CN105488487B - A kind of iris locating method and device - Google Patents
A kind of iris locating method and device Download PDFInfo
- Publication number
- CN105488487B CN105488487B CN201510905787.0A CN201510905787A CN105488487B CN 105488487 B CN105488487 B CN 105488487B CN 201510905787 A CN201510905787 A CN 201510905787A CN 105488487 B CN105488487 B CN 105488487B
- Authority
- CN
- China
- Prior art keywords
- iris
- point
- boundary
- coordinate
- hot spot
- 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.)
- Active
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
-
- 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)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a kind of iris locating method and device, this method includes:Obtain iris image;Spot detection is carried out to the iris image, obtains the hot spot point of the iris image;Pretreatment operation is carried out to the iris image according to the hot spot point detected;According to the gradient consistency feature of pupil to iris, the internal boundary points of iris are obtained;Based on gray scale gradual change and gradient consistency feature, the outer boundary point of iris is obtained;By the internal boundary points and the outer boundary point, the inner boundary and outer boundary of the iris are fitted, to complete the positioning to the iris.Iris locating method and device provided by the present invention, the outer edge of iris can be quickly and accurately positioned, efficiently solve that Iris Location speed is slow, the low problem of non-ideal iris image positioning accuracy provides accurate Iris Location result for subsequent characteristic matching.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of iris locating method and device.
Background technology
Biometrics identification technology makes because accuracy rate is high, will not forget or loses, is not easy to forge or be stolen, carry
It is used widely with convenient.In biometrics identification technology, fingerprint be easy forge and steal, face easily by it is sick and wounded and from
Body growth variation.Largely scientific investigations showed that iris has uniqueness, stability, can adopt as a kind of important biological characteristic
The advantages that collection property, non-infringement property.These advantages make place of the iris recognition especially suitable for needing authentication.
Iris authentication system flow is:Image Acquisition, image preprocessing, feature extraction coding match certification.Wherein iris
Positioning is the important link during iris preprocessing, the effective coverage that iris is accurately positioned out be subsequent process smoothly into
Capable basis.Since harvester is limited by hardware, light environment, the iris image of acquisition suffers from different interference,
Such as details is fuzzy, contrast is low, human eye occlusion, these all cause difficulty to Iris Location.
Classical iris locating method is all based on round structure, and the integral differential ring of such as Daugman based on gradient is based on
The Hough transform method of the Wildes of boundary point, least-squares algorithm, Pull&Push algorithms.
Integral differential ring is to position iris edge, Hough transform using the maximum value for calculating whole circumference gradient integral
Loop truss algorithm is with the most centers of circle of votes are obtained under Radius in search parameter space to position iris edge, minimum two
Multiplication is that the error minimum positioning iris with circle structure, Pull&Push algorithms are formed using Hooke's law using boundary point
Elastic force reaches the center of circle to position iris by successive ignition.
Although above method all obtains good effect in Iris Location, all there are many defects, wherein integrating micro-
Point ring computational efficiency is low, is easily influenced with illumination by blocking;To not rounded edge fitting location of mistake and meter easily occur for Hough transform
It is slow to calculate speed, time complexity is high;Least square fitting and Pull&Push require height to the selection of boundary point, are not suitable for low
Quality noise iris image positions.
In conclusion existing Iris-orientation Algorithm still has prodigious room for improvement, quick accurate robust how is realized
Iris Location be still a problem urgently to be resolved hurrily.
Invention content
The object of the present invention is to provide a kind of iris locating method and devices, it is therefore intended that solution in the prior art cannot be fast
The problem of speed accurately positions iris.
In order to solve the above technical problems, the present invention provides a kind of iris locating method, including:
Obtain iris image;
Spot detection is carried out to the iris image, obtains the hot spot point of the iris image;
Pretreatment operation is carried out to the iris image according to the hot spot point detected;
According to the gradient consistency feature of pupil to iris, the internal boundary points of iris are obtained;
Based on gray scale gradual change and gradient consistency feature, the outer boundary point of iris is obtained;
By the internal boundary points and the outer boundary point, the inner boundary and outer boundary of the iris are fitted,
To complete the positioning to the iris.
Optionally, described to carry out spot detection to the iris image, the hot spot point for obtaining the iris image includes:
By preset spot detection operator, convolution algorithm is carried out to the gray value high point of the iris image;
The big point coordinates of convolution value is obtained, judges whether the point coordinates is light according to intensity profile around the point coordinates
Spot.
Optionally, the preset spot detection operator is the disk that radius is 4, value be just, peripheral value be it is negative,
Remaining position zero padding so that the spot detection operator sum of zero.
Optionally, the hot spot point that the basis detects carries out pretreatment operation to the iris image:
The iris image is cut according to the hot spot point;
Morphological erosion is carried out to the iris image and rebuilds operation;
Centered on the coordinate of the hot spot point, polar coordinates expansion is carried out.
Optionally, the gradient consistency feature according to pupil to iris, the internal boundary points for obtaining iris include:
Edge detection, the nearest edge coordinate point of each radial acquisition are carried out to the image of polar coordinates expansion;
Calculate the gradient value at the edge coordinate point:
Grad (x, y)=I (x+1, y)-I (x-1, y);
According to the gradient consistency feature of pupil to iris, noise spot boundary point is excluded, the inner boundary of the iris is obtained
Point.
Optionally, described to be based on gray scale gradual change and gradient consistency feature, the outer boundary point for obtaining iris includes:
It calculates outside pupil radium, the Grad Grad (x, y) of radial [0,60] and [120,180] records the ladder
The maximum value GradMax (x, y) of angle value and the coordinate (x, y) of corresponding position;
Calculate the average gray of the point of continuous preset quantity 2n+1:
With IEFor thresholding, binaryzation is carried out to the point of the preset quantity:
According to the feature of the gray value gradual change of iris to sclera, by as i > 0 B (x+i, y)=1 exclude noise side
Boundary, to obtain correct boundary coordinate (x, y);
Meet the coordinate points that gradient is consistent and gray scale is progressive in the correct boundary coordinate or so radial search, each
The nearest coordinate points of the radial correct boundary coordinate of selected distance are iterated as new boundary point, and item is preset until meeting
Until part.
Optionally, described by the internal boundary points and the outer boundary point, the inner boundary to the iris and outside
Boundary be fitted including:
By least variance method and weights Hough transformation method, the inner boundary and outer boundary of the iris are intended
It closes.
Optionally, by least variance method and weights Hough transformation method, the inner boundary of the iris is fitted
Including:
The hot spot point coordinates is calculated to the distance value of the internal boundary points, calculates the variance of the distance value;
Using stochastic gradient descent method, center is set to be moved towards the direction of variance minimum, iteration is repeatedly to obtain the center of circle;
After obtaining the center of circle, three dimensions is become one-dimensional by Hough transformation, adjusts radius, is calculatedIts
In, ri1For the distance of each internal boundary points to the center of circle, r1For radius, ωi1For the boundary point voting stake;
Record works as ∑ ωi1R when maximum1, it is determined as inner circle radius.
Optionally, by least variance method and weights Hough transformation method, the outer boundary of the iris is fitted
Including:
Center coordinate of eye pupil is calculated to the distance value of the outer boundary point, calculates the variance of the distance value;
Using stochastic gradient descent method, center is set to be moved towards the direction of variance minimum, iteration is repeatedly to obtain the center of circle;
After obtaining the center of circle, three dimensions is become one-dimensional by Hough transformation, adjusts radius, is calculatedIts
In, ri2For each outer boundary point to the distance in the center of circle, r2For radius, ωi2For the boundary point voting stake;
Record works as ∑ ωi2R when maximum2, it is determined as exradius.
The present invention also provides a kind of Iris Location devices, including:
Acquisition module, for obtaining iris image;
Detection module obtains the hot spot point of the iris image for carrying out spot detection to the iris image;
Preprocessing module, for carrying out pretreatment operation to the iris image according to the hot spot point detected;
First acquisition module obtains the internal boundary points of iris for the gradient consistency feature according to pupil to iris;
Second acquisition module obtains the outer boundary point of iris for being based on gray scale gradual change and gradient consistency feature;
Locating module, for by the internal boundary points and the outer boundary point, inner boundary to the iris and outside
Boundary is fitted, to complete the positioning to the iris.
Iris locating method and device provided by the present invention, by obtaining iris image;Hot spot is carried out to iris image
Detection, obtains the hot spot point of iris image;Pretreatment operation is carried out to iris image according to the hot spot point detected;According to pupil
To the gradient consistency feature of iris, the internal boundary points of iris are obtained;Based on gray scale gradual change and gradient consistency feature, obtain
The outer boundary point of iris;And by internal boundary points and outer boundary point, the inner boundary and outer boundary of iris are fitted, with complete
The positioning of pairs of iris.Iris locating method and device provided by the present invention, can be quickly and accurately positioned the inside and outside of iris
Edge, efficiently solves that Iris Location speed is slow, the low problem of non-ideal iris image positioning accuracy, is subsequent feature
With the accurate Iris Location result of offer.
Description of the drawings
It, below will be to embodiment or existing for the clearer technical solution for illustrating the embodiment of the present invention or the prior art
Attached drawing is briefly described needed in technology description, it should be apparent that, the accompanying drawings in the following description is only this hair
Some bright embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of flow chart of specific implementation mode of iris locating method provided by the present invention;
Fig. 2 is the flow chart of spot detection in iris locating method provided in an embodiment of the present invention;
Fig. 3 is the flow chart for the internal boundary points that iris is obtained in iris locating method provided in an embodiment of the present invention;
Fig. 4 is the flow chart for the outer boundary point that iris is obtained in iris locating method provided in an embodiment of the present invention;
Fig. 5 is the process flow being fitted to the inner boundary of iris in iris locating method provided in an embodiment of the present invention
Figure;
Fig. 6 is the process flow being fitted to the outer boundary of iris in iris locating method provided in an embodiment of the present invention
Figure;
Fig. 7 is the structure diagram of Iris Location device provided in an embodiment of the present invention.
Specific implementation mode
Iris authentication system is partitioned into effective iris region by the iris image obtained to imaging device, with database
In iris image matching, complete verification to user identity.Core of the invention there is provided a kind of iris locating method and
Device.
In order to enable those skilled in the art to better understand the solution of the present invention, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.Obviously, described embodiments are only a part of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Lower obtained every other embodiment, shall fall within the protection scope of the present invention.
A kind of flow chart of specific implementation mode of iris locating method provided by the present invention is as shown in Figure 1, this method
Including:
Step S101:Obtain iris image;
Step S102:Spot detection is carried out to the iris image, obtains the hot spot point of the iris image;
Step S103:Pretreatment operation is carried out to the iris image according to the hot spot point detected;
Specifically, carrying out pretreated process to iris image can be:
The iris image is cut according to the hot spot point;Such as take the box of radius 150 that can correctly cut out in hot spot coordinate
Cut image.
Morphological erosion is carried out to the iris image and rebuilds operation;If selective etching window is the disk that radius is 8,
Then image is rebuild, hot spot can be filled.
Centered on the coordinate of the hot spot point, polar coordinates expansion is carried out.
Step S104:According to the gradient consistency feature of pupil to iris, the internal boundary points of iris are obtained;
Step S105:Based on gray scale gradual change and gradient consistency feature, the outer boundary point of iris is obtained;
Step S106:By the internal boundary points and the outer boundary point, to the inner boundary and outer boundary of the iris
It is fitted, to complete the positioning to the iris.
Iris locating method provided by the present invention, by obtaining iris image;Spot detection is carried out to iris image, is obtained
To the hot spot point of iris image;Pretreatment operation is carried out to iris image according to the hot spot point detected;According to pupil to iris
Gradient consistency feature, obtain the internal boundary points of iris;Based on gray scale gradual change and gradient consistency feature, iris is obtained
Outer boundary point;And according to internal boundary points and outer boundary point, the inner boundary and outer boundary of iris are fitted, to complete to rainbow
The positioning of film.Iris locating method provided by the present invention can be quickly and accurately positioned the outer edge of iris, effectively solve
Iris Location of having determined speed is slow, and the low problem of non-ideal iris image positioning accuracy provides accurately for subsequent characteristic matching
Iris Location result.
Usual iris authentication system uses infrared light to be used as light source, and with the advantages such as night vision, non-stimulated, but infrared LED can be
At hot spot, which can influence subsequently to position pupil expert.The process of spot detection is further described below, such as Fig. 2
Shown in the flow chart of spot detection, which includes:
Step S201:By preset spot detection operator, convolution fortune is carried out to the gray value high point of the iris image
It calculates;
Specifically, it is 11 × 11 that preset spot detection operator, which can be size, and outermost is negative value, and it is 5 to embed radius
Disk, be worth for just, remaining mends 0, and it is 0 to make the operator summation.
Above-mentioned convolution algorithm refers to, and is covered in the high bright spot of image with the operator center, finds out operator and image corresponding points ash
The dot product of angle value and, as convolution results of the central point.
Step S202:The big point coordinates of convolution value is obtained, judges that the point is sat according to intensity profile around the point coordinates
Whether mark is hot spot point.
The big point coordinates of convolution value is obtained, due to spot size problem, convolution may Wrong localization, it is also necessary to these
Point analysis intensity profile around it, if being with the low point of a circle gray value outside, and center gray value is high, is judged as being really light
Spot.
The process of the internal boundary points to obtaining iris is described in detail below, please refers to the inner boundary that Fig. 3 obtains iris
The flow chart of point, the process include:
Step S301:Canny edge detections are carried out to the image of polar coordinates expansion, the nearest edge of each radial acquisition is sat
Punctuate;
Step S302:Calculate the gradient value at the edge coordinate point:
Grad (x, y)=I (x+1, y)-I (x-1, y);
According to the gradient consistency feature of pupil to iris, noise spot boundary point is excluded, the inner boundary of the iris is obtained
Point.
According to the gradient consistency principle of pupil to iris, the Grad approximately equal of marginal point can effectively exclude eyelash
Hair, edge breaks fail to fill the noise margins point such as complete hot spot edge.
On the basis of the above embodiments, as shown in the flow chart of the outer boundary point of Fig. 4 acquisition irises, which includes:
Step S401:It calculates outside pupil radium, the Grad Grad (x, y) of radial [0,60] and [120,180], record
Under the maximum value GradMax (x, y) of the Grad and the coordinate (x, y) of corresponding position;
Step S402:Calculate the average gray of the point of continuous preset quantity 2n+1:
Specifically, the average gray of radially continuous 11 points of each coordinate points I (x, y) can be calculated:
Step S403:With IEFor thresholding, binaryzation is carried out to the point of the preset quantity:
Specifically, to 11 binaryzations,
Step S404:According to the feature of the gray value gradual change of iris to sclera, by as i > 0 B (x+i, y)=1 arrange
Except noise margin, to obtain correct boundary coordinate (x, y);
Since the gray value of iris to sclera is progressive formation, i.e., correct marginal point meet as i≤0 B (x+i, y)=
0, the B (x+i, y)=1 as i > 0 exclude noise margin with this and obtain correct boundary coordinate (x, y).
Step S405:Meet the seat that gradient is consistent and gray scale is progressive in the correct boundary coordinate or so radial search
Punctuate, the nearest coordinate points of the correct boundary coordinate of each radial direction selected distance are iterated, Zhi Daoman as new boundary point
Until sufficient preset condition.
Preset condition can be specially:360 degree are all sought all over or not new boundary point.
Step intends the inner boundary and outer boundary of the iris by the internal boundary points and the outer boundary point
Closing to be specially:
By least variance method and weights Hough transformation method, the inner boundary and outer boundary of the iris are intended
It closes.
Below to by least variance method and weights Hough transformation method, being fitted to the inner boundary of the iris
Process is described further, and shown in the process flow diagram flow chart being fitted to the inner boundary of iris such as Fig. 5, which includes:
Step S501:The hot spot point coordinates is calculated to the distance value of the internal boundary points, calculates the side of the distance value
Difference;
According to the internal boundary points coordinate that the step S102 hot spot coordinate points obtained and step S104 obtain, calculates hot spot and sit
The distance for marking internal boundary points calculates the variance of these distance values.
Step S502:Using stochastic gradient descent method, center is made to be moved towards the direction of variance minimum, iteration is repeatedly to obtain
The center of circle;
Since boundary meets round structure, closer to the pupil center of circle, which obtains that variance is smaller, i.e., the variance is one convex
Function.With stochastic gradient descent method, center is made to be moved towards the direction of variance minimum, iteration repeatedly reaches the center of circle.
Step S503:After obtaining the center of circle, three dimensions is become one-dimensional by Hough transformation, adjusts radius, is calculatedWherein, ri1For the distance of each internal boundary points to the center of circle, r1For radius, ωi1For the boundary point voting stake;
Step S504:Record works as ∑ ωi1R when maximum1, it is determined as inner circle radius.
Similarly, shown in the process flow diagram flow chart being fitted to the outer boundary of iris such as Fig. 6, the outer boundary of iris is intended
The process of conjunction specifically includes:
Step S601:Center coordinate of eye pupil is calculated to the distance value of the outer boundary point, calculates the variance of the distance value;
Step S602:Using stochastic gradient descent method, center is made to be moved towards the direction of variance minimum, iteration is repeatedly to obtain
The center of circle;
Step S603:After obtaining the center of circle, three dimensions is become one-dimensional by Hough transformation, adjusts radius, is calculatedWherein, ri2For each outer boundary point to the distance in the center of circle, r2For radius, ωi2For the boundary point voting stake;
Step S604:Record works as ∑ ωi2R when maximum2, it is determined as exradius.
Iris locating method provided by the invention is of great significance to the fast robust positioning of low quality iris image,
Advantage is as follows:
(1) present invention makes full use of hot spot characteristic in pupil, the coarse positioning pupil position being exceedingly fast, fixed for inward flange thereafter
Position provides initial center;
(2) present invention can effectively exclude the noises such as eyelashes iris texture using the gradient consistency principle of pupil to iris
Boundary, is accurately positioned iris internal boundary points, and accurate boundary point is conducive to the fitting of Hough transformation thereafter;
(3) present invention utilizes least variance method, can fast search arrive pupil center, by the three-dimensional parameter of Hough transformation sky
Between be reduced to one-dimensional, to be exceedingly fast acceleration Hough transformation;
(4) weight Hough transformation proposed by the present invention can realize the global fitting of boundary point, and traditional Hough transformation is only
It can be considered to falling the point on the same circumference, other boundary points are then ignored, and easily form local fit;
(5) present invention solves low contrast using iris to the gray scale gradual change principle and edge gradient consistency of sclera
Iris image outer edge obtain difficult problem;
(6) gradient consistency and gray scale gradually changeable of the present invention is all iris inherently characteristic, can be extensive
Applied to various iris authentication systems.
Iris Location device provided in an embodiment of the present invention is introduced below, Iris Location device described below with
Above-described iris locating method can correspond reference.
Fig. 7 is the structure diagram of Iris Location device provided in an embodiment of the present invention, can be with reference to Fig. 7 Iris Locations devices
Including:
Acquisition module 100, for obtaining iris image;
Detection module 200 obtains the hot spot point of the iris image for carrying out spot detection to the iris image;
Preprocessing module 300, for carrying out pretreatment operation to the iris image according to the hot spot point detected;
First acquisition module 400 obtains the inner boundary of iris for the gradient consistency feature according to pupil to iris
Point;
Second acquisition module 500 obtains the outer boundary of iris for being based on gray scale gradual change and gradient consistency feature
Point;
Locating module 600, for by the internal boundary points and the outer boundary point, inner boundary to the iris and
Outer boundary is fitted, to complete the positioning to the iris.
Iris Location device provided by the present invention, by obtaining iris image;Spot detection is carried out to iris image, is obtained
To the hot spot point of iris image;Pretreatment operation is carried out to iris image according to the hot spot point detected;According to pupil to iris
Gradient consistency feature, obtain the internal boundary points of iris;Based on gray scale gradual change and gradient consistency feature, iris is obtained
Outer boundary point;And according to internal boundary points and outer boundary point, the inner boundary and outer boundary of iris are fitted, to complete to rainbow
The positioning of film.Iris Location device provided by the present invention, can be quickly and accurately positioned the outer edge of iris, effectively solve
Iris Location of having determined speed is slow, and the low problem of non-ideal iris image positioning accuracy provides accurately for subsequent characteristic matching
Iris Location result.
Each embodiment is described by the way of progressive in this specification, the highlights of each of the examples are with it is other
The difference of embodiment, just to refer each other for same or similar part between each embodiment.For being filled disclosed in embodiment
For setting, since it is corresponded to the methods disclosed in the examples, so description is fairly simple, related place is referring to method part
Explanation.
Professional further appreciates that, unit described in conjunction with the examples disclosed in the embodiments of the present disclosure
And algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is implemented in hardware or software actually, depends on the specific application and design constraint of technical solution.Profession
Technical staff can use different methods to achieve the described function each specific application, but this realization is not answered
Think beyond the scope of this invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Iris locating method provided by the present invention and device are described in detail above.Tool used herein
Principle and implementation of the present invention are described for body example, and the explanation of above example is only intended to help to understand this hair
Bright method and its core concept.It should be pointed out that for those skilled in the art, not departing from the present invention
, can be with several improvements and modifications are made to the present invention under the premise of principle, these improvement and modification also fall into right of the present invention
It is required that protection domain in.
Claims (8)
1. a kind of iris locating method, which is characterized in that including:
Obtain iris image;
Spot detection is carried out to the iris image, obtains the hot spot point of the iris image;
Pretreatment operation is carried out to the iris image according to the hot spot point detected;
According to the gradient consistency feature of pupil to iris, the internal boundary points of iris are obtained;
Based on gray scale gradual change and gradient consistency feature, the outer boundary point of iris is obtained;
By the internal boundary points and the outer boundary point, the inner boundary and outer boundary of the iris are fitted, with complete
The positioning of the pairs of iris;
Wherein, the hot spot point that the basis detects carries out pretreatment operation to the iris image:
The iris image is cut according to the hot spot point;
Morphological erosion is carried out to the iris image and rebuilds operation;
Centered on the coordinate of the hot spot point, polar coordinates expansion is carried out;
Described to be based on gray scale gradual change and gradient consistency feature, the outer boundary point for obtaining iris includes:
It calculates outside pupil radium, the Grad Grad (x, y) of radial [0,60] and [120,180] records the Grad
Maximum value GradMax (x, y) and corresponding position coordinate (x, y);
Calculate the average gray of the point of continuous preset quantity 2n+1:
With IEFor thresholding, binaryzation is carried out to the point of the preset quantity:
According to the feature of the gray value gradual change of iris to sclera, by as i > 0 B (x+i, y)=1 exclude noise margin, with
Obtain correct boundary coordinate (x, y);
Meet the coordinate points that gradient is consistent and gray scale is progressive in the correct boundary coordinate or so radial search, it is each radial
The nearest coordinate points of the correct boundary coordinate of selected distance are iterated as new boundary point, are until meeting preset condition
Only.
2. iris locating method as described in claim 1, which is characterized in that described to carry out hot spot inspection to the iris image
It surveys, the hot spot point for obtaining the iris image includes:
By preset spot detection operator, convolution algorithm is carried out to the gray value high point of the iris image;
The big point coordinates of convolution value is obtained, judges whether the point coordinates is hot spot according to intensity profile around the point coordinates
Point.
3. iris locating method as claimed in claim 2, which is characterized in that the preset spot detection operator is that radius is
4 disk, value are just that peripheral value is negative, remaining position zero padding so that the spot detection operator sum of zero.
4. iris locating method as described in claim 1, which is characterized in that the gradient consistency according to pupil to iris
Feature, the internal boundary points for obtaining iris include:
Edge detection, the nearest edge coordinate point of each radial acquisition are carried out to the image of polar coordinates expansion;
Calculate the gradient value at the edge coordinate point:
Grad (x, y)=I (x+1, y)-I (x-1, y);
According to the gradient consistency feature of pupil to iris, noise spot boundary point is excluded, the internal boundary points of the iris are obtained.
5. iris locating method as described in claim 1, which is characterized in that described to pass through the internal boundary points and the outside
Boundary's point, inner boundary and outer boundary to the iris be fitted including:
By least variance method and weights Hough transformation method, the inner boundary and outer boundary of the iris are fitted.
6. iris locating method as claimed in claim 5, which is characterized in that pass through least variance method and weights Hough transformation
Method, to the inner boundary of the iris be fitted including:
The hot spot point coordinates is calculated to the distance value of the internal boundary points, calculates the variance of the distance value;
Using stochastic gradient descent method, center is set to be moved towards the direction of variance minimum, iteration is repeatedly to obtain the center of circle;
After obtaining the center of circle, three dimensions is become one-dimensional by Hough transformation, adjusts radius, is calculatedWherein, ri1
For the distance of each internal boundary points to the center of circle, r1For radius, ωi1For the boundary point voting stake;
Record works as ∑ ωi1R when maximum1, it is determined as inner circle radius.
7. iris locating method as claimed in claim 5, which is characterized in that pass through least variance method and weights Hough transformation
Method, to the outer boundary of the iris be fitted including:
Center coordinate of eye pupil is calculated to the distance value of the outer boundary point, calculates the variance of the distance value;
Using stochastic gradient descent method, center is set to be moved towards the direction of variance minimum, iteration is repeatedly to obtain the center of circle;
After obtaining the center of circle, three dimensions is become one-dimensional by Hough transformation, adjusts radius, is calculatedWherein, ri2
For each outer boundary point to the distance in the center of circle, r2For radius, ωi2For the boundary point voting stake;
Record works as ∑ ωi2R when maximum2, it is determined as exradius.
8. a kind of Iris Location device, which is characterized in that including:
Acquisition module, for obtaining iris image;
Detection module obtains the hot spot point of the iris image for carrying out spot detection to the iris image;
Preprocessing module, for carrying out pretreatment operation to the iris image according to the hot spot point detected;
First acquisition module obtains the internal boundary points of iris for the gradient consistency feature according to pupil to iris;
Second acquisition module obtains the outer boundary point of iris for being based on gray scale gradual change and gradient consistency feature;
Locating module is used for by the internal boundary points and the outer boundary point, to the inner boundary and outer boundary of the iris
It is fitted, to complete the positioning to the iris;
Wherein, the hot spot point that the basis detects carries out pretreatment operation to the iris image:
The iris image is cut according to the hot spot point;
Morphological erosion is carried out to the iris image and rebuilds operation;
Centered on the coordinate of the hot spot point, polar coordinates expansion is carried out;
Described to be based on gray scale gradual change and gradient consistency feature, the outer boundary point for obtaining iris includes:
It calculates outside pupil radium, the Grad Grad (x, y) of radial [0,60] and [120,180] records the Grad
Maximum value GradMax (x, y) and corresponding position coordinate (x, y);
Calculate the average gray of the point of continuous preset quantity 2n+1:
With IEFor thresholding, binaryzation is carried out to the point of the preset quantity:
According to the feature of the gray value gradual change of iris to sclera, by as i > 0 B (x+i, y)=1 exclude noise margin, with
Obtain correct boundary coordinate (x, y);
Meet the coordinate points that gradient is consistent and gray scale is progressive in the correct boundary coordinate or so radial search, it is each radial
The nearest coordinate points of the correct boundary coordinate of selected distance are iterated as new boundary point, are until meeting preset condition
Only.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510905787.0A CN105488487B (en) | 2015-12-09 | 2015-12-09 | A kind of iris locating method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510905787.0A CN105488487B (en) | 2015-12-09 | 2015-12-09 | A kind of iris locating method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105488487A CN105488487A (en) | 2016-04-13 |
CN105488487B true CN105488487B (en) | 2018-11-02 |
Family
ID=55675459
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510905787.0A Active CN105488487B (en) | 2015-12-09 | 2015-12-09 | A kind of iris locating method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105488487B (en) |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106778567B (en) * | 2016-12-05 | 2019-05-28 | 望墨科技(武汉)有限公司 | A method of iris recognition is carried out by neural network |
CN107292869B (en) * | 2017-06-07 | 2020-04-07 | 西安电子科技大学 | Image speckle detection method based on anisotropic Gaussian kernel and gradient search |
CN108734701B (en) * | 2018-04-25 | 2021-05-25 | 天津市索维电子技术有限公司 | Placido ring image morphological change identification method |
CN108710832B (en) * | 2018-04-26 | 2021-07-30 | 北京万里红科技股份有限公司 | Reference-free iris image definition detection method |
CN110895667B (en) * | 2018-09-12 | 2023-04-07 | 上海耕岩智能科技有限公司 | Optical image processing method and storage medium |
CN109684915B (en) * | 2018-11-12 | 2021-01-01 | 温州医科大学 | Pupil tracking image processing method |
CN112163507B (en) * | 2020-09-25 | 2024-03-05 | 北方工业大学 | Mobile-end-oriented lightweight iris recognition system |
CN113591658B (en) * | 2021-07-23 | 2023-09-05 | 深圳全息信息科技发展有限公司 | Eye protection system based on distance sensing |
CN115880303B (en) * | 2023-03-08 | 2023-06-06 | 杭州凌像科技有限公司 | Sub-pixel precision positioning detection method and system for round hole of PCB |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101201893A (en) * | 2006-09-30 | 2008-06-18 | 电子科技大学中山学院 | Iris recognizing preprocessing method based on grey level information |
CN102629319A (en) * | 2012-03-27 | 2012-08-08 | 中国科学院自动化研究所 | Robust iris region segmentation method based on specific boundary detectors |
CN104268527A (en) * | 2014-09-26 | 2015-01-07 | 北京无线电计量测试研究所 | Iris locating method based on radial gradient detection |
CN104463159A (en) * | 2014-12-31 | 2015-03-25 | 北京释码大华科技有限公司 | Image processing method and device of iris positioning |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7583823B2 (en) * | 2006-01-11 | 2009-09-01 | Mitsubishi Electric Research Laboratories, Inc. | Method for localizing irises in images using gradients and textures |
-
2015
- 2015-12-09 CN CN201510905787.0A patent/CN105488487B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101201893A (en) * | 2006-09-30 | 2008-06-18 | 电子科技大学中山学院 | Iris recognizing preprocessing method based on grey level information |
CN102629319A (en) * | 2012-03-27 | 2012-08-08 | 中国科学院自动化研究所 | Robust iris region segmentation method based on specific boundary detectors |
CN104268527A (en) * | 2014-09-26 | 2015-01-07 | 北京无线电计量测试研究所 | Iris locating method based on radial gradient detection |
CN104463159A (en) * | 2014-12-31 | 2015-03-25 | 北京释码大华科技有限公司 | Image processing method and device of iris positioning |
Also Published As
Publication number | Publication date |
---|---|
CN105488487A (en) | 2016-04-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105488487B (en) | A kind of iris locating method and device | |
JP6212099B2 (en) | Image template masking | |
EP1605822B1 (en) | Positive patient identification | |
CN104463159B (en) | A kind of image processing method and device for positioning iris | |
Sutra et al. | The Viterbi algorithm at different resolutions for enhanced iris segmentation | |
US20090220126A1 (en) | Processing an image of an eye | |
CN106022315A (en) | Pupil center positioning method for iris recognition | |
CN104123534A (en) | Biometric recognition | |
CN105868731A (en) | Binocular iris characteristic obtaining method, binocular iris characteristic obtaining device, identity identification method and identity identification system | |
CN106203358A (en) | A kind of iris locating method and equipment | |
CN103778406A (en) | Object detection method and device | |
CN109446935B (en) | Iris positioning method for iris recognition in long-distance traveling | |
WO2007097510A1 (en) | Deformation-resilient iris recognition methods | |
CN1319014C (en) | Personal identity recognising method based on pinna geometric parameter | |
Roy et al. | Iris segmentation using game theory | |
Latha et al. | A novel method for person authentication using retinal images | |
Niemeijer et al. | Automatic Detection of the Optic Disc, Fovea and Vacular Arch in Digital Color Photographs of the Retina. | |
CN105809128A (en) | Eye pupil positioning method and system for eye part image and shooting terminal | |
Matveev | Circular shortest path as a method of detection and refinement of iris borders in eye image | |
WO2020215229A1 (en) | Face registration method, face registration device, server and storage medium | |
Peters | Effects of segmentation routine and acquisition environment on iris recognition | |
Liu et al. | Eyelid localization in iris images captured in less constrained environment | |
CN105069428A (en) | Multi-template iris identification method based on similarity principle and multi-template iris identification device based on similarity principle | |
Hasegawa et al. | Synthetic eye images for pupil dilation mitigation | |
Subbarayudu et al. | A novel iris recognition system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information |
Address after: 438000 Dongpo courtyard 55, Dongpo Avenue, Huangzhou District, Huanggang, Hubei, E6 1-101 Applicant after: Hubei run Hong Polytron Technologies Inc Address before: 438000 No. 11 along Yanjiang Road, Huangzhou District, Huanggang, Hubei. Applicant before: HUBEI RUNHONG TECHNOLOGY CO., LTD. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |