based on image procossing are applied to Fingerprint Lock, specifically comprise the following steps:
S101: the fingerprint sensor behind the fingerprint collecting region of user's finger contacts Fingerprint Lock, in fingerprint collecting region
It is triggered and working condition is entered by sleep state, the information in fingerprint of user is acquired by the fingerprint sensor.
In embodiments of the present invention, it does not need to observe image in real time during carrying out fingerprint recognition due to Fingerprint Lock, only
Need to carry out the acquisition of information in fingerprint in triggering, therefore, to the of less demanding of fingerprint sensor, general ash
Degree capacitance type sensor, cmos sensor can be met the requirements, and cost is relatively low, meanwhile, the fingerprint sensor can be usually
Sleep state is kept, working condition is entered by sleep state on triggering and carries out the acquisition of information in fingerprint, and is being acquired
Sleep state is reentered after operation, which can be with effectively save energy consumption.
S102: being pre-processed to obtain image data to information in fingerprint collected, including the image successively carried out
Dividing processing, image intelligent enhancing processing, binary conversion treatment and image thinning processing.
In embodiments of the present invention, described image dividing processing specifically include the calculating of fingerprint image image field, image segmentation,
Equalization, convergence and smoothing processing, as Figure 2-Figure 5, Fig. 2 is the original fingerprint image obtained, and Fig. 3 is image intelligent
Enhancing treated fingerprint image, Fig. 4 are the fingerprint image after binary conversion treatment, and Fig. 5 is the fingerprint image of image thinning processing
Picture.
The calculating of the fingerprint image image field refers to the fingerprint image image field for calculating separately the information in fingerprint, including strong
Spend field, gradient fields, the field of direction and frequency fields；Wherein, the intensity field of fingerprint image mainly reacts fingerprint image photon or electricity
The distribution situation of son, is the amount to describe the fingerprint ridge bright-dark degree；The gradient fields of fingerprint image, which are mainly reacted, to be referred to
The streakline of print image field swells situations such as degree；The field of direction of fingerprint image be mainly react fingerprint image image field center and
The trend of (horizontal circle oblique angle) streakline；The frequency fields of fingerprint image then mainly react streakline spacing case.
Described image segmentation refers to the segmentation of the foreground and background of fingerprint image, and the prospect of fingerprint image is fingerprint object
Itself, the embodiment of the present invention determines fingerprint object by calculating the value of intensity field and gradient fields, and by the fingerprint object from
Background parts are split.
The embodiment of the present invention carries out equalization processing to the fingerprint object and refers to through the gray scale field intensity value to pixel
Operation makes fingerprint image all be uniformly distributed equal pixel number in various gray scale field strength, passes through extension pixel gray level
Value range enhances the effect of image overall contrast ratio.
The embodiment of the present invention refers to fingerprint object progress convergence process and smoothing processing passes through Gaussian template respectively
Operation and smooth template operation, can effectively remove the points of contamination formed in image acquisition process, improve the accurate of fingerprint collecting
Degree.
The embodiment of the present invention allows the fingerprint image of acquisition to become more fully apparent by image intelligent enhancing processing, by obtaining
Related enhancement information is taken, removes enhancing image using related enhancement information；Since the Visual intelligent enhancing of the mankind depends on view
Feel acts on the stimulation analysis of " frequency fields " and " field of direction " in " field ", therefore visual object (fingerprint ridge) is advised by " field "
Rule intelligence enhancing.
Specifically, the embodiment of the present invention uses Gabor wavelet filter, it is sensitive to specific direction and frequency stimulation, and
It is sensitive to the specific direction and frequency location stimulation, and be in Wavelet Properties in specific direction and frequency location to the stimulation
Convergence enhancing, it may be assumed that
On fingerprint ridge direction, convergence enhancing is carried out to fingerprint ridge in the field of direction in the position, to make up image
The deficiencies of fracture of middle streakline；In the vertical direction of fingerprint ridge, Gabor function conforms exactly to the identical feature of streakline, can
To carry out concussion reinforcement to image streakline in frequency fields in the position.
It is that gray level image is converted to only two that the embodiment of the present invention, which carries out binary conversion treatment to the information in fingerprint,
The image of kind color value, wherein the black crestal line region of fingerprint image is more black, and white valley line region is whiter, i.e., is made by threshold value white
The valley line area grayscale of color all reaches 255, and the crestal line region of black all reaches 0, and fingerprint ridge object is thus made to become black and white two
Chromatic graph picture, there are two types of methods, including gray scale thresholding split plot design and intelligent binaryzation domain analysis for general Fingerprint Image Binarization
Method, for the embodiment of the present invention using intelligent binaryzation neighbor analysis method, principle is as follows:
The effect that particle in field is necessarily shown up is same, the fingerprint particle in fingerprint ridge field (field of direction)
It is considered as by its effect arrangement, and possesses the property of field.So, in a certain region, in the tangent line of some fingerprint particle
On direction, necessarily similar fingerprint particle.The point in tangential direction that certain is put on ridge i.e. in a certain region still falls within ridge,
Paddy is also similarly.
Its concrete implementation process is as follows: setting f (x0-y0) be the point gray value, the field of direction be o (x0-y0), w is
Contiguous range, H are the sum of tangential pixel value: H=sum (f (x, x/cos (O (x0,y0)))) (x=-w/2...w/2), V is method
To the sum of pixel value, V=sum (f (x, x/sin (O (x0,y0)))) (x=-w/2...w/2), if V > H, the point on ridge,
Conversely, on paddy, in actual operation, it is contemplated that error component, therefore ask gray scale and when, weight is all provided with to every bit,
Error is reduced using average weighted method, in order to accelerate speed, template is made in Gabor function, is fitted with template
Gabor function, and because the operation of two-dimensional rectangle template is also very time-consuming, therefore rectangle template is become to the segment mould of two intersections
Version, does so template operation, operand is with regard to small more；The tangential filtering template obtained after abbreviation is: Hw=1/7 (2,2,3,4,3,
2,2), normal direction filtering template is are as follows: Vw=1/7 (1,1,1,1,1,1,1).The later image of binaryzation is as shown in Figure 4.
The embodiment of the present invention is to the information in fingerprint successively after smooth, intelligence enhancing, binaryzation etc. are handled
Become the black-and-white two color fingerprint image of high quality, but binaryzation fingerprint image is analyzed, handled and extracted feature and also compare
Trouble, because fingerprint characteristic occurs usually in the form of pixel characteristic point, and the streakline width after binaryzation is by more than one picture
Vegetarian refreshments composition, therefore, it is difficult to establish the feature point model of only one point of width, so must be to fingerprint image through streakline image
Abstract processing, therefore, the application handles the fingerprint image further progress image thinning after binaryzation, generates fingerprint image
As skeleton, as shown in figure 5, Fig. 5 is the fingerprint image of image thinning processing.In embodiments of the present invention, image thinning, which is handled, is
By rodlike fingerprint ridge, become that a frame configuration is unchanged, the unchanged thin curve of topological structure, thus by the skeleton of image
Detection is extracted, and establishes feature point model from this；Fingerprint skeleton is the center line of fingerprint ridge, and the skeleton that takes the fingerprint is exactly to mention
The center line (extracting profile then is the edge for extracting image) of print streakline, finally, the black crestal line portion of the finger-print region
Divide and be symmetrically thinned by width, fingerprint ridge is allow to become the line that only remaining width is a pixel.
S103: fingerprint feature information extraction is carried out to the pretreated image data.
Fig. 6 is that the present invention carries out the fingerprint image after fingerprint feature information extraction, as shown in fig. 6, the embodiment of the present invention pair
Extracting to the pretreated image data progress fingerprint feature information is the singular point extracted in image data, and one
, if there is singular point, then surrounding field of direction variation acutely, is also based on the principle to the extraction of image data, described
Singular point includes triangulation point, central point or endpoint.
In embodiments of the present invention, taken the fingerprint image singular point based on Poincare Index, is defined herein
Poincare Index is the sum of the direction change of the point (about 25) on a closed curve.It is sealed along fingerprint orientation
Closed curve is a counterclockwise circle, if the sum of pixel direction change on curve is 0, which is general point；
And if be 1/2, which is central point, and if -1/2, then the corresponding pixel of point is triangulation point；If
The direction Sita of picture element belongs to [0, PI], and discretization rectangular closed length of a curve is L, and length of curve cannot be too small, otherwise
Pseudo- singular point is introduced, then may include greatly multiple singular points very much.
Specifically, the Poincare Index for the picture element (x, y) that closed curve is surrounded is calculated by the following formula:
Poincare (i, j)=1/ (2PI) * Sigma extracts singular point to simplify Poincare Index, and closed curve uses 5x5
Grid calculate Poincare Index value in 5x5 grid, centered on (i, j), it is bent to form closure in the direction of the clock
Line D1,D2,...D12The direction of the point is respectively indicated, 1,12 > of closed curve Poincare (i, j)=Sigma < | Di-D
((i+1) mod12) |, similarly in 3x3 grid, for Poincare (i, j)=Sigma<1,8>| di-d ((i+1) mod8) |
Because there is noise in some fingerprint images, it is understood that there may be pseudo- singular point, in order to eliminate pseudo- singular point, only in 3x3 and
It is just really odd at last when the Poincare value (central point is 1/2 or triangulation point is -1/2) that 5x5 grid calculates is identical
Dissimilarity uses their mean value as final singular point if resulting singular point nearby has singular point.The present invention is implemented
Each pixel of example traversal image, and judge whether it is triangulation point, central point or endpoint；If it is determined that being triangulation point, center
Point or endpoint then continue to judge whether it meets boundary threshold and whether peripheral direction field changes acutely, records if meeting
The point is characterized a little, is ignored if being unsatisfactory for, and the collection of the characteristic point is combined into the fingerprint feature information.
S104: the data in the fingerprint feature information of extraction and fingerprint base are subjected to matching verifying, and are tested in matching
The Fingerprint Lock is controlled after demonstrate,proving successfully to open.
The embodiment of the present invention, which passes through, by the characteristic point extracted is assembled into topological data structure, and successively carry out triangulation point,
Central point, endpoint and topological data structure matching, match if meeting and are proved to be successful.
In embodiments of the present invention, the data in fingerprint base can be pre-stored, be also possible to through cloud data
Synchronous to obtain, under off-line state, the embodiment of the present invention is by number in the fingerprint feature information of extraction and fingerprint base
According to carrying out matching verifying, under presence, then directly obtain the fingerprint feature information of extraction is synchronous with cloud
Data are matched.
High-precision fingerprint identification method described in the embodiment of the present invention based on image procossing, passes through the fingerprint to acquisition
Image successively carries out pretreatment and fingerprint feature information extracts, and carries out matching verifying in the data in fingerprint base, especially pair
Image dividing processing, image intelligent enhancing processing, binary conversion treatment and the figure that information in fingerprint collected successively carries out
As micronization processes, the work to having under the complex environments such as dust on dry and wet finger, fingerprint incompleteness and fingerprint sensor is effectively increased
Precision between body fingerprint and original fingerprint greatly improves the accuracy of fingerprint identification of Fingerprint Lock.
On the basis of the above embodiments, the high-precision fingerprint recognition based on image procossing that the present invention also provides a kind of
System, as shown in fig. 7, be the principle assumption diagram of the high-precision fingerprint recognition system of the present invention based on image procossing, including
Image capture module 100, image processing module 200 and images match module 300.
Described image acquisition module 100 includes the fingerprint sensor that is arranged in the fingerprint collecting region of Fingerprint Lock, with
After family finger contacts fingerprint collecting region, the fingerprint sensor in fingerprint collecting region, which is triggered, enters work by sleep state
After state, the information in fingerprint of user is acquired.
Described image processing module 200 is used to be pre-processed to obtain image data to information in fingerprint collected,
Including image dividing processing, image intelligent enhancing processing, binary conversion treatment and the image thinning processing successively carried out, and
Fingerprint feature information extraction is carried out to the pretreated image data.
Described image processing module 200 carries out image dividing processing specifically: calculates separately the information in fingerprint
Fingerprint image image field, including intensity field, gradient fields, the field of direction and frequency fields；Fingerprint is determined according to the intensity field and gradient fields
Object splits the fingerprint object from background parts；The fingerprint object is successively equalized, restrain and
Smoothing processing.
It is specially according to the field of direction and frequency fields pair that described image processing module 200, which carries out image intelligent enhancing processing,
Fingerprint object carries out intelligent enhancing, wherein on fingerprint ridge direction, carries out in the field of direction in the position to fingerprint ridge
Convergence enhancing, in the vertical direction of fingerprint ridge, carries out concussion reinforcement to image streakline in frequency fields in the position.
Described image processing module 200 carries out fingerprint feature information extraction specifically: each pixel of image is traversed,
And judge whether it is triangulation point, central point or endpoint；If it is determined that being triangulation point, central point or endpoint, then continue whether judge it
Meet boundary threshold and whether peripheral direction field changes acutely, records the point if meeting and be characterized a little, if being unsatisfactory for neglecting
Slightly, the collection of the characteristic point is combined into the fingerprint feature information.
The data in the fingerprint feature information and fingerprint base that described image matching module 300 is used to extract carry out
Matching verifying, and control the Fingerprint Lock after matching is proved to be successful and open；Described image matching module 300 will extract
Characteristic point is assembled into topological data structure, and successively carries out triangulation point, central point, endpoint and topological data structure matching, if
Meet, matching is proved to be successful.
High-precision fingerprint recognition system described in this hair embodiment based on image procossing can be performed above-described embodiment and be mentioned
The high-precision fingerprint identification method based on image procossing supplied, the high-precision fingerprint recognition system tool based on image procossing
The corresponding functional steps of high-precision fingerprint identification method and beneficial effect based on image procossing described in standby above-described embodiment,
Referring specifically to the embodiment of the above-mentioned high-precision fingerprint identification method based on image procossing, the embodiment of the present invention is herein no longer
It repeats.
The content being not described in detail in this specification belongs to the prior art well known to professional and technical personnel in the field.With
Upper is only the embodiment of the present invention, is not intended to limit the scope of the patents of the invention, although with reference to the foregoing embodiments to the present invention into
Detailed description of having gone can still remember aforementioned each specific embodiment for coming for those skilled in the art
The technical solution of load is modified, or carries out equivalence replacement to part of technical characteristic.It is all to utilize description of the invention
The equivalence replacement that content is done directly or indirectly is used in other related technical areas, similarly protects in the invention patent
Within the scope of.
Claims (10)
1. a kind of high-precision fingerprint identification method based on image procossing is applied to Fingerprint Lock characterized by comprising
Behind the fingerprint collecting region of user's finger contacts Fingerprint Lock, the fingerprint sensor in fingerprint collecting region is triggered by sleeping
Dormancy state enters working condition, and the information in fingerprint of user is acquired by the fingerprint sensor；
Information in fingerprint collected is pre-processed to obtain image data, including successively carry out image dividing processing,
Image intelligent enhancing processing, binary conversion treatment and image thinning processing；
Fingerprint feature information extraction is carried out to the pretreated image data；
Data in the fingerprint feature information of extraction and fingerprint base are subjected to matching verifying, and are controlled after matching is proved to be successful
The Fingerprint Lock is made to open.
2. the high-precision fingerprint identification method according to claim 1 based on image procossing, which is characterized in that described image
Dividing processing specifically includes:
Calculate separately the fingerprint image image field of the information in fingerprint, including intensity field, gradient fields, the field of direction and frequency fields；
Fingerprint object is determined according to the intensity field and gradient fields, and the fingerprint object is split from background parts；
The fingerprint object is successively equalized, is restrained and smoothing processing.
3. the high-precision fingerprint identification method according to claim 2 based on image procossing, which is characterized in that described image
Intelligent enhancing processing specifically includes:
Intelligent enhancing is carried out to fingerprint object according to the field of direction and frequency fields, wherein on fingerprint ridge direction, in the position
The field of direction on convergence enhancing is carried out to fingerprint ridge, in the vertical direction of fingerprint ridge, in the position to figure in frequency fields
As streakline carries out concussion reinforcement.
4. the high-precision fingerprint identification method according to claim 1 based on image procossing, which is characterized in that described to institute
Pretreated image data progress fingerprint feature information extraction is stated to specifically include:
Each pixel of image is traversed, and judges whether it is triangulation point, central point or endpoint；
If it is determined that being triangulation point, central point or endpoint, then continue to judge whether it meets boundary threshold and peripheral direction field is
No variation acutely, records the point if meeting and is characterized a little, if being unsatisfactory for ignoring, the collection of the characteristic point is combined into the fingerprint
Characteristic information.
5. the high-precision fingerprint identification method according to claim 4 based on image procossing, which is characterized in that described to mention
The fingerprint feature information taken carries out matching verifying with the data in fingerprint base
The characteristic point extracted is assembled into topological data structure, and successively carries out triangulation point, central point, endpoint and topological Numbers
According to structure matching, matches and be proved to be successful if meeting.
6. a kind of high-precision fingerprint recognition system based on image procossing is applied to any one of the claims 1-5 base
In the high-precision fingerprint identification method of image procossing characterized by comprising
Image capture module, including the fingerprint sensor being arranged in the fingerprint collecting region of Fingerprint Lock, in user's finger contacts
Behind fingerprint collecting region, the fingerprint sensor in fingerprint collecting region is triggered working condition is entered by sleep state after, acquisition
The information in fingerprint of user；
Image processing module obtains image data for being pre-processed to information in fingerprint collected, including successively into
Capable image dividing processing, image intelligent enhancing processing, binary conversion treatment and image thinning processing, and to the pretreatment
Image data afterwards carries out fingerprint feature information extraction；
Images match module, for the data in the fingerprint feature information extracted and fingerprint base to be carried out matching verifying, and
The Fingerprint Lock is controlled after matching is proved to be successful to open.
7. the high-precision fingerprint recognition system according to claim 6 based on image procossing, which is characterized in that described image
Processing module is specifically used for:
Calculate separately the fingerprint image image field of the information in fingerprint, including intensity field, gradient fields, the field of direction and frequency fields；
Fingerprint object is determined according to the intensity field and gradient fields, and the fingerprint object is split from background parts；
The fingerprint object is successively equalized, is restrained and smoothing processing.
8. the high-precision fingerprint recognition system according to claim 7 based on image procossing, which is characterized in that described image
Processing module is also used to:
Intelligent enhancing is carried out to fingerprint object according to the field of direction and frequency fields, wherein on fingerprint ridge direction, in the position
The field of direction on convergence enhancing is carried out to fingerprint ridge, in the vertical direction of fingerprint ridge, in the position to figure in frequency fields
As streakline carries out concussion reinforcement.
9. the high-precision fingerprint recognition system according to claim 6 based on image procossing, which is characterized in that described image
Processing module is also used to:
Each pixel of image is traversed, and judges whether it is triangulation point, central point or endpoint；
If it is determined that being triangulation point, central point or endpoint, then continue to judge whether it meets boundary threshold and peripheral direction field is
No variation acutely, records the point if meeting and is characterized a little, if being unsatisfactory for ignoring, the collection of the characteristic point is combined into the fingerprint
Characteristic information.
10. the high-precision fingerprint recognition system according to claim 9 based on image procossing, which is characterized in that the figure
As matching module is used for:
The characteristic point extracted is assembled into topological data structure, and successively carries out triangulation point, central point, endpoint and topological Numbers
According to structure matching, matches and be proved to be successful if meeting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811008189.3A CN109815780A (en) | 2018-08-31 | 2018-08-31 | A kind of high-precision fingerprint identification method and system based on image procossing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811008189.3A CN109815780A (en) | 2018-08-31 | 2018-08-31 | A kind of high-precision fingerprint identification method and system based on image procossing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109815780A true CN109815780A (en) | 2019-05-28 |
Family
ID=66601524
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811008189.3A Pending CN109815780A (en) | 2018-08-31 | 2018-08-31 | A kind of high-precision fingerprint identification method and system based on image procossing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109815780A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110288732A (en) * | 2019-06-14 | 2019-09-27 | 同济大学 | An integrated device of a dual-chip smart lock fingerprint recognition functional unit |
| CN111882715A (en) * | 2020-07-29 | 2020-11-03 | 金陵科技学院 | Method for intelligent trunk locking system based on ant colony algorithm |
| CN112287732A (en) * | 2019-07-25 | 2021-01-29 | 上海车景网络科技有限公司 | Fingerprint quick comparison method and system |
| CN113408416A (en) * | 2021-06-18 | 2021-09-17 | 展讯通信（上海）有限公司 | Fingerprint frequency estimation method and device and fingerprint information extraction method and device |
| CN113673407A (en) * | 2021-08-16 | 2021-11-19 | 浙江大华技术股份有限公司 | A fingerprint reader and method for transmitting fingerprint information |
| CN114212050A (en) * | 2021-12-15 | 2022-03-22 | 深圳市致知行科技有限公司 | Control method for unlocking vehicle door based on capacitive sensing |
| CN114612943A (en) * | 2022-02-14 | 2022-06-10 | 广西大学 | An operating method of a high-precision touch control device |
| CN118379765A (en) * | 2024-03-26 | 2024-07-23 | 国网黑龙江省电力有限公司齐齐哈尔供电公司 | A network verification method and system based on fingerprint recognition |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6011860A (en) * | 1997-02-12 | 2000-01-04 | Nec Corporation | Small reliable image input apparatus incorporated in finger-print collation system of personal identification |
| CN101727567A (en) * | 2008-10-28 | 2010-06-09 | 苏州中科集成电路设计中心有限公司 | Fingerprint identification method and identification processing device thereof |
| CN103886296A (en) * | 2014-03-25 | 2014-06-25 | 清华大学 | Fingerprint identification method and device based on feedback |
| CN105788048A (en) * | 2016-04-13 | 2016-07-20 | 时建华 | Electronic lock system achieving recognition through fingerprints |
| CN105931324A (en) * | 2016-04-13 | 2016-09-07 | 时建华 | Door lock recognized through fingerprint |
-
2018
- 2018-08-31 CN CN201811008189.3A patent/CN109815780A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6011860A (en) * | 1997-02-12 | 2000-01-04 | Nec Corporation | Small reliable image input apparatus incorporated in finger-print collation system of personal identification |
| CN101727567A (en) * | 2008-10-28 | 2010-06-09 | 苏州中科集成电路设计中心有限公司 | Fingerprint identification method and identification processing device thereof |
| CN103886296A (en) * | 2014-03-25 | 2014-06-25 | 清华大学 | Fingerprint identification method and device based on feedback |
| CN105788048A (en) * | 2016-04-13 | 2016-07-20 | 时建华 | Electronic lock system achieving recognition through fingerprints |
| CN105931324A (en) * | 2016-04-13 | 2016-09-07 | 时建华 | Door lock recognized through fingerprint |
Non-Patent Citations (1)
| Title |
|---|
| LES: ""基于STM 32芯片的指纹识别系统设计与实现"", 《HTTPS://WWW.ELECFANS.COM/EMB/DANPIANJI/20171225607447_A.HTML》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110288732A (en) * | 2019-06-14 | 2019-09-27 | 同济大学 | An integrated device of a dual-chip smart lock fingerprint recognition functional unit |
| CN110288732B (en) * | 2019-06-14 | 2021-04-30 | 同济大学 | A dual-chip smart lock fingerprint recognition functional unit integrated device |
| CN112287732A (en) * | 2019-07-25 | 2021-01-29 | 上海车景网络科技有限公司 | Fingerprint quick comparison method and system |
| CN111882715A (en) * | 2020-07-29 | 2020-11-03 | 金陵科技学院 | Method for intelligent trunk locking system based on ant colony algorithm |
| CN113408416A (en) * | 2021-06-18 | 2021-09-17 | 展讯通信（上海）有限公司 | Fingerprint frequency estimation method and device and fingerprint information extraction method and device |
| CN113673407A (en) * | 2021-08-16 | 2021-11-19 | 浙江大华技术股份有限公司 | A fingerprint reader and method for transmitting fingerprint information |
| CN114212050A (en) * | 2021-12-15 | 2022-03-22 | 深圳市致知行科技有限公司 | Control method for unlocking vehicle door based on capacitive sensing |
| CN114612943A (en) * | 2022-02-14 | 2022-06-10 | 广西大学 | An operating method of a high-precision touch control device |
| CN118379765A (en) * | 2024-03-26 | 2024-07-23 | 国网黑龙江省电力有限公司齐齐哈尔供电公司 | A network verification method and system based on fingerprint recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109815780A (en) | A kind of high-precision fingerprint identification method and system based on image procossing | |
| Cherabit et al. | Circular hough transform for iris localization | |
| Zhang et al. | Fingerprint classification based on extraction and analysis of singularities and pseudo ridges | |
| Ma et al. | Iris recognition based on multichannel Gabor filtering | |
| CN101093538B (en) | A Method of Iris Recognition Based on Wavelet Transform Zero-Crossing Representation | |
| CN100395770C (en) | A Hand Feature Fusion Authentication Method Based on Feature Relationship Measurement | |
| CN102332084B (en) | Identity identification method based on palm print and human face feature extraction | |
| CN110555380A (en) | Finger vein identification method based on Center Loss function | |
| CN107169479A (en) | Intelligent mobile equipment sensitive data means of defence based on fingerprint authentication | |
| Verma et al. | Contactless palmprint verification system using 2-D gabor filter and principal component analysis. | |
| Aleem et al. | Fast and accurate retinal identification system: Using retinal blood vasculature landmarks | |
| Belhadj | Biometric system for identification and authentication | |
| CN106203322A (en) | A kind of identity authorization system based on hand back vein and palmmprint fusion image and method | |
| Jain et al. | Fingerprint recognition | |
| CN109657657A (en) | A kind of mobile phone small area high-precision fingerprint identification method and system based on image procossing | |
| Zhang et al. | A novel iris recognition method based on feature fusion | |
| Gao et al. | On designing a swiniris transformer based iris recognition system | |
| CN103593660B (en) | The palm grain identification method that gradient of intersecting under a kind of invariant feature image encodes | |
| Jaswal et al. | Finger knuckle image based personal authentication using DeepMatching | |
| Jayachandra et al. | Iris Recognition based on Pupil using Canny edge detection and K-Means Algorithm | |
| Moganeshwaran et al. | Fingerprint-fingervein multimodal biometric authentication system in field programmable gate array | |
| Tian et al. | Personal identity recognition approach based on iris pattern | |
| Patel et al. | Fingerprint matching using two methods | |
| Win et al. | An efficient fingerprint matching system for low quality images | |
| Ghouti et al. | Color iris recognition using quaternion phase correlation |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190528 |
|
| RJ01 | Rejection of invention patent application after publication |