CN110414300A - Method and device for synthesizing iris characteristics - Google Patents
Method and device for synthesizing iris characteristics Download PDFInfo
- Publication number
- CN110414300A CN110414300A CN201810404512.2A CN201810404512A CN110414300A CN 110414300 A CN110414300 A CN 110414300A CN 201810404512 A CN201810404512 A CN 201810404512A CN 110414300 A CN110414300 A CN 110414300A
- Authority
- CN
- China
- Prior art keywords
- iris
- iris feature
- noise template
- feature
- noise
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000002194 synthesizing effect Effects 0.000 title claims abstract description 5
- 230000004927 fusion Effects 0.000 claims abstract description 11
- 239000002131 composite material Substances 0.000 claims description 52
- 230000015572 biosynthetic process Effects 0.000 claims description 51
- 238000003786 synthesis reaction Methods 0.000 claims description 51
- 239000000203 mixture Substances 0.000 claims description 13
- 238000010189 synthetic method Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 6
- 210000000554 iris Anatomy 0.000 description 280
- 238000004364 calculation method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 210000003786 sclera Anatomy 0.000 description 2
- 241000790351 Iris latifolia Species 0.000 description 1
- 108091068595 Long family Proteins 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000000720 eyelash Anatomy 0.000 description 1
- 210000000744 eyelid Anatomy 0.000 description 1
- 238000009415 formwork Methods 0.000 description 1
- 210000004209 hair Anatomy 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a method and a device for synthesizing iris characteristics, wherein the method comprises the following steps: acquiring iris characteristics of N iris images meeting preset conditions, wherein the iris characteristics comprise a noise template and iris characteristic codes, and the code value of each bit of the noise template represents the validity of the bit; calculating a synthetic noise template according to the noise templates of the N iris features, wherein the region formed by the valid bits of the synthetic noise template is the fusion of the regions formed by the valid bits of the N noise templates; counting the iris feature codes of the N iris features according to the synthetic noise template to obtain synthetic iris feature codes; the code value of the iris characteristic code corresponding to all the noise templates which are effective on the same bit and the most frequently appearing code value on the corresponding bit of the bit is the code value of the synthesized iris characteristic code on the corresponding bit; and combining the synthesized noise template and the synthesized iris characteristic code to obtain synthesized iris characteristics. The invention increases the effective area of the iris and improves the quality of the iris characteristics.
Description
Technical field
The present invention relates to iris image process fields, particularly relate to the synthetic method and device of a kind of iris feature.
Background technique
One complete iris identification system is mainly made of five aspects: the acquisition of iris image, iris image
Pretreatment, the feature extraction of iris image and the aspect ratio pair of iris.The application mode of iris identification system is general
Two kinds of registration and certification can be divided into.In iris identification system, the feature extraction of iris image is very the key link,
The quality of the iris feature extracted directly affects the accuracy and rate of registration and certification.
It is in practical applications, general only to register once by taking iris registration process as an example, and can authenticate in use repeatedly,
If iris feature template is not that very well, will affect subsequent authentication procedure when registration, there is the problems such as certification is difficult, accidentally knows, most
The experience of entire iris identity authorization system is influenced eventually.The iris register method of early stage can be generally divided into following two: 1) is infused
Iris image quality (such as clarity) is judged when volume.2) registers multiple iris image samples simultaneously, that is to say, that note
The feature templates of multiple client iris images of volume.
Method for being judged when registration iris image quality, every iris image is intended to carry out when due to registration
Quality estimation increases the complexity of program, bad or use in the iris image quality of the user of acquisition so that registion time is long
Family position can cause registration difficult when improper, do not register, need user repeatedly to cooperate and register, therefore, the registration side
That there are registion time is long for method, and registration is difficult, the bad problem of user experience.
On the one hand method for registering multiple iris image samples simultaneously occupies Installed System Memory, on the other hand may shadow
Subsequent authentication procedure is rung, such as: it needs to carry out large-scale data library searching when certification, since registration feature template is relatively more simultaneously
And quality cannot be guaranteed, and will increase the risk accidentally known, authenticated time lengthens, and therefore, the possible misclassification rate of the register method is higher,
Increase comparison time (such as 5 feature samples, certification needs to compare five times every time).
Summary of the invention
In order to solve the above technical problems, the present invention provides the synthetic method and device of a kind of iris feature, the present invention increases
The effective coverage area of iris, improves the quality of iris feature.
It is as follows that the present invention provides technical solution:
On the one hand, the present invention provides a kind of synthetic methods of iris feature, which is characterized in that the described method includes:
The iris feature for meeting N number of iris image of preset condition is obtained, the iris feature includes noise template and rainbow
The encoded radio of film feature coding, each of the noise template represents the validity of this；
A composite noise template is calculated according to the noise template of N number of iris feature, wherein the composite noise mould
The region of the significance bit composition of plate is the fusion in the region that the significance bit of N number of noise template forms；
It is counted according to iris feature coding of the composite noise template to N number of iris feature, obtains a synthesis
Iris feature coding；Wherein, effectively the corresponding iris feature of all noise templates encodes the correspondence in this on same position
The most encoded radio of frequency of occurrence is to synthesize iris feature coding in the encoded radio of the correspondence position on position；
A synthesis iris feature is obtained according to composite noise template and synthesis iris feature coded combination.
An embodiment according to the present invention, it is described to obtain the iris feature for meeting N number of iris image of preset condition, the rainbow
Film feature includes noise template and iris feature coding, and the encoded radio of each of the noise template represents the validity of this,
Include:
Obtain several iris images of same user；
Several iris features are extracted from several iris images；
Several iris features are mutually compared, if mutually ratio passes through, record the iris feature passed through, if mutually than failure, record
The frequency of failure；
If the frequency of failure is less than preset times and the iris feature of record reaches predetermined number, by the iris feature of record
Iris feature as N number of iris image.
Another embodiment according to the present invention, the Gabor binary-coding feature that the iris feature is 2048, wherein before
1024 are encoded to noise template, and latter 1024 are encoded to iris feature coding, and the encoded radio of noise template is that 1 representative is effective,
It is invalid to represent for 0.
Another embodiment according to the present invention, the noise template according to N number of iris feature are calculated a synthesis and make an uproar
Acoustic mode plate, wherein the region of the significance bit composition of the composite noise template is the region that the significance bit of N number of noise template forms
Fusion, comprising:
The encoded radio of each identical bits of N number of noise template is carried out respectively or operation obtains composite noise template.
Another embodiment according to the present invention, it is described according to the composite noise template to the iris feature of N number of iris feature
Coding is counted, and a synthesis iris feature coding is obtained；Wherein, effective all noise templates are corresponding on same position
Iris feature coding most encoded radio of frequency of occurrence on the correspondence position of this is to synthesize iris feature coding in the correspondence
The encoded radio of position, comprising:
When encoded radio in a certain position of composite noise template is 1, all noise templates that this is 1 are found out；
It counts the corresponding iris feature of the noise template found out and encodes the number that 0,1 value occurs on the correspondence position of this；
If the number that 0 number >=1 occurred occurs, synthesizing value of the iris feature coding in the correspondence position is 0, otherwise,
Synthesizing value of the iris feature coding in the correspondence position is 1.
On the other hand, the present invention provides a kind of synthesizer of iris feature, described device includes:
Module is obtained, for obtaining the iris feature for meeting N number of iris image of preset condition, the iris feature includes
Noise template and iris feature coding, the encoded radio of each of the noise template represent the validity of this；
A composite noise template is calculated for the noise template according to N number of iris feature in computing module, wherein
The region of the significance bit composition of the composite noise template is the fusion in the region that the significance bit of N number of noise template forms；
Statistical module, for being counted according to iris feature coding of the composite noise template to N number of iris feature,
Obtain a synthesis iris feature coding；Wherein, effectively the corresponding iris feature of all noise templates encodes on same position
The most encoded radio of frequency of occurrence is to synthesize iris feature coding in the encoded radio of the correspondence position on the correspondence position of this；
Synthesis module, it is special for obtaining a synthesis iris according to composite noise template and synthesis iris feature coded combination
Sign.
An embodiment according to the present invention, the acquisition module include:
Acquiring unit, for obtaining several iris images of same user；
Extraction unit, for extracting several iris features from several iris images；
Mutually than unit, for mutually being compared several iris features, if mutually ratio passes through, the iris feature passed through is recorded, if
Mutually than failure, the frequency of failure is recorded；
Comparing unit will if the iris feature for the frequency of failure to be less than preset times and record reaches predetermined number
Iris feature of the iris feature of record as N number of iris image.
Another embodiment according to the present invention, the Gabor binary-coding feature that the iris feature is 2048, wherein before
1024 are encoded to noise template, and latter 1024 are encoded to iris feature coding, and the encoded radio of noise template is that 1 representative is effective,
It is invalid to represent for 0.
Another embodiment according to the present invention, the computing module are used for:
The encoded radio of each identical bits of N number of noise template is carried out respectively or operation obtains composite noise template.
Another embodiment according to the present invention, the statistical module include:
Searching unit, for the encoded radio in a certain position of composite noise template be 1 when, find out this be 1 all noises
Template；
Statistic unit encodes 0,1 on the correspondence position of this for counting the corresponding iris feature of noise template found out
It is worth the number occurred；
Determination unit synthesizes iris feature coding in the correspondence position if the number that number >=1 occurred for 0 occurs
Value be 0, otherwise, synthesis iris feature coding the correspondence position value be 1.
The invention has the following advantages:
The embodiment of the present invention obtains a synthesis iris feature by the iris feature of multiple iris images, wherein by multiple
The effective coverage of iris feature noise template merges to obtain the noise template of synthesis iris feature, and is compiled according to multiple iris features
Code calculates the corresponding iris feature coding of composite noise template, increases the effective coverage area of iris.And it is synthesized calculating
It is when iris feature encodes, the corresponding iris feature coding frequency of occurrence in same position of all effective noise templates is most
Encoded radio as synthesis iris feature coding encoded radio in the position, prevent feature contingency caused by noise, improve
The quality of iris feature, reduces misclassification rate.
Present invention is preferably used in the synthesis iris features when iris is registered, obtained as iris feature template, after participation
Continuous identification certification.The iris feature template increases the registered area of iris, improves the quality of registration feature template, guarantees
The validity of registration feature template improves the success rate of identification, solves that conventional Registration method experience property is poor, registion time is long
And the problem that misclassification rate is high.
Detailed description of the invention
Fig. 1 is the synthetic method flow chart of the iris feature of the embodiment of the present invention 1；
Fig. 2 is the synthesizer schematic diagram of the iris feature of the embodiment of the present invention 2.
Specific embodiment
To keep the technical problem to be solved in the present invention, technical solution and advantage clearer, below in conjunction with attached drawing and tool
Technical solution of the present invention is clearly and completely described in body embodiment.Obviously, described embodiment is only the present invention
A part of the embodiment, instead of all the embodiments.The group of embodiments of the present invention, which are generally described and illustrated herein in the accompanying drawings
Part can be arranged and be designed with a variety of different configurations.Therefore, below to the embodiment of the present invention provided in the accompanying drawings
Detailed description is not intended to limit the range of claimed invention, but is merely representative of selected embodiment of the invention.Base
In the embodiment of the present invention, those skilled in the art's every other reality obtained without making creative work
Example is applied, shall fall within the protection scope of the present invention.
Embodiment 1:
The embodiment of the invention provides a kind of synthetic methods of iris feature.
The embodiment of the present invention is preferred for when iris is registered, and synthesis obtains the iris feature template of high quality, after participation
Continuous identification certification.Certainly, the embodiment of the present invention can be used for other occasions relatively high to iris feature quality requirement, and
It is not limited to when iris is registered.
As shown in Figure 1, this method comprises:
Step S100: the iris feature for meeting N number of iris image of preset condition is obtained, iris feature includes noise template
It is encoded with iris feature, the encoded radio that noise template is each represents the validity of this.
Meet preset condition and refer to that the quality of the iris feature of iris image is met the requirements, preset condition can according to need
Setting.The iris feature of the embodiment of the present invention includes noise template and iris feature coding, and noise template, which refers to, positions eyelid,
The result of eyelash detection and spot detection is by binaryzation [0,1] with the equal-sized matrix of iris image come table
Show, iris feature coding is 0,1 encoded radio of real iris feature.Noise template and iris feature are encoded in same position
Position is corresponding, if the position of noise template is effective, the encoded radio of the correspondence position of iris feature coding is effectively, to correspond to iris figure
The position is effective on picture.Noise template representative be iris region validity, noise template significance bit composition area
Domain represents the effective coverage of iris, i.e. iris and sclera portion.
Step S200: a composite noise template is calculated according to the noise template of N number of iris feature, wherein synthesis
The region of the significance bit composition of noise template is the fusion in the region that the significance bit of N number of noise template forms.By by N number of noise
The region fusion of the significance bit composition of template increases the area in the region of the significance bit composition of composite noise template, that is, increases
The area of the effective coverage of iris.
Step S300: it is counted according to iris feature coding of the composite noise template to N number of iris feature, obtains one
Synthesize iris feature coding；Wherein, effectively the corresponding iris feature of all noise templates is encoded this 's on same position
The most encoded radio of frequency of occurrence is to synthesize iris feature coding in the encoded radio of the correspondence position on corresponding position.
On the basis of the area of the aforementioned effective coverage for increasing iris, need for its correspondence of composite noise formwork calculation
Iris feature coding；By aforementioned, the region of the significance bit composition of composite noise template is that the significance bit of N number of noise template forms
Region fusion, it is seen then that if a position of composite noise template is effective, N number of noise template at least one have in the position
Effect, then can be using value of the corresponding iris feature coding of effective noise template on the correspondence position of this as composite noise mould
The corresponding iris feature coding of plate (i.e. synthesis iris feature coding).Identical processing is carried out to each, synthesis can be obtained
The encoded radio that feature coding is each.Due to being likely to be accidentally occur situation at this time, in order to avoid caused accidental
Property, the most iris feature encoded radio of corresponding position frequency of occurrence is counted, the quality of iris feature is improved, reduces misclassification rate.
Step S400: a synthesis iris feature is obtained according to composite noise template and synthesis iris feature coded combination.
They are combined and synthesis iris spy can be obtained by the aforementioned composite noise template that obtains with after synthesis iris feature coding
Sign, uses as feature templates.
The embodiment of the present invention obtains a synthesis iris feature by the iris feature of multiple iris images, wherein by multiple
It merges to obtain the noise template (i.e. composite noise template) of synthesis iris feature, and root in the effective coverage of iris feature noise template
It is encoded according to multiple iris features and calculates the corresponding iris feature coding of composite noise template (i.e. synthesis iris feature coding), increased
The effective coverage area of iris.And it is when calculating synthesis iris feature coding, all effective noise templates are corresponding
The iris feature coding volume of the most encoded radio of frequency of occurrence as synthesis iris feature coding in the position in same position
Code value prevents feature contingency caused by noise, improves the quality of iris feature, reduces misclassification rate.
Present invention is preferably used in the synthesis iris features when iris is registered, obtained as iris feature template, after participation
Continuous identification certification.The iris feature template increases the registered area of iris, improves the quality of registration feature template, guarantees
The validity of registration feature template improves the success rate of identification, solves that conventional Registration method experience property is poor, registion time is long
And the problem that misclassification rate is high.
In the present embodiment, judge whether to meet preset condition, step S100 using the method for comparing iris feature mutually
Include:
Step S110: several iris images of same user are obtained.Iris recognition instrument, iris authentication instrument, rainbow can be passed through
The irises equipment such as film door access machine shoots multiple iris images of user or shooting user's eye video, and multiframe packet is read from video
Image containing iris region.
Step S120: several iris features are extracted from several iris images, in this step, it is not absolutely required to extract
There is the iris feature of iris image.
Step S130: mutually comparing several iris features, if mutually ratio passes through, records the iris feature passed through, if mutually ratio
Failure records the frequency of failure.
It is preferable to use Hamming distances mutually to be compared two iris features for the embodiment of the present invention, and formula is as follows:
Wherein, AjAnd BjThe jth position Gabor characteristic coding of iris feature A and B are respectively indicated,Indicate XOR operation.Cause
This, for the two width iris images of the same person, Hamming distance HD is smaller；For two width iris images of different people, the Chinese
Prescribed distance is larger.Therefore mutually than when, set a threshold value, less than thinking from same iris for the threshold value, mutual ratio passes through, greatly
In thinking from different irises, mutually than failure for the threshold value.
Step S140:, will note if the frequency of failure is less than preset times and the iris feature of record reaches predetermined number (N)
Iris feature of the iris feature of record as N number of iris image；Otherwise, iris feature is extracted from several iris images again
(step S120), or reacquire several iris images (step S110).
The embodiment of the present invention mutually compares the multiframe iris image feature of extraction, mutual than recording in the case where passing through
The feature of the multiple image obtains several satisfactory features, mutually preferable than the quality of the N number of iris feature passed through, and
And it is more consistent.
In embodiments of the present invention, it can be and mutually compared two-by-two again after extracting several iris features, is also possible to
Mutually compared after extracting an iris feature with the iris feature before mutually than passing through, be exemplified below:
A) several iris images of same user are obtained.
B) several iris images are pre-processed.
C) iris feature for extracting the first width iris image, caches the iris feature after extracting successfully, iris feature note
Iris feature number n for Fea1, caching is denoted as 1.The first width iris image can be first frame image, be also possible to
The piece image optionally come out in multiple iris images.
D) iris feature for extracting the second width iris image, is extracted after iris feature success and the first width iris image
Feature Fea1 is compared, if mutually ratio passes through, caches iris feature Fea2, and the iris feature number n of caching adds 1, if mutually than losing
It loses, then record primary the case where failing, is denoted as count_fail=1.The second width iris image can be the second frame figure
Picture is also possible to the piece images different from the first width iris image optionally come out in multiple iris images.
E) repeat to continue the step in d), extract third and fourth, the iris features of five ... width iris images, it is special to extract iris
It, can be with the mutual ratio of one or more of the iris feature of above-mentioned caching, if mutually than failure, cumulative count_ after levying successfully
The value of fail, if mutually comparing successfully, just caching is mutually than successful iris feature, is successively denoted as Fea3, Fea4 ..., and by caching
Iris feature number n is cumulative, backward and so on.Described third and fourth, five ... width iris images can be third and fourth, five ...
Frame image is also possible to a series of width images different from iris image above-mentioned optionally come out in multiple iris images.
F) value for judging count_fail and characteristic n illustrates that initial characteristics Fea1 is asked as count_fail > 10
Topic, empties the feature of all cachings；It, can be from step when undrawn iris image remaining in several iris images is more
C) start, choose a width iris image again, extract initial iris feature；When undrawn rainbow remaining in several iris images
When film image is less, iris image can be reacquired, that is, be equivalent to and to restart to register since step a).
Illustrate N=7, extracts Fea1, Fea2, Fea3, Fea4, Fea5, Fea6, Fea7 feature altogether at this time.
The Gabor binary-coding feature that the iris feature of the embodiment of the present invention is 2048, wherein first 1024 are encoded to
Noise template, the encoded radio of noise template are that 1 representative is effective, represent iris and sclera portion, and the encoded radio of noise template is 0
It is invalid to represent, and represents the noise section of iris, noise template is denoted as [Noi1, Noi2, Noi3, Noi4 ... ... .Noi1024]；Afterwards
1024 are encoded to the coding of iris feature 0,1, are denoted as [Cod1, Cod2, Cod3 ... ... Cod1024].
Based on 2048 Gabor binary-coding features, by taking Fea1 as an example, noise template are as follows:
Fea1_N1,Fea1_N2,Fea1_N3,……,Fea1_N1024；
Iris feature coding are as follows:
Fea1_C1,Fea1_C2,Fea1_C3,……,Fea1_C1024
When N=7, the Noi1 of 7 iris features is respectively as follows:
Fea1_N1, Fea2_N1, Fea3_N1, Fea4_N1, Fea5_N1, Fea6_N1, Fea7_N1；
The Cod1 of 7 iris features is respectively as follows:
Fea1_C1, Fea2_C1, Fea3_C1, Fea4_C1, Fea5_C1, Fea6_C1, Fea7_C1.
The circular of composite noise template are as follows: to the encoded radios of each identical bits of N number of noise template respectively into
Capable or operation obtains composite noise template.
A) the 0 of Noi1,1 value, progress or operation are determined, specifically:
N1=Fea1_N1 | | Fea2_N1 | | Fea3_N1 | | Fea4_N1 | | Fea5_N1 | | Fea6_N1 | | Fea7_N1；
If calculated result is 1, Noi1 1, effectively, opposite Noi1 is 0, in vain.
B) a) step is repeated, determines Noi2, the value that Noi3, Noi4 ... ... are .Noi1024.
Based on 2048 Gabor binary-coding features, calculation method (step S300) packet of iris feature coding is synthesized
It includes:
Step S310: when the encoded radio in a certain position of composite noise template is 1, all noise templates that this is 1 are found out.
Step S320: it counts corresponding iris feature coding 0,1 value on the correspondence position of this of the noise template found out and goes out
Existing number.
Step S330: if the number that 0 number >=1 occurred occurs, iris feature coding is synthesized in the value of the correspondence position
It is 0, otherwise, value of the synthesis iris feature coding in the correspondence position is 1.
By taking 7 iris features above-mentioned as an example, calculation method is as follows:
A) in the case where Noi1 is 1, for this 7 features, when Fea1_N1 is 1, statistics Fea1_C1 occurs 0,1
Number, and so on, work as Fea2_N1, Fea3_N1, Fea4_N1, Fea5_N1, Fea6_N1 are counted respectively when Fea7_N1 is 1
There is 0,1 number in Fea2_C1, Fea3_C1, Fea4_C1, Fea5_C1, Fea6_C1, Fea7_C1.
B) when 0 number > 1 number, then the value of Cod1 be 0；
When the number of 1 number > 0, then the value of Cod1 is 1；
When the number of 0 number=1, then the value of Cod1 be 0 (initial value, in practical application,
In this case the probability occurred is seldom).
Actually it is exemplified below:
Fea1_N1=0, Fea2_N1=1, Fea3_N1=1,
Fea4_N1=0, Fea5_N1=1, Fea6_N1=1,
Fea7_N1=1
Wherein Fea2_N1, Fea3_N1, Fea5_N1, Fea6_N1, Fea7_N1 1, then only to Fea2_C1, Fea3_C1,
Fea5_C1, Fea6_C1, Fea7_C1 carry out 0,1 statistics, remaining 2 do not consider.The number that such as 1 number is 4,0 is 1, because
4 > 1, so the value of Cod1 is 1；
C) above-mentioned a)-b is repeated) the step of, obtain Cod2, the value of Cod3 ... ... .Cod1024.
Finally according to Noi1, Noi2 ... ... .Noi1024 and Cod1, the value of Cod2 ... ... .Cod1024 obtains synthesis rainbow
Film feature templates.
Embodiment 2:
The embodiment of the invention provides a kind of synthesizers of iris feature.
As shown in Fig. 2, the device includes:
Module 11 is obtained, for obtaining the iris feature for meeting N number of iris image of preset condition, iris feature includes making an uproar
Acoustic mode plate and iris feature coding, the encoded radio that noise template is each represent the validity of this.
A composite noise template is calculated for the noise template according to N number of iris feature in computing module 12,
In, the region of the significance bit composition of composite noise template is the fusion in the region that the significance bit of N number of noise template forms.
Statistical module 13 is obtained for being counted according to iris feature coding of the composite noise template to N number of iris feature
It is encoded to a synthesis iris feature；Wherein, effectively the corresponding iris feature coding of all noise templates exists on same position
The most encoded radio of frequency of occurrence is to synthesize iris feature coding in the encoded radio of the correspondence position on the correspondence position of this.
Synthesis module 14, for obtaining a synthesis iris according to composite noise template and synthesis iris feature coded combination
Feature.
The embodiment of the present invention obtains a synthesis iris feature by the iris feature of multiple iris images, wherein by multiple
It merges to obtain the noise template (i.e. composite noise template) of synthesis iris feature, and root in the effective coverage of iris feature noise template
It is encoded according to multiple iris features and calculates the corresponding iris feature coding of composite noise template (i.e. synthesis iris feature coding), increased
The effective coverage area of iris.And it is when calculating synthesis iris feature coding, all effective noise templates are corresponding
The iris feature coding volume of the most encoded radio of frequency of occurrence as synthesis iris feature coding in the position in same position
Code value prevents feature contingency caused by noise, improves the quality of iris feature, reduces misclassification rate.
Above-mentioned acquisition module includes:
Acquiring unit, for obtaining several iris images of same user.
Extraction unit, for extracting several iris features from several iris images.
Mutually than unit, for mutually being compared several iris features, if mutually ratio passes through, the iris feature passed through is recorded, if
Mutually than failure, the frequency of failure is recorded.
Comparing unit will if the iris feature for the frequency of failure to be less than preset times and record reaches predetermined number
Iris feature of the iris feature of record as N number of iris image.
The Gabor binary-coding feature that the iris feature of the present embodiment is 2048, wherein first 1024 are encoded to noise
Template, latter 1024 are encoded to iris feature coding, and the encoded radio of noise template is that 1 representative is effective, and it is invalid to represent for 0.
Above-mentioned computing module is used for: carrying out respectively to the encoded radio of each identical bits of N number of noise template or operation obtains
Composite noise template.
Above-mentioned statistical module includes:
Searching unit, for the encoded radio in a certain position of composite noise template be 1 when, find out this be 1 all noises
Template.
Statistic unit encodes 0,1 on the correspondence position of this for counting the corresponding iris feature of noise template found out
It is worth the number occurred.
Determination unit synthesizes iris feature coding in the correspondence position if the number that number >=1 occurred for 0 occurs
Value be 0, otherwise, synthesis iris feature coding the correspondence position value be 1.
The technical effect and preceding method embodiment phase of device provided by the embodiment of the present invention, realization principle and generation
Together, to briefly describe, Installation practice part does not refer to place, can refer to corresponding contents in preceding method embodiment.Affiliated neck
The technical staff in domain can be understood that, for convenience and simplicity of description, the device of foregoing description and the specific work of unit
Make process, the corresponding process during reference can be made to the above method embodiment, details are not described herein.
In embodiment provided by the present invention, it should be understood that disclosed device and method, it can be by others side
Formula is realized.The apparatus embodiments described above are merely exemplary, for example, the division of the unit, only one kind are patrolled
Function division is collected, there may be another division manner in actual implementation, in another example, multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some communication interfaces, device or unit
It connects, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in embodiment provided by the invention can integrate in one processing unit, it can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that an equipment (can be individual calculus
Machine, server, the network equipment or embedded device etc.) execute all or part of each embodiment the method for the present invention
Step.And storage medium above-mentioned include: USB flash disk, it is mobile hard disk, read-only memory (ROM, Read-Only Memory), random
Access various Jie that can store program code such as memory (RAM, Random Access Memory), magnetic or disk
Matter.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention.Should all it cover in protection of the invention
Within the scope of.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of synthetic method of iris feature, which is characterized in that the described method includes:
The iris feature for meeting N number of iris image of preset condition is obtained, the iris feature includes that noise template and iris are special
The encoded radio of assemble-publish code, each of the noise template represents the validity of this；
A composite noise template is calculated according to the noise template of N number of iris feature, wherein the composite noise template
The region of significance bit composition is the fusion in the region that the significance bit of N number of noise template forms；
It is counted according to iris feature coding of the composite noise template to N number of iris feature, obtains a synthesis iris
Feature coding；Wherein, effectively the corresponding iris feature of all noise templates encodes on the correspondence position of this on same position
The most encoded radio of frequency of occurrence is to synthesize iris feature coding in the encoded radio of the correspondence position；
A synthesis iris feature is obtained according to composite noise template and synthesis iris feature coded combination.
2. the synthetic method of iris feature according to claim 1, which is characterized in that the acquisition meets preset condition
The iris feature of N number of iris image, the iris feature include noise template and iris feature coding, and the noise template is each
The encoded radio of position represents the validity of this, comprising:
Obtain several iris images of same user；
Several iris features are extracted from several iris images；
Several iris features are mutually compared, if mutually ratio passes through, record the iris feature passed through, if mutually than failure, record failure
Number；
If the frequency of failure be less than preset times and record iris feature reach predetermined number, using the iris feature of record as
The iris feature of N number of iris image.
3. the synthetic method of iris feature according to claim 1 or 2, which is characterized in that the iris feature is 2048
The Gabor binary-coding feature of position, wherein first 1024 are encoded to noise template, latter 1024 are encoded to iris feature coding,
The encoded radio of noise template is that 1 representative is effective, and it is invalid to represent for 0.
4. the synthetic method of iris feature according to claim 3, which is characterized in that described according to N number of iris feature
A composite noise template is calculated in noise template, wherein the region of the significance bit composition of the composite noise template is N number of
The fusion in the region of the significance bit composition of noise template, comprising:
The encoded radio of each identical bits of N number of noise template is carried out respectively or operation obtains composite noise template.
5. the synthetic method of iris feature according to claim 3, which is characterized in that described according to the composite noise mould
Plate counts the iris feature coding of N number of iris feature, obtains a synthesis iris feature coding；Wherein, in same position
Above the corresponding iris feature coding most encoded radio of frequency of occurrence on the correspondence position of this of effective all noise templates is
Encoded radio for synthesis iris feature coding in the correspondence position, comprising:
When encoded radio in a certain position of composite noise template is 1, all noise templates that this is 1 are found out；
It counts the corresponding iris feature of the noise template found out and encodes the number that 0,1 value occurs on the correspondence position of this；
If the number that 0 number >=1 occurred occurs, synthesizing value of the iris feature coding in the correspondence position is 0, otherwise, synthesis
It is 1 that iris feature, which encodes the value in the correspondence position,.
6. a kind of synthesizer of iris feature, which is characterized in that described device includes:
Module is obtained, for obtaining the iris feature for meeting N number of iris image of preset condition, the iris feature includes noise
Template and iris feature coding, the encoded radio of each of the noise template represent the validity of this；
A composite noise template is calculated for the noise template according to N number of iris feature, wherein described in computing module
The region of the significance bit composition of composite noise template is the fusion in the region that the significance bit of N number of noise template forms；
Statistical module is obtained for being counted according to iris feature coding of the composite noise template to N number of iris feature
One synthesis iris feature coding；Wherein, effectively the corresponding iris feature of all noise templates is encoded at this on same position
The most encoded radio of frequency of occurrence is to synthesize iris feature coding in the encoded radio of the correspondence position on the correspondence position of position；
Synthesis module, for obtaining a synthesis iris feature according to composite noise template and synthesis iris feature coded combination.
7. the synthesizer of iris feature according to claim 6, which is characterized in that the acquisition module includes:
Acquiring unit, for obtaining several iris images of same user；
Extraction unit, for extracting several iris features from several iris images；
Mutually than unit, for mutually being compared several iris features, if mutually ratio passes through, the iris feature passed through is recorded, if mutually ratio
Failure records the frequency of failure；
Comparing unit will record if the iris feature for the frequency of failure to be less than preset times and record reaches predetermined number
Iris feature of the iris feature as N number of iris image.
8. the synthesizer of iris feature according to claim 6 or 7, which is characterized in that the iris feature is 2048
The Gabor binary-coding feature of position, wherein first 1024 are encoded to noise template, latter 1024 are encoded to iris feature coding,
The encoded radio of noise template is that 1 representative is effective, and it is invalid to represent for 0.
9. the synthesizer of iris feature according to claim 8, which is characterized in that the computing module is used for:
The encoded radio of each identical bits of N number of noise template is carried out respectively or operation obtains composite noise template.
10. the synthesizer of iris feature according to claim 8, which is characterized in that the statistical module includes:
Searching unit, for the encoded radio in a certain position of composite noise template be 1 when, find out this be 1 all noise templates；
Statistic unit goes out for counting corresponding iris feature coding 0,1 value on the correspondence position of this of noise template found out
Existing number；
Determination unit synthesizes iris feature coding in the value of the correspondence position if the number that number >=1 occurred for 0 occurs
It is 0, otherwise, value of the synthesis iris feature coding in the correspondence position is 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810404512.2A CN110414300B (en) | 2018-04-28 | 2018-04-28 | Method and device for synthesizing iris characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810404512.2A CN110414300B (en) | 2018-04-28 | 2018-04-28 | Method and device for synthesizing iris characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110414300A true CN110414300A (en) | 2019-11-05 |
| CN110414300B CN110414300B (en) | 2021-07-06 |
Family
ID=68357207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810404512.2A Active CN110414300B (en) | 2018-04-28 | 2018-04-28 | Method and device for synthesizing iris characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110414300B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5291560A (en) * | 1991-07-15 | 1994-03-01 | Iri Scan Incorporated | Biometric personal identification system based on iris analysis |
| CN101894256A (en) * | 2010-07-02 | 2010-11-24 | 西安理工大学 | Iris identification method based on odd-symmetric 2D Log-Gabor filter |
| US20110075892A1 (en) * | 2009-09-25 | 2011-03-31 | International Business Machines Corporation | System and method for generating and employing short length iris codes |
| CN102521575A (en) * | 2011-12-16 | 2012-06-27 | 北京天诚盛业科技有限公司 | Iris identification method based on multidirectional Gabor and Adaboost |
| CN103577813A (en) * | 2013-11-25 | 2014-02-12 | 中国科学院自动化研究所 | Information fusion method for heterogeneous iris recognition |
| CN105279492A (en) * | 2015-10-22 | 2016-01-27 | 北京天诚盛业科技有限公司 | Iris identification method and device |
| CN107256385A (en) * | 2017-05-22 | 2017-10-17 | 西安交通大学 | Infrared iris Verification System and method based on 2D Log Gabor Yu composite coding method |
-
2018
- 2018-04-28 CN CN201810404512.2A patent/CN110414300B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5291560A (en) * | 1991-07-15 | 1994-03-01 | Iri Scan Incorporated | Biometric personal identification system based on iris analysis |
| US20110075892A1 (en) * | 2009-09-25 | 2011-03-31 | International Business Machines Corporation | System and method for generating and employing short length iris codes |
| CN101894256A (en) * | 2010-07-02 | 2010-11-24 | 西安理工大学 | Iris identification method based on odd-symmetric 2D Log-Gabor filter |
| CN102521575A (en) * | 2011-12-16 | 2012-06-27 | 北京天诚盛业科技有限公司 | Iris identification method based on multidirectional Gabor and Adaboost |
| CN103577813A (en) * | 2013-11-25 | 2014-02-12 | 中国科学院自动化研究所 | Information fusion method for heterogeneous iris recognition |
| CN105279492A (en) * | 2015-10-22 | 2016-01-27 | 北京天诚盛业科技有限公司 | Iris identification method and device |
| CN107256385A (en) * | 2017-05-22 | 2017-10-17 | 西安交通大学 | Infrared iris Verification System and method based on 2D Log Gabor Yu composite coding method |
Non-Patent Citations (1)
| Title |
|---|
| 李海青等: "虹膜识别技术进展与趋势", 《信息安全研究》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110414300B (en) | 2021-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zeng et al. | A survey of face recognition techniques under occlusion | |
| Rathgeb et al. | Towards cancelable multi-biometrics based on bloom filters: a case study on feature level fusion of face and iris | |
| Gomez-Barrero et al. | Unlinkable and irreversible biometric template protection based on bloom filters | |
| Ngo et al. | Biometric hash: high-confidence face recognition | |
| Dong et al. | Iris matching based on personalized weight map | |
| US20190362058A1 (en) | Face unlocking method and device, electronic device, and computer storage medium | |
| Teoh et al. | Personalised cryptographic key generation based on FaceHashing | |
| Rathgeb et al. | Secure iris recognition based on local intensity variations | |
| Gomez-Barrero et al. | Protected facial biometric templates based on local gabor patterns and adaptive bloom filters | |
| Connie et al. | PalmHashing: a novel approach for dual-factor authentication | |
| Nanni et al. | Empirical tests on biohashing | |
| Rathgeb et al. | Unlinkable improved multi-biometric iris fuzzy vault | |
| Bours et al. | Continuous authentication using biometric keystroke dynamics | |
| Findling et al. | Mobile match-on-card authentication using offline-simplified models with gait and face biometrics | |
| Paulini et al. | Multi-Bit Allocation: Preparing Voice Biometrics for Template Protection. | |
| Cho et al. | GAN-based blur restoration for finger wrinkle biometrics system | |
| Chan et al. | Face recognition by facial attribute assisted network | |
| Qin et al. | Vulnerabilities of unattended face verification systems to facial components-based presentation attacks: An empirical study | |
| CN110414300A (en) | Method and device for synthesizing iris characteristics | |
| Stokkenes et al. | Biometric transaction authentication using smartphones | |
| Sujitha et al. | Highly secure palmprint based biometric template using fuzzy vault | |
| Sadhya et al. | A locality sensitive hashing based approach for generating cancelable fingerprints templates | |
| Tian et al. | Personal identity recognition approach based on iris pattern | |
| Luo et al. | A robust single-sensor face and iris biometric identification system based on multimodal feature extraction network | |
| Chin et al. | Multimodal biometrics based bit extraction method for template security |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Method and device for synthesizing iris features Effective date of registration: 20220228 Granted publication date: 20210706 Pledgee: China Construction Bank Corporation Xiongxian sub branch Pledgor: BEIJING EYECOOL TECHNOLOGY Co.,Ltd. Registration number: Y2022990000113 |
|
| CP02 | Change in the address of a patent holder | ||
| CP02 | Change in the address of a patent holder |
Address after: 071800 Beijing Tianjin talent home (Xincheng community), West District, Xiongxian Economic Development Zone, Baoding City, Hebei Province Patentee after: BEIJING EYECOOL TECHNOLOGY Co.,Ltd. Address before: 100085 804, 8th floor, building 1, yard 1, shangdishi street, Haidian District, Beijing Patentee before: BEIJING EYECOOL TECHNOLOGY Co.,Ltd. |