CN105868731A - Binocular iris characteristic obtaining method, binocular iris characteristic obtaining device, identity identification method and identity identification system - Google Patents
Binocular iris characteristic obtaining method, binocular iris characteristic obtaining device, identity identification method and identity identification system Download PDFInfo
- Publication number
- CN105868731A CN105868731A CN201610236748.0A CN201610236748A CN105868731A CN 105868731 A CN105868731 A CN 105868731A CN 201610236748 A CN201610236748 A CN 201610236748A CN 105868731 A CN105868731 A CN 105868731A
- Authority
- CN
- China
- Prior art keywords
- iris
- binocular
- image
- texture image
- feature
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/193—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/197—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Ophthalmology & Optometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a binocular iris characteristic obtaining method, a binocular iris characteristic obtaining device, an identity identification method and an identity identification system. The binocular iris characteristic obtaining method comprises the steps of respectively determining boundaries of a left-eye iris and a right-eye iris in an image; sampling a series of concentric circles between the left-eye iris boundary and the right-eye iris boundary, and acquiring a left-eye iris pattern image and a right-eye iris pattern image; fusing the left-eye iris pattern image and the right-eye iris pattern image for obtaining one image, thereby obtaining a binocular pattern image; performing partial characteristic extraction on the binocular pattern image and coding the extracted information, thereby obtaining a binocular iris characteristic. The amount of information contained in the binocular iris characteristic is two times of that of information contained in a single-eye iris characteristic, thereby effectively improving identification safety and improving difficulty in breaking iris verification when the binocular iris characteristic is applied in identity identification.
Description
Technical field
The invention belongs to field of information security technology, obtain particularly to a kind of binocular iris feature
Method and device, auth method and system.
Background technology
Owing to traditional identity identifying method such as relies on key, certificate to carry out authentication existence
The practical situation that people separates with thing, it is difficult to ensure that the effectiveness of authentication, cannot meet
Cybertimes and the commonly used occasion of computer are to the security requirement of authentication and convenience
Requirement, the unseparated problem of thing of people in the urgent need to address and reference's identity, i.e. testimony of a witness unification
Problem.Face, iris, fingerprint etc. are the inseparable parts of human body, if using these
Biological characteristic represents the identity of people, then meet the requirement of testimony of a witness unification, also has individual simultaneously
Body diversity and long-time stability, therefore, living things feature recognition has become following field of identity authentication
Main authentication mode.There is not people and separate with certificate in identity identifying method based on biological characteristic
Situation, do not exist and lose and the phenomenon forgotten, add by the difficulty of other people personation, at silver
Row, aviation boarding, online login, information security etc. require that high occasion receives much concern, but
Technology is the most immature at present, applies the most limited, becomes the hot issue of research in recent years.Rainbow
Film is positioned at eyes important on human body, is the annular section between pupil and sclera,
Texture is formed has randomness, and the iris texture of different people exists individual variation, any two eyes
The probability that the iris of eyeball is similar is almost nil, so iris authentication can become a kind of effectively
Identity identifying method.
But, owing to being affected by ambient lighting and image sensor performance, existing monocular rainbow
Film detecting device obtain iris image unsatisfactory, cause the texture of iris to thicken or
Detailed information disappears, and this have impact on effective extraction of iris texture characteristic, adds different iris
Similar probability, makes iris diagnostic device the phenomenon of erroneous judgement easily occur.Existing iris stricture of vagina
Reason feature extraction and expression are easily subject to the impact of iris annulus original position and cause iris feature phase place
Inconsistent problem, this brings difficulty also to the comparison of iris feature.
Summary of the invention
Present invention aim at, it is provided that testing of a kind of accurate and effective and the high binocular iris of safety
Card method and system.
In order to achieve the above object, the invention provides a kind of binocular iris feature acquisition methods and
Device, auth method and system.
First aspect, the present invention provides a kind of binocular iris feature acquisition methods, including:
In image according to acquisition human eye binocular iris, the gray value of each pixel determines described image
Middle pupil of left eye and the position of pupil of right eye, further according to pupil of left eye and the position of pupil of right eye
The gray value of the image of neighboring area, determines the iris inner and outer boundary of left eye and right eye；
A series of concentric circulars between described iris of left eye and iris of right eye inner and outer boundary are adopted
Sample, it is thus achieved that iris of left eye texture image and iris of right eye texture image, wherein, described iris
Texture image, in described left eye or right eye between iris inner and outer boundary a series of concentric circulars enter
The image of the some composition after row collection；
Described iris of left eye texture image and iris of right eye texture image are merged, obtains
Binocular texture image；
Described binocular texture image is carried out local shape factor and the information extracted is compiled
Code, it is thus achieved that the feature of binocular iris.
Preferably, described between iris of left eye and iris of right eye inner and outer boundary a series of with one heart
Circle is sampled, it is thus achieved that the step bag of iris of left eye texture image and iris of right eye texture image
Include:
By oculopupillary for left and right center line, using the line of this center as zero angle
Original position；
From the beginning of zero angle original position, between iris of left eye and iris of right eye inner and outer boundary
A series of concentric circulars are circumferentially sampled, it is thus achieved that iris of left eye texture image and iris of right eye
Texture image.
Preferably, described iris of left eye texture image and iris of right eye texture image are merged one
Rising, the step obtaining binocular texture image includes:
Using the gray value of the every one-row pixels in described iris of left eye texture image as binocular texture
The gray value of the pixel of the odd-numbered line of image；
Using the gray value of the every one-row pixels in described iris of right eye texture image as binocular texture
The gray value of the pixel of the even number line of image, thus obtain binocular texture image.
Second aspect, the invention provides a kind of binocular iris feature acquisition device, including:
Iris position determination unit, each picture in the image according to acquisition human eye binocular iris
The gray value of element determines pupil of left eye and the position of pupil of right eye in described image, further according to left eye
The gray value of the image of the neighboring area, position of pupil and pupil of right eye, determines left eye and right eye
Iris inner and outer boundary；
Iris texture acquiring unit, for described iris of left eye and iris of right eye inner and outer boundary it
Between a series of concentric circulars sample, it is thus achieved that iris of left eye texture image and iris of right eye stricture of vagina
Reason image, wherein, described iris texture image, inside and outside to iris in described left eye or right eye
The image of the some composition after a series of concentric circulars are acquired between border；
Binocular texture fetching unit, for by described iris of left eye texture image and iris of right eye stricture of vagina
Reason image co-registration is together, obtains binocular texture image；
Feature extraction unit, for carrying out local shape factor and inciting somebody to action to described binocular texture image
The information coding extracted, it is thus achieved that the feature of binocular iris.
Preferably, described iris texture acquiring unit, it is further used for:
By oculopupillary for left and right center line, using the line of this center as zero angle
Original position；
From the beginning of zero angle original position, between iris of left eye and iris of right eye inner and outer boundary
A series of concentric circulars are circumferentially sampled, it is thus achieved that iris of left eye texture image and iris of right eye
Texture image.
Preferably, described binocular texture fetching unit, it is further used for,
Using the gray value of the every one-row pixels in described iris of left eye texture image as binocular texture
The gray value of the pixel of the odd-numbered line of image；
It is additionally operable to the gray value of the every one-row pixels in described iris of right eye texture image as double
The gray value of the pixel of the even number line of mesh texture image, thus obtain binocular texture image.
The third aspect, the present invention provides a kind of auth method, and the method is according to the most above-mentioned institute
The binocular iris feature acquisition methods stated obtains the feature of binocular iris,
Described method also includes:
Prestore several binocular iris features；
Calculate the feature of the binocular iris obtained and the feature of several binocular irises prestored
Similarity；
If judging to know the feature of the binocular iris of acquisition and any one the binocular rainbow prestored
The characteristic similarity of film is more than the threshold value preset, then certification is passed through.
Preferably, described default threshold value is determined by following method, including:
The similarity distribution situation of the feature of the binocular iris gathered the most in the same time according to same people,
The similarity distribution situation of the feature of the binocular iris between different people and the peace of authentication requesting
Congruence level, determines described default threshold value.
Fourth aspect, the invention provides a kind of authentication system, including as described above
Binocular iris feature acquisition device, also includes memorizer and processor,
Described memorizer, is used for prestoring several binocular iris features；
Described processor, for calculating the binocular rainbow that described binocular iris feature acquisition device obtains
The similarity of the feature of film and the feature of several binocular irises prestored；
Described processor, if being additionally operable to judge the feature knowing the binocular iris of acquisition and deposit in advance
The characteristic similarity of any one binocular iris of storage is more than the threshold value preset, then certification is passed through.
Preferably, described default threshold value is determined by following method, including:
The similarity distribution situation of the feature of the binocular iris gathered the most in the same time according to same people,
The similarity distribution situation of the feature of the binocular iris between different people and the peace of authentication requesting
Congruence level, determines described default threshold value.
The binocular iris feature acquisition methods that the present invention provides is by the iris by left eye and right eye
Texture image merges and obtains binocular texture image, then binocular texture image is carried out feature
Extracting and obtain binocular iris feature with coding, the information that this feature comprises is monocular iris feature bag
The twice of the information contained, thus when this binocular iris feature is applied to identification, it is possible to have
Effect improves the safety identified, adds the difficulty that iris is false proof.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below
In describing embodiment, the required accompanying drawing used is briefly described, it should be apparent that under,
Accompanying drawing in the description of face is only some examples of the present invention, for those of ordinary skill in the art
From the point of view of, on the premise of not paying creative work, it is also possible to obtain other according to these accompanying drawings
Accompanying drawing.
Fig. 1 is the embodiment flow chart of the binocular iris feature acquisition methods that the present invention provides；
Fig. 2 is the example structure schematic diagram of the binocular iris feature acquisition device that the present invention provides；
Fig. 3 is the embodiment flow chart of the auth method that the present invention provides；
Fig. 4 is the specific embodiment flow chart of the auth method that the present invention provides；
Fig. 5 is the example structure schematic diagram of the authentication means that the present invention provides.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, to the technical side in the embodiment of the present invention
Case is clearly and completely described, it is clear that described embodiment is only the present invention one
Divide embodiment rather than whole embodiments.Based on the embodiment in the present invention, this area is general
The every other embodiment that logical technology people is obtained under not making creative work premise, all
Belong to the scope of protection of the invention.
First aspect, the invention provides the embodiment of a kind of binocular iris feature acquisition methods,
As it is shown in figure 1, include:
S101, determine institute according to obtaining the gray value of each pixel in the image of human eye binocular iris
State pupil of left eye and the position of pupil of right eye in image, further according to pupil of left eye and pupil of right eye
The gray value of the image of neighboring area, position, determines the iris inner and outer boundary of left eye and right eye；
S102, to a series of concentric circulars between described iris of left eye and iris of right eye inner and outer boundary
Sample, it is thus achieved that iris of left eye texture image and iris of right eye texture image, wherein, institute
State iris texture image, in described left eye or right eye between iris inner and outer boundary a series of with
The heart justifies the image of the some composition after being acquired；
S103, described iris of left eye texture image and iris of right eye texture image are merged,
Obtain binocular texture image；
S104, described binocular texture image is carried out local shape factor the information that will extract
Encode, it is thus achieved that the feature of binocular iris.
The binocular iris feature acquisition methods that the present invention provides is by the iris by left eye and right eye
Texture image merges and obtains binocular texture image, then binocular texture image is carried out feature
Extracting and obtain binocular iris feature with coding, the information that this feature comprises is monocular iris feature bag
The twice of the information contained, thus when this binocular iris feature is applied to identification, it is possible to have
Effect improves the safety identified, adds the difficulty that iris is false proof.
In the specific implementation, step S101 can be implemented in the following manner, specifically:
Automatically the figure of the binocular iris gathered has been focused on according to range sensor and focusing system
Picture, the region less by detection gray value primarily determines that right and left eyes pupil position, the most again root
According to the gray value of image of the neighboring area, position of pupil of left eye and pupil of right eye, can pass through
Edge extracting obtains all possible boundary point, then allows the Circle Parameters of these boundary point pairs candidate
Voting, the Circle Parameters many by gained vote draws circle, so that it is determined that in the iris of left eye and right eye
External boundary.
Would certainly understand from is, it is also possible to use additive method to determine the inner and outer boundary of iris, this
Bright this is not especially limited.
In the specific implementation, step S102 can be implemented in the following manner, specifically includes:
S1021, by oculopupillary for left and right center line, using the line of this center as
Zero angle original position；
S1022, from the beginning of zero angle original position, to iris of left eye and iris of right eye inner and outer boundary
Between a series of concentric circulars circumferentially sample, it is thus achieved that iris of left eye texture image and the right side
Eye iris texture image.
A series of concentric circulars are circumferentially sampled namely a series of concentric circulars are carried out here
Normalized, the final iris of left eye texture image obtained and iris of right eye texture image are
The rectangular area of formed objects, comprises in this region and all of samples a series of concentric circulars
Discrete point is obtained after (namely normalized).
Rise owing to determining, by the line of binocular pupil center, the phase place that iris texture characteristic represents
Beginning position, thus avoids in prior art owing to head inclination causes iris feature in angle side
To the problem occurring that phase place is inconsistent, the method making the embodiment of the present invention provide has invariable rotary
Property, when coupling without two iris features being carried out phase equalization by phase shift again
Judge.
In the specific implementation, step S103 can be implemented in the following manner, specifically includes:
Using the gray value of the every one-row pixels in iris of left eye texture image as binocular texture image
The gray value of pixel of odd-numbered line；Ash by the every one-row pixels in iris of right eye texture image
Angle value is as the gray value of the pixel of the even number line of binocular texture image, thus obtains binocular texture
Image.
It is understood that it is above-mentioned by iris of left eye texture image and iris of right eye texture image
The method merged is one embodiment of the present of invention, certainly can also use other
Iris of left eye texture image and iris of right eye texture image are merged, such as by method:
Can be using the gray value of the every string pixel in iris of left eye texture image as binocular texture image
The gray value of pixel of odd-numbered line；Again by the every string pixel in iris of right eye texture image
Gray value is as the gray value of the pixel of the even number line of binocular texture image.This is not made by the present invention
Concrete restriction.Two width image co-registration method together is each fallen within the protection model of the present invention by other
Enclose.
In the specific implementation, step S104 can be implemented in the following manner, specifically includes:
Local shape factor algorithm is used to extract binocular texture image in different radii position and difference
The phase property information of angle position, and carry out binary-coding with 0 and 1.Similarly, the present invention
The method of local characteristics algorithm and coding is not made concrete restriction.
Second aspect, present invention also offers a kind of binocular iris feature acquisition device embodiment,
As in figure 2 it is shown, include:
Iris position determination unit 301, is used in the image according to acquisition human eye binocular iris each
The gray value of pixel determines pupil of left eye and the position of pupil of right eye in described image, further according to a left side
The gray value of the image of the neighboring area, position of eye pupil hole and pupil of right eye, determines left eye and the right side
The iris inner and outer boundary of eye；
Iris texture acquiring unit 302, for described iris of left eye and iris of right eye inner and outer boundary
Between a series of concentric circulars sample, it is thus achieved that iris of left eye texture image and iris of right eye
Texture image, wherein, described iris texture image, in iris in described left eye or right eye
The image of the some composition after a series of concentric circulars are acquired between external boundary；
Binocular texture fetching unit 303, for by described iris of left eye texture image and iris of right eye
Texture image merges, and obtains binocular texture image；
Feature extraction unit 304, for carrying out local shape factor also to described binocular texture image
The information coding that will extract, it is thus achieved that the feature of binocular iris.
In the specific implementation, iris texture acquiring unit 302, it is further used for:
By oculopupillary for left and right center line, using the line of this center as zero angle
Original position；From the beginning of zero angle original position, to iris of left eye and iris of right eye inner and outer boundary
Between a series of concentric circulars circumferentially sample, it is thus achieved that iris of left eye texture image and the right side
Eye iris texture image.
In the specific implementation, binocular texture fetching unit 303, it is further used for,
Using the gray value of the every one-row pixels in described iris of left eye texture image as binocular texture
The gray value of the pixel of the odd-numbered line of image；It is additionally operable in described iris of right eye texture image
The gray value of every one-row pixels as the gray value of the pixel of the even number line of binocular texture image, from
And obtain binocular texture image.
The acquisition device of the binocular iris feature introduced due to the present embodiment is for can perform this
The device of the method that binocular iris feature obtains in bright embodiment, so based on the embodiment of the present invention
Described in binocular iris feature obtain method, those skilled in the art will appreciate that
The detailed description of the invention of the binocular iris feature acquisition device of the present embodiment and its various change shapes
How formula, so realize in the embodiment of the present invention for this binocular iris feature acquisition device at this
Binocular iris feature acquisition methods be no longer discussed in detail.As long as those skilled in the art are real
Execute the device that in the embodiment of the present invention, binocular iris feature acquisition methods is used, broadly fall into this Shen
The scope that please be protect.
The third aspect, the invention provides a kind of auth method, and wherein, the method is root
The feature of binocular iris is obtained according to binocular iris feature acquisition methods described above.Such as Fig. 3
Shown in, the method also includes:
S301, prestore several binocular iris features；
S302, the feature calculating the binocular iris obtained and several binocular irises prestored
The similarity of feature；
If S303 judges to know the feature of the binocular iris of acquisition and any one prestored
The characteristic similarity of binocular iris is more than the threshold value preset, then certification is passed through.
Wherein, step S301 can be accomplished by, as shown in Figure 4, and including:
Gather iris of left eye image and iris of right eye image, by iris of left eye image and right eye
The localization of iris circle of iris image；Right and left eyes pupil position line, determines iris region normalizing
The zero start angle position changed, and by right and left eyes iris normalization region merging technique；Extract localized mode
Formula feature, obtains iris feature, constitutes identity characteristic template；Several identity characteristic template structures
Become the data base of identity characteristic template.Concrete process obtained with iris feature described above
Journey is similar to, and does not repeats them here.
Step S302 and step S303 can be accomplished by, as shown in Figure 4, and including:
According to the feature of the binocular iris that the method for the feature of binocular iris described above obtains,
Calculate the feature of the binocular iris obtained and the phase of the feature of several binocular irises prestored
Like degree, namely carry out pattern contrast with the identity characteristic template in the data base of identity characteristic template.
If judging to know the feature of the binocular iris of acquisition and any one the binocular iris prestored
Characteristic similarity is more than the threshold value preset, then certification is passed through；Otherwise, then certification is not passed through.
Owing to the feature of iris comes from right and left eyes, identical angle direction and radial direction feature
It is relevant, therefore by above-mentioned identity identifying method, if it is desired to personation identity, needs
Removing to forge the iris of eyes, this increases again and is twice than forging simple eye iris difficulty and risk, pseudo-
Cause this raising, can avoid further palming off phenomenon, improve the safety of information system.
In the specific implementation, the threshold value preset here is determined by following method, including:
The similarity distribution situation of feature of binocular iris that gathers the most in the same time according to same people, difference
The similarity distribution situation of the feature of the binocular iris between people and the safety etc. of authentication requesting
Level, determines described default threshold value.That is, according to the substantial amounts of iris sample gathered the most in the same time
Originally in carrying out class, comparison obtains similar degree in the class distribution situation, obtains class according to comparison between a large amount of classes
Between distribution of similarity situation, and the safe class according to authentication requesting, finally determine for
By the threshold size of certification.
It is understood that threshold value here can be changed according to practical situation, it is also possible to pass through
Other mode is arranged, and this is not especially limited by the present invention.
Fourth aspect, the invention provides a kind of authentication system embodiment, as it is shown in figure 5,
Including binocular iris feature acquisition device 501 described above, also include memorizer 502 and place
Reason device 503,
Memorizer 502, is used for prestoring several binocular iris features；
Processor 503, for calculating the binocular iris that binocular iris feature acquisition device 501 obtains
The similarity of feature and the feature of several binocular irises prestored；
Processor 503, if being additionally operable to judge the feature knowing the binocular iris of acquisition and prestore
Any one binocular iris characteristic similarity more than preset threshold value, then certification is passed through.
Similarly, the threshold value here preset at is determined by following method, including: according to same
Between the similarity distribution situation of the feature of the binocular iris that one people gathers the most in the same time, different people
The similarity distribution situation of feature of binocular iris and the safe class of authentication requesting, really
The fixed threshold value preset.
The authentication system introduced due to the present embodiment is for can perform in the embodiment of the present invention
The system of the method for authentication, so based on the authentication described in the embodiment of the present invention
Method, those skilled in the art will appreciate that the tool of the authentication system of the present embodiment
Body embodiment and its various versions, so at this for this authentication system how
The auth method realized in the embodiment of the present invention is no longer discussed in detail.As long as belonging to this area
Technical staff implements the device that auth method in the embodiment of the present invention is used, and broadly falls into this
The scope that application to be protected.
Device embodiment described above is only schematically, wherein said as separated part
The unit of part explanation can be or may not be physically separate, shows as unit
Parts can be or may not be physical location, i.e. may be located at a place, or also
Can be distributed on multiple NE.Can select according to the actual needs part therein or
The whole module of person realizes the purpose of the present embodiment scheme.Those of ordinary skill in the art are not paying
In the case of going out performing creative labour, i.e. it is appreciated that and implements.
Through the above description of the embodiments, those skilled in the art it can be understood that
The mode of required general hardware platform can be added by software to each embodiment to realize, certainly
Hardware can also be passed through.Based on such understanding, technique scheme is the most in other words to existing
The part having technology to contribute can embody with the form of software product, and this computer is soft
Part product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, light
Dish etc., including some instructions with so that computer equipment (can be personal computer,
Server, or the network equipment etc.) perform some part institute of each embodiment or embodiment
The method stated.
Last it is noted that above example is only in order to illustrate technical scheme, and
Non-to its restriction；Although the present invention being described in detail with reference to previous embodiment, ability
The those of ordinary skill in territory is it is understood that it still can be to the skill described in foregoing embodiments
Art scheme is modified, or wherein portion of techniques feature is carried out equivalent；And these are repaiied
Change or replace, not making the essence of appropriate technical solution depart from various embodiments of the present invention technical side
The spirit and scope of case.
Claims (10)
1. a binocular iris feature acquisition methods, it is characterised in that including:
In image according to acquisition human eye binocular iris, the gray value of each pixel determines described image
Middle pupil of left eye and the position of pupil of right eye, further according to pupil of left eye and the position of pupil of right eye
The gray value of the image of neighboring area, determines the iris inner and outer boundary of left eye and right eye；
A series of concentric circulars between described iris of left eye and iris of right eye inner and outer boundary are adopted
Sample, it is thus achieved that iris of left eye texture image and iris of right eye texture image, wherein, described iris
Texture image, in described left eye or right eye between iris inner and outer boundary a series of concentric circulars enter
The image of the some composition after row collection；
Described iris of left eye texture image and iris of right eye texture image are merged, obtains
Binocular texture image；
Described binocular texture image is carried out local shape factor and the information extracted is compiled
Code, it is thus achieved that the feature of binocular iris.
2. the method for claim 1, it is characterised in that described to iris of left eye with the right side
A series of concentric circulars between eye iris inner and outer boundary are sampled, it is thus achieved that iris of left eye texture maps
The step of picture and iris of right eye texture image includes:
By oculopupillary for left and right center line, using the line of this center as zero angle
Original position；
From the beginning of zero angle original position, between iris of left eye and iris of right eye inner and outer boundary
A series of concentric circulars are circumferentially sampled, it is thus achieved that iris of left eye texture image and iris of right eye
Texture image.
3. the method for claim 1, it is characterised in that by described iris of left eye texture
Image and iris of right eye texture image merge, and the step obtaining binocular texture image includes:
Using the gray value of the every one-row pixels in described iris of left eye texture image as binocular texture
The gray value of the pixel of the odd-numbered line of image；
Using the gray value of the every one-row pixels in described iris of right eye texture image as binocular texture
The gray value of the pixel of the even number line of image, thus obtain binocular texture image.
4. a binocular iris feature acquisition device, it is characterised in that including:
Iris position determination unit, each picture in the image according to acquisition human eye binocular iris
The gray value of element determines pupil of left eye and the position of pupil of right eye in described image, further according to left eye
The gray value of the image of the neighboring area, position of pupil and pupil of right eye, determines left eye and right eye
Iris inner and outer boundary；
Iris texture acquiring unit, for described iris of left eye and iris of right eye inner and outer boundary it
Between a series of concentric circulars sample, it is thus achieved that iris of left eye texture image and iris of right eye stricture of vagina
Reason image, wherein, described iris texture image, inside and outside to iris in described left eye or right eye
The image of the some composition after a series of concentric circulars are acquired between border；
Binocular texture fetching unit, for by described iris of left eye texture image and iris of right eye stricture of vagina
Reason image co-registration together, obtains binocular texture image；
Feature extraction unit, for carrying out local shape factor and inciting somebody to action to described binocular texture image
The information coding extracted, it is thus achieved that the feature of binocular iris.
5. device as claimed in claim 4, it is characterised in that described iris texture obtains single
Unit, is further used for:
By oculopupillary for left and right center line, using the line of this center as zero angle
Original position；
From the beginning of zero angle original position, between iris of left eye and iris of right eye inner and outer boundary
A series of concentric circulars are circumferentially sampled, it is thus achieved that iris of left eye texture image and iris of right eye
Texture image.
6. device as claimed in claim 4, it is characterised in that described binocular texture acquirement list
Unit, is further used for,
Using the gray value of the every one-row pixels in described iris of left eye texture image as binocular texture
The gray value of the pixel of the odd-numbered line of image；
It is additionally operable to the gray value of the every one-row pixels in described iris of right eye texture image as double
The gray value of the pixel of the even number line of mesh texture image, thus obtain binocular texture image.
7. an auth method, it is characterised in that according to as described in claim 1-3 is arbitrary
Binocular iris feature acquisition methods obtain binocular iris feature,
Described method also includes:
Prestore several binocular iris features；
Calculate the feature of the binocular iris obtained and the feature of several binocular irises prestored
Similarity；
If judging to know the feature of the binocular iris of acquisition and any one the binocular rainbow prestored
The characteristic similarity of film is more than the threshold value preset, then certification is passed through.
8. method as claimed in claim 7, it is characterised in that described default threshold value is logical
Cross what following method determined, including:
The similarity distribution situation of the feature of the binocular iris gathered the most in the same time according to same people,
The similarity distribution situation of the feature of the binocular iris between different people and the peace of authentication requesting
Congruence level, determines described default threshold value.
9. an authentication system, it is characterised in that include right want 4-6 arbitrary as described in
Binocular iris feature acquisition device, also includes memorizer and processor,
Described memorizer, is used for prestoring several binocular iris features；
Described processor, for calculating the binocular rainbow that described binocular iris feature acquisition device obtains
The similarity of the feature of film and the feature of several binocular irises prestored；
Described processor, if being additionally operable to judge the feature knowing the binocular iris of acquisition and deposit in advance
The characteristic similarity of any one binocular iris of storage is more than the threshold value preset, then certification is passed through.
10. system as claimed in claim 9, it is characterised in that described default threshold value is logical
Cross what following method determined, including:
The similarity distribution situation of the feature of the binocular iris gathered the most in the same time according to same people,
The similarity distribution situation of the feature of the binocular iris between different people and the peace of authentication requesting
Congruence level, determines described default threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610236748.0A CN105868731A (en) | 2016-04-15 | 2016-04-15 | Binocular iris characteristic obtaining method, binocular iris characteristic obtaining device, identity identification method and identity identification system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610236748.0A CN105868731A (en) | 2016-04-15 | 2016-04-15 | Binocular iris characteristic obtaining method, binocular iris characteristic obtaining device, identity identification method and identity identification system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105868731A true CN105868731A (en) | 2016-08-17 |
Family
ID=56632891
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610236748.0A Pending CN105868731A (en) | 2016-04-15 | 2016-04-15 | Binocular iris characteristic obtaining method, binocular iris characteristic obtaining device, identity identification method and identity identification system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105868731A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107145820A (en) * | 2017-03-16 | 2017-09-08 | 杭州岱石科技有限公司 | Eyes localization method based on HOG features and FAST algorithms |
| CN107480747A (en) * | 2017-06-28 | 2017-12-15 | 邱艺 | A kind of verification method of mobile phone dual camera recognition anti-counterfeiting characteristic information |
| CN108388858A (en) * | 2018-02-11 | 2018-08-10 | 北京京东金融科技控股有限公司 | Iris method for anti-counterfeit and device |
| CN108596112A (en) * | 2018-04-27 | 2018-09-28 | 北京万里红科技股份有限公司 | A kind of choice of dynamical method of extensive iris feature identification matching threshold |
| CN109299678A (en) * | 2018-09-08 | 2019-02-01 | 太若科技(北京)有限公司 | A kind of method, tripper and AR glasses using iris unlock AR glasses |
| CN110837749A (en) * | 2018-08-15 | 2020-02-25 | 北京京东金融科技控股有限公司 | Identity recognition method, device, electronic equipment and medium |
| CN111178189A (en) * | 2019-12-17 | 2020-05-19 | 北京无线电计量测试研究所 | Network learning auxiliary method and system |
| CN111274997A (en) * | 2020-02-17 | 2020-06-12 | 天津中科智能识别产业技术研究院有限公司 | Iris recognition neural network model training method based on binocular fusion |
| CN113706597A (en) * | 2021-08-30 | 2021-11-26 | 广州虎牙科技有限公司 | Video frame image processing method and electronic equipment |
| CN113780034A (en) * | 2020-06-09 | 2021-12-10 | 上海聚虹光电科技有限公司 | Eye focus tracking method based on iris recognition |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1584915A (en) * | 2004-06-15 | 2005-02-23 | 沈阳工业大学 | Human iris identifying method |
| US20060088193A1 (en) * | 2004-10-21 | 2006-04-27 | Muller David F | Method and system for generating a combined retina/iris pattern biometric |
| CN101034434A (en) * | 2007-04-10 | 2007-09-12 | 杭州电子科技大学 | Identification recognizing method based on binocular iris |
| CN101165704A (en) * | 2006-10-20 | 2008-04-23 | 西安紫牛信息技术有限公司 | Composite fingerprint template matching method |
| CN105184133A (en) * | 2015-07-30 | 2015-12-23 | 广东欧珀移动通信有限公司 | Authentication method and apparatus, and corresponding mobile terminal |
-
2016
- 2016-04-15 CN CN201610236748.0A patent/CN105868731A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1584915A (en) * | 2004-06-15 | 2005-02-23 | 沈阳工业大学 | Human iris identifying method |
| US20060088193A1 (en) * | 2004-10-21 | 2006-04-27 | Muller David F | Method and system for generating a combined retina/iris pattern biometric |
| CN101165704A (en) * | 2006-10-20 | 2008-04-23 | 西安紫牛信息技术有限公司 | Composite fingerprint template matching method |
| CN101034434A (en) * | 2007-04-10 | 2007-09-12 | 杭州电子科技大学 | Identification recognizing method based on binocular iris |
| CN105184133A (en) * | 2015-07-30 | 2015-12-23 | 广东欧珀移动通信有限公司 | Authentication method and apparatus, and corresponding mobile terminal |
Non-Patent Citations (1)
| Title |
|---|
| 张志坚: "多模态生物特征识别融合算法的研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107145820A (en) * | 2017-03-16 | 2017-09-08 | 杭州岱石科技有限公司 | Eyes localization method based on HOG features and FAST algorithms |
| CN107480747A (en) * | 2017-06-28 | 2017-12-15 | 邱艺 | A kind of verification method of mobile phone dual camera recognition anti-counterfeiting characteristic information |
| CN108388858B (en) * | 2018-02-11 | 2020-05-01 | 京东数字科技控股有限公司 | Iris anti-fake method and device |
| CN108388858A (en) * | 2018-02-11 | 2018-08-10 | 北京京东金融科技控股有限公司 | Iris method for anti-counterfeit and device |
| CN108596112A (en) * | 2018-04-27 | 2018-09-28 | 北京万里红科技股份有限公司 | A kind of choice of dynamical method of extensive iris feature identification matching threshold |
| CN110837749A (en) * | 2018-08-15 | 2020-02-25 | 北京京东金融科技控股有限公司 | Identity recognition method, device, electronic equipment and medium |
| CN109299678A (en) * | 2018-09-08 | 2019-02-01 | 太若科技(北京)有限公司 | A kind of method, tripper and AR glasses using iris unlock AR glasses |
| CN111178189A (en) * | 2019-12-17 | 2020-05-19 | 北京无线电计量测试研究所 | Network learning auxiliary method and system |
| CN111178189B (en) * | 2019-12-17 | 2024-04-09 | 北京无线电计量测试研究所 | Network learning auxiliary method and system |
| CN111274997A (en) * | 2020-02-17 | 2020-06-12 | 天津中科智能识别产业技术研究院有限公司 | Iris recognition neural network model training method based on binocular fusion |
| CN111274997B (en) * | 2020-02-17 | 2023-02-24 | 天津中科智能识别产业技术研究院有限公司 | Iris recognition neural network model training method based on binocular fusion |
| CN113780034A (en) * | 2020-06-09 | 2021-12-10 | 上海聚虹光电科技有限公司 | Eye focus tracking method based on iris recognition |
| CN113706597A (en) * | 2021-08-30 | 2021-11-26 | 广州虎牙科技有限公司 | Video frame image processing method and electronic equipment |
| CN113706597B (en) * | 2021-08-30 | 2024-06-25 | 广州虎牙科技有限公司 | Video frame image processing method and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105868731A (en) | Binocular iris characteristic obtaining method, binocular iris characteristic obtaining device, identity identification method and identity identification system | |
| EP3373798B1 (en) | Method and system for classifying optic nerve head | |
| US10966602B2 (en) | Automatically detecting eye type in retinal fundus images | |
| KR101356358B1 (en) | Computer-implemented method and apparatus for biometric authentication based on images of an eye | |
| Ibrahim et al. | Iris localization using local histogram and other image statistics | |
| US7327860B2 (en) | Conjunctival scans for personal identification | |
| JP2012519927A (en) | A novel inpainting technique and method for reconstructing iris scans through partial acquisition mosaic processing | |
| CN106778525A (en) | Identity identifying method and device | |
| KR20140020735A (en) | Quality metrics for biometric authentication | |
| WO2013087026A1 (en) | Locating method and locating device for iris | |
| Das et al. | A new method for sclera vessel recognition using OLBP | |
| Srivastava | Personal identification using iris recognition system, a review | |
| Vimal et al. | RETRACTED ARTICLE: A method of progression detection for glaucoma using K-means and the GLCM algorithm toward smart medical prediction | |
| Burge et al. | Using ear biometrics for passive identification | |
| Feng et al. | Fingerprint alteration | |
| Noah Akande et al. | Implementation of a framework for healthy and diabetic retinopathy retinal image recognition | |
| Bevilacqua et al. | Retinal fundus biometric analysis for personal identifications | |
| Abdel-Latif et al. | Achieving information security by multi-modal iris-retina biometric approach using improved mask R-CNN | |
| Chandrappa et al. | A novel approach to glaucoma screening using optic nerve head through image fusion and fractal geometry | |
| Roy et al. | Detection of bifurcation angles in a retinal fundus image | |
| Borkar et al. | IRIS recognition system | |
| Bassi et al. | Human biometric identification through brain print | |
| Malik et al. | An efficient retinal vessels biometric recognition system by using multi-scale local binary pattern descriptor | |
| Harun et al. | New algorithm of extraction of palmprint region of interest (ROI) | |
| Kooshkestani et al. | A new method for iris recognition systems based on fast pupil localization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160817 |
|
| RJ01 | Rejection of invention patent application after publication |