CN106203358B - A kind of iris locating method and equipment - Google Patents
A kind of iris locating method and equipment Download PDFInfo
- Publication number
- CN106203358B CN106203358B CN201610556166.0A CN201610556166A CN106203358B CN 106203358 B CN106203358 B CN 106203358B CN 201610556166 A CN201610556166 A CN 201610556166A CN 106203358 B CN106203358 B CN 106203358B
- Authority
- CN
- China
- Prior art keywords
- circle
- boundary
- iris
- border
- pixel
- 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
- G06V40/193—Preprocessing; Feature extraction
Abstract
The invention discloses a kind of iris locating method and equipment, comprising: iris authentication system obtains iris image, includes iris to be positioned, pupil in the iris image；Determine the position of the hot spot in the pupil, the hot spot is injected the pupil by external light source and formed；According to the position of the hot spot and the grayscale information of the iris image, determine the first border circle and the second boundary circle in the iris image for characterizing the iris position to be positioned, first border circle includes the center of circle and the radius of first border circle, the center of circle of the second boundary circle comprising the second boundary circle and radius；According to first border circle and the second boundary circle, the iris in the iris image is positioned.Iris authentication system by simply image processing techniques and curve fitting algorithm, can quickly orient the position of iris in iris image, improve the working efficiency of iris authentication system according to the grayscale information of the iris image got in this way.
Description
Technical field
The present invention relates to technical field of image processing more particularly to a kind of iris locating method and equipment.
Background technique
Iris recognition technology is a kind of biometrics identification technology, has uniqueness, stability, safety and untouchable
The advantages that, it is the research hotspot and development trend in living things feature recognition field.
Iris authentication system mainly includes Image Acquisition, image preprocessing, iris feature extracts and characteristic matching.
Firstly, iris authentication system carries out Image Acquisition, the eye image comprising iris image is obtained.
Secondly, iris authentication system carries out image preprocessing to eye image, the position of iris in eye image is determined.Tool
Body, iris is a part of eye structure, between pupil and sclera, by carrying out image to the eye image got
Segmentation, and then determine the position of the iris in eye image.
Again, iris authentication system extracts the texture feature information of iris according to the position of determining iris.
Finally, the texture feature information of the iris extracted is matched with fixed form, iris recognition result is obtained.
It can be seen that Iris Location is the committed step in iris authentication system.The position that iris is accurately positioned can be true
The complete of the texture feature information of subsequent extracted iris is protected, and then guarantees iris recognition result.
However, traditional iris locating method is included the round operator Iris-orientation Algorithm of Daugman and is examined based on edge
Hough transform Iris-orientation Algorithm of survey etc..
The round operator Iris-orientation Algorithm of Daugman is a kind of to carry out Iris Location based on circle detection adaptation
Algorithm can accurately detect out the position of iris, but the algorithm of Daugman is to collected eye image quality requirement
Height reduces the working efficiency of iris authentication system so that the time consumed by Iris Location process is longer.
Hough transform Iris-orientation Algorithm based on edge detection mainly extracts pupil by using edge detection operator respectively
The marginal information of the marginal information of hole and iris, iris and sclera, and then determine using Hough changing method the position of iris.
But comprising the disturbing factors such as eyelashes, eyelid in the eye image due to getting, in Hough transform calculation amount compared with
Greatly, the time for causing Iris Location process to consume is longer, still reduces the working efficiency of iris authentication system.
It can be seen that a kind of iris locating method is needed, for solving the Iris Location in existing iris authentication system
The lower problem of the working efficiency of iris authentication system caused by the time consumed in the process is longer.
Summary of the invention
In view of this, the embodiment of the present invention provides a kind of iris locating method and equipment, know for solving existing iris
The lower problem of the working efficiency of iris authentication system caused by the time consumed during Iris Location in other system is longer.
The embodiment of the present invention provides a kind of iris locating method, comprising:
Iris image is obtained, includes iris to be positioned, pupil in the iris image；
Determine the position of the hot spot in the pupil, the hot spot is injected the pupil by external light source and formed；
According to the position of the hot spot and the grayscale information of the iris image, determine in the iris image for table
The first border circle and the second boundary circle of the iris position to be positioned are levied, first border circle includes described the
The center of circle of one border circle and radius, the center of circle of the second boundary circle comprising the second boundary circle and radius；
According to first border circle and the second boundary circle, the iris in the iris image is positioned.
The present invention, which implements, provides a kind of Iris Location equipment, comprising:
Acquiring unit includes iris to be positioned, pupil in the iris image for obtaining iris image；
First determination unit, for determining the position of the hot spot in the pupil, the hot spot injects institute by external light source
Pupil is stated to be formed；
Second determination unit, for determining institute according to the position of the hot spot and the grayscale information of the iris image
State the first border circle and the second boundary circle in iris image for characterizing the iris position to be positioned, described the
One border circle includes the center of circle and the radius of first border circle, the center of circle of the second boundary circle comprising the second boundary circle
And radius；
Positioning unit, for positioning in the iris image according to first border circle and the second boundary circle
Iris.
The present invention has the beneficial effect that:
Technical solution provided in an embodiment of the present invention, iris authentication system obtain iris image, wrap in the iris image
Containing iris to be positioned, pupil；Determine the position of the hot spot in the pupil, the hot spot injects the pupil by external light source
It is formed；According to the position of the hot spot and the grayscale information of the iris image, determine in the iris image for characterizing
The first border circle and the second boundary circle of the iris position to be positioned, first border circle include described first
The center of circle of border circle and radius, the center of circle of the second boundary circle comprising the second boundary circle and radius；According to described first
Border circle and the second boundary circle, position the iris in the iris image.Iris authentication system can be according to acquisition in this way
The grayscale information of the iris image arrived, by simply image processing techniques and curve fitting algorithm, in iris image quickly
The working efficiency of iris authentication system is improved in the position for orienting iris.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly introduced, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill in field, without any creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 is a kind of flow diagram of iris locating method provided in an embodiment of the present invention；
Fig. 2 is facula position schematic diagram provided in an embodiment of the present invention；
Fig. 3 is the schematic diagram of the pixel of the first border circle provided in an embodiment of the present invention；
Fig. 4 is the determination result schematic diagram of the first border circle provided in an embodiment of the present invention；
Fig. 5 is the rectangular area schematic diagram of determining the second boundary circle provided in an embodiment of the present invention；
Fig. 6 be same one-row pixels provided in an embodiment of the present invention between two pixels and the center of circle of the first border circle
Positional diagram；
Fig. 7 is the determination result schematic diagram of the second boundary provided in an embodiment of the present invention circle；
Fig. 8 is a kind of structural schematic diagram of Iris Location equipment provided in an embodiment of the present invention.
Specific embodiment
In iris authentication system, Iris Location is the key that iris recognition technology.The outer boundary of iris is adjacent with sclera,
It is approximately circle, the inner boundary of iris is adjacent with pupil, and also approximately at round, therefore, iris is between pupil and sclera
Area.The purpose of Iris Location be determine iris inner boundary circle the center of circle, radius and outer boundary circle the center of circle,
Radius, this makes it possible to the positions of precise positioning iris.
After iris authentication system gets the iris image comprising iris, the position of iris is positioned according to iris image
It sets.Due to including the disturbing factors such as eyelashes, eyelid in iris image, and in some iris images, between iris and sclera
Boundary it is unobvious, these can impact the positioning of exterior iris boundary.
In iris authentication system, exterior iris boundary positioning has important influence to the discrimination of iris recognition.Outside iris
Boundary alignment is excessive, i.e., has navigated to inside sclera the outer boundary circle of iris, caused one in Iris Texture Features Extraction
Part sclera texture is extracted as iris texture characteristic, influences last recognition result；Exterior iris boundary positions too small, rainbow
The texture feature information of film extracts not exclusively, equally influences last recognition result.
In order to obtain accurately Iris Location as a result, existing Iris Location technology using complicated Iris-orientation Algorithm into
Row iteration calculates, and causes Iris Location to take a long time, causes the working efficiency of iris authentication system lower.
In order to achieve the object of the present invention, the embodiment of the invention provides a kind of iris locating method and equipment, iris is known
Other system obtains iris image, includes iris to be positioned, pupil in the iris image；Determine the hot spot in the pupil
Position, the hot spot are injected the pupil by external light source and are formed；According to the position of the hot spot and the iris image
Grayscale information determines the first border circle in the iris image for characterizing the iris position to be positioned and the
Two border circles, first border circle include the center of circle and the radius of first border circle, and the second boundary circle is comprising described
The center of circle of the second boundary circle and radius；According to first border circle and the second boundary circle, position in the iris image
Iris.Iris authentication system can pass through simply image procossing according to the grayscale information of the iris image got in this way
Technology and curve fitting algorithm quickly locate out the position of iris in iris image, improve the work of iris authentication system
Efficiency.
The each embodiment of the present invention is described in further detail with reference to the accompanying drawings of the specification, it is clear that described
Embodiment is only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this field
Those of ordinary skill's all other embodiment obtained without making creative work, belongs to protection of the present invention
Range.
Embodiment 1
Fig. 1 is a kind of flow diagram of iris locating method provided in an embodiment of the present invention, and the method can be as follows
It is shown.
Step 101: obtaining iris image.
It wherein, include iris to be positioned, pupil in the iris image.
In a step 101, image acquisition operations are first carried out in iris authentication system, obtain iris image, and then to acquisition
To the iris image handled, position the iris in the iris image.
In practical applications, the iris image that the iris authentication system is got can be comprising the rainbow to be positioned
The eye image of film, in order to make it easy to understand, the eye image is known as iris image.
Step 102: determining the position of the hot spot in the pupil.
Wherein, the hot spot is injected the pupil by external light source and is formed.
In a step 102, in iris authentication system, better iris texture characteristic information, is obtaining rainbow in order to obtain
When film image, need to carry out light filling using external light source.In order to avoid the hot spot that external light source is formed falls in iris region to rainbow
The covering of the texture feature information of film can be such that the hot spot falls in pupil.For example, Fig. 2 is provided in an embodiment of the present invention
Facula position schematic diagram.
It, can be in iris image acquisition it should be noted that in order to avoid being damaged in Image Acquisition to eyes
Light filling is carried out using wavelength is the infrared light supply of 850nm, other light sources can also be used, be not specifically limited here.
Due to external light source formed the hot spot be located inside the pupil, it is thus determined that the position of the hot spot it
Afterwards, the position range of the pupil can be determined roughly according to the position of the hot spot.
Preferably, the position of the hot spot in the pupil is determined, comprising:
Binary conversion treatment is carried out to the iris image according to the threshold value of setting；
According to the iris image after the binary conversion treatment, light is detected from the iris image after the binary conversion treatment
Spot connected domain；
In the iris image, according to the grey value profile around the hot spot connected domain detected, determine described in
The position of hot spot.
It should be noted that being referred to around the hot spot connected domain using hot spot connected domain center as the center of circle, to set
Definite value be radius circle in remove the region of the hot spot connected domain.
In the iris image, compared with the gray value of the pupil, the gray value of the hot spot in the pupil
It is higher.Therefore, binary conversion treatment is carried out to the iris image according to the gray threshold of setting, the gray threshold of the setting is
First threshold.
In the iris image after binary conversion treatment, the part higher than the first threshold is displayed in white, and is lower than institute
The part for stating first threshold shows black.
The gray value of the hot spot is higher than the gray value of the pupil, therefore the iris image after the binary conversion treatment
In, the region being displayed in white belongs to hot spot connected domain.
In practical applications, when irradiating progress light filling using the external light source, due to reflective equal disturbing factors, so that
In the iris image got, other than the gray value of the hot spot part is higher, there is also other gray values compared with
High region, therefore after carrying out binary conversion treatment to the iris image, it can detecte out at least one hot spot connected domain.
The hot spot is located inside the pupil, and the gray value of the hot spot is higher than the gray value of the pupil, because
This, has biggish Gray Level Jump between the gray value of the pupil around the gray value of the hot spot and the hot spot.
In the iris image, grey value profile around at least one hot spot connected domain according to detecting,
The position of the hot spot is determined at least one described hot spot connected domain.
If the gray value around the hot spot connected domain is in the tonal range of setting, it is determined that the hot spot connected domain
Position be the hot spot position.
If the gray value around the hot spot connected domain is not in the tonal range of setting, it is determined that the hot spot connection
The position of the not described hot spot in the position in domain, as caused by reflective equal disturbing factors.
The hot spot is located inside the pupil, therefore, according to the position of the determining hot spot, can determine institute roughly
State the position range of pupil.
The iris to be positioned between the pupil and the sclera, therefore according to roughly determine the pupil
Position range, can quickly position the position of the iris in the follow-up process, avoid the time caused by blind search wave
Take.
Step 103: according to the position of the hot spot and the grayscale information of the iris image, determining the iris image
In for characterize the iris position to be positioned the first border circle and the second boundary circle.
Wherein, first border circle includes the center of circle of first border circle and radius, the second boundary circle include
The center of circle of the second boundary circle and radius.
It include the iris to be positioned, pupil, sclera in the iris image, for characterizing the iris to be positioned
First border circle of position is adjacent with the pupil, for characterizing the second boundary of the iris position to be positioned
Circle is adjacent with the sclera.
In the iris image, since the hot spot is located in the pupil, first border circle and the pupil
Adjacent, the gray value of the iris is higher than the gray value of the pupil, therefore according to the position of the hot spot determined in step 102
It sets and the grayscale information of the iris image, can determine in the iris image for characterizing the iris institute to be positioned
The first border circle in position.
Preferably, according to the position of the hot spot and the grayscale information of the iris image, the iris image is determined
In for characterizing the first border circle of the iris position to be positioned, comprising:
According to the position of the hot spot, the hot spot is filled；
According to the position of the filled hot spot, setting row pixel is chosen in the iris image；
According to the gray value of the setting row pixel, determine that the gray value in every one-row pixels positioned at spot center two sides is jumped
Become maximum pixel；
It is carried out curve fitting using least square method to the pixel, determines the center of circle and half of first border circle
Diameter.
Since the gray value of the iris is higher than the gray value of the pupil, the gray value of the hot spot is also above the pupil
Therefore the gray value in hole in order to avoid the hot spot interferes the determination of first border circle, needs described in the determination
Before first border circle, the hot spot is filled.
Morphological erosion and image reconstruction algorithm can be used to the filling of the hot spot, are not specifically limited here.
Fig. 3 is the schematic diagram of the pixel of the first border circle provided in an embodiment of the present invention.
According to the position of the filled hot spot, using the spot center as starting point, n row is chosen up and down respectively
Pixel.
According to the gray value of each pixel in the 2n row pixel, in every one-row pixels of the 2n row pixel,
It searches the gray value in every one-row pixels positioned at spot center two sides and jumps maximum pixel namely first boundary
Round boundary point.
The gray value jump maximum pixel refer to gray value between the two neighboring pixel difference (or
Absolute value of the difference) when being greater than second threshold, the big pixel of gray value in the two neighboring pixel.
Since first border circle is adjacent with the pupil, the second boundary circle, the Gong adjacent with the sclera
The gray value of film is higher than the gray value of the iris, and the gray value of the iris is higher than the gray value of the pupil, therefore, in institute
The jump of gray value can all be occurred by stating at the first border circle and first border circle.
When determining first border circle, in order to avoid the second boundary circle at Gray Level Jump influence, with
The spot center is that may include in every one-row pixels described in the n row pixel that starting point is chosen up and down respectively
Partial pixel point in pixel and the iris in pupil does not include the intrascleral pixel.
Therefore, the number of the pixel in every one-row pixels in the setting row pixel of selection can be rule of thumb
It is preset, it is not specifically limited here.
For example, including 9 pixels: pixel 1-9,9 pixels in certain one-row pixels of the 2n row pixel
Gray value be (52,50,9,10,9,9,8,51,50), the second threshold be 20, according to the ash between 9 pixels
Degree situation of change that is to say first side it was determined that pixel 2 and pixel 8 are that gray value jumps maximum pixel
The boundary point of boundary's circle.
In the 2n row pixel, every one-row pixels can determine that two gray values jump maximum pixel.
[x (i), y (i)], i=1,2,3...4n be that 4n gray value jump determining from the 2n row pixel is maximum
Pixel.
For the 4n pixel, is carried out curve fitting using least square method to the 4n pixel, determine institute
State the center of circle and the radius of the first border circle.
Assuming that the equation of first border circle are as follows:
(x-xc1)2+(y-yc1)2=r1 2,
Wherein, (xc1,yc1) be first border circle central coordinate of circle, r1It is the radius of first border circle.
The equation of first border circle of setting is unfolded, obtains following equations:
x2+y2-2xc1x-2yc1y+xc1 2+yc1 2-r1 2=0,
Enable a=-2xc1, b=-2yc1, c=xc1 2+yc1 2-r1 2, it can obtain:
Ax+by+c=- (x2+y2)。
The 4n pixel is substituted into above-mentioned formula, obtains the matrix form of above-mentioned formula are as follows:
It enablesThen obtain minimum
The matrix form of square law: AC=B.
, can be in the hope of C according to principle of least square method, namely obtain the value of a, b, c.It can be in the hope of according to the value of a, b, c
The central coordinate of circle and radius of first border circle are respectively as follows:
According to the central coordinate of circle and radius of first border circle, that is, it can determine first border circle, Fig. 4 is the present invention
The determination result schematic diagram for the first border circle that embodiment provides.
It should be noted that when being carried out curve fitting according to the boundary point of first border circle, it can be using minimum two
Multiplication can also be not specifically limited here using other curve fitting algorithms.
According to the position of the hot spot and the grayscale information of the iris image, determine in the iris image for table
After the first border circle for levying the iris position to be positioned, and then according to first border circle and the iris
The grayscale information of image determines in the iris image for characterizing the second boundary of the iris position to be positioned
Circle.
Preferably, it determines in the iris image for characterizing the second boundary of the iris position to be positioned
Circle, comprising:
According to the center of circle of first border circle, rectangular area is chosen in the iris image；
According to the rectangular area, the second boundary circle is determined.
Compared with first border circle, the boundary between the second boundary circle and the sclera is unobvious, Er Qieyou
In the difficulty for there are the interference of the factors such as eyelashes, eyelid, causing the circle positioning of iris the second boundary.
First border circle and the second boundary circle are the very close concentric circles in one group of center of circle, therefore, according to institute
The center of circle for stating the first border circle, chooses rectangular area below the center of circle of first border circle, and according to the rectangular area,
Determine the second boundary circle.Fig. 5 is the rectangular area schematic diagram of determining the second boundary circle provided in an embodiment of the present invention.
It should be noted that the length and width of the rectangular area can be rule of thumb preset, does not do have here
Body limits.
The rectangular area is located at below the center of circle of first border circle, the center of the rectangular area and described first
Vertical range between the center of circle of border circle is third threshold value.
Since the vertical range between first border circle and the center of circle of the second boundary circle is less than the 4th threshold value, institute
Third threshold value is stated greater than the 4th threshold value, therefore, the rectangular area is located at below the center of circle of the second boundary circle.In this way
The influence that the determination the second boundary can be justified to avoid disturbing factors such as eyelashes, eyelids.
Preferably, for characterizing the second boundary of the iris position to be positioned in determining the iris image
Before circle, the method also includes:
The iris image is smoothed；
Histogram equalization processing is carried out to the iris image after the smoothing processing.
In order to more accurately determine the second boundary circle, before determining the second boundary circle, firstly, to the rainbow
Film image is smoothed to cut down noise using gaussian filtering, then, carries out to the iris image after smoothing processing
Histogram equalization enhances the contrast of image.
In the iris image, the second boundary circle is adjacent with the sclera, and the gray value of the iris is lower than institute
The gray value of sclera is stated, therefore according to the rectangular area and the grayscale information of the iris image, can determine the rainbow
For characterizing the second boundary circle of the iris position to be positioned in film image.
Preferably, according to the rectangular area and the grayscale information of the iris image, the second boundary circle is determined,
Include:
In the rectangular area, setting row pixel is chosen；
According to the gray value of the setting row pixel, the ash for being located at first border circle two sides in every one-row pixels is determined
Angle value jumps maximum pixel；
According to the pixel, the boundary point of the second boundary circle is determined；
It is carried out curve fitting using boundary point of the least square method to the second boundary circle, determines the second boundary circle
The center of circle and radius.
Determining the second boundary bowlder, the pixel in the setting row pixel of selection, in every one-row pixels
Number can be rule of thumb preset, be not specifically limited here.
Specifically, in the rectangular area, setting row pixel is chosen.According to each pixel in the setting row pixel
The gray value of point is searched in every a line of the setting row pixel and is located at first border circle in every one-row pixels
The gray value of two sides jumps maximum pixel.
In the setting row pixel, every one-row pixels can determine that two gray values jump maximum pixel.
Such as: n row pixel is had chosen in the rectangular area, after lookup, is searched and is obtained in the n row pixel
2n gray value jumps maximum pixel, comprising: the n gray values on the left of first border circle jump maximum picture
Vegetarian refreshments, the n gray values on the right side of first border circle jump maximum pixel.
Since the texture information in the iris region is more, the gray-value variation in the iris region is more complicated,
So the gray value found in the setting row pixel jumps in maximum pixel, it can include the second boundary
Round false edges point, needs according to the pixel, from the pixel, removes the boundary point of the mistake, determines institute
State the correct boundary point of the second boundary circle.
Specifically, according to the pixel, the boundary point of the second boundary circle is determined, comprising:
Maximum two pictures are jumped for the gray value positioned at first border circle two sides determined in same one-row pixels
Vegetarian refreshments, determine respectively each pixel to the center of circle of first border circle horizontal distance；
According to the horizontal distance, the boundary point of the second boundary circle is determined.
In actual iris image, it is located at two boundary points in one-row pixels, relatively in the second boundary circle
It is circle of geometrically symmetric namely described two boundary points to the second boundary circle for the center of circle of the second boundary circle
Horizontal distance between the heart is equal.
Since the horizontal distance between the center of circle of first border circle and the center of circle of the second boundary circle is less than the 5th
Threshold value.
Therefore, two pixels determined in the mutually colleague in the setting row pixel: it is located at first border circle
The gray value in left side jumps maximum pixel and the gray value on the right side of first border circle jumps maximum pixel
Point, the difference of described two pixels to the horizontal distance between the center of circle of first border circle is again smaller than the 5th threshold value.
Such as: Fig. 6 is the center of circle of two pixels and the first border circle in same one-row pixels provided in an embodiment of the present invention
Between positional diagram.
Circle in Fig. 6 is the second boundary circle of iris, and point A is the center of circle of the second boundary circle, and point B is the first side of iris
The center of circle of boundary's circle.Point C is the left margin point of the iris the second boundary circle, and point D is the right margin of the iris the second boundary circle
Point, wherein point C and point D is located at in one-row pixels.
Horizontal distance between point C and point D to the center of circle A of the second boundary circle is equal, point C and point D to described second
Horizontal distance between the center of circle A of border circle is all X1mm。
Horizontal distance between the center of circle A of first border circle and the center of circle B of the second boundary circle is less than X2mm。
As seen from Figure 5, the difference of the horizontal distance between the point C and point D to the center of circle B of first border circle with
Horizontal distance between the center of circle A of first border circle and the center of circle B of the second boundary circle is equal.
Therefore, the difference of the horizontal distance between the point C and point D to the center of circle B of first border circle is again smaller than X2mm。
Therefore, in the setting row pixel, for the described two pixels found in same one-row pixels, firstly,
Determine that each described pixel to the horizontal distance in the center of circle of first border circle, also, determines described two pictures respectively
Vegetarian refreshments to the center of circle of first border circle two horizontal distances whether within the set range；Then, it is determined that described two pictures
Vegetarian refreshments to the center of circle of first border circle horizontal distance difference, and the difference of the horizontal distance and the 5th threshold value are made into ratio
Compared with.
When the difference of the horizontal distance is less than the 5th threshold value, and described two horizontal distances within the set range when, really
Fixed described two pixels are the boundary points of the second boundary circle.
When the difference of the horizontal distance is greater than the 5th threshold value, and a horizontal distance among described two horizontal distances
Within the set range, another horizontal distance not within the set range when, remove the horizontal distance not within the set range
Pixel determines that the pixel of the horizontal distance within the set range is the boundary point of the second boundary circle.
When the horizontal distance difference be greater than the 5th threshold value, and described two horizontal distances all within the set range when,
Determine that described two pixels are the unknown boundary points of the second boundary circle.
By the above method, the boundary point and unknown boundary of the second boundary circle have been determined in the setting row pixel
Point.
According to the boundary point of determining the second boundary circle, the round boundary point of the second boundary is calculated to described first
The average level distance in the center of circle of border circle.
The horizontal distance in the center of circle by the unknown boundary point to first border circle and average level distance are made
Compare.
When the horizontal distance in the center of circle of the unknown boundary point to first border circle and the average level are apart from it
When difference is less than six threshold values, determine that the unknown boundary point is the boundary point of the second boundary circle.
According to the above method, first border circle two sides can be located at according to what is determined from the setting row pixel
Gray value jumps maximum pixel, determines the boundary point of the second boundary circle.
It is carried out curve fitting using boundary point of the least square method to the second boundary circle, determines the second boundary circle
The center of circle and radius.
For example, most according to the gray value jump positioned at first border circle two sides determined from the setting row pixel
Big pixel, it is determined that n boundary point of the second boundary circle, [x (j), y (j)], and j=1,2,3...n.
For n boundary point of the second boundary circle, it is quasi- that curve is carried out to the n boundary point using least square method
It closes, determines the center of circle and the radius of the second boundary circle.
Assuming that the equation of the second boundary circle are as follows:
(x-xc2)2+(y-yc2)2=r2 2,
Wherein, (xc2,yc2) it is the round central coordinate of circle of the second boundary, r2It is the radius of the second boundary circle.
The equation of the second boundary circle of expansion setting, obtains following equations:
x2+y2-2xc2x-2yc2y+xc2 2+yc2 2-r2 2=0.
Enable d=-2xc1, e=-2yc1, f=xc1 2+yc1 2-r1 2, it can obtain:
Dx+ey+f=- (x2+y2)。
The n boundary point is substituted into above-mentioned formula, obtains the matrix form of above-mentioned formula are as follows:
It enablesThen obtain least square
The matrix form of method: DF=E.
, can be in the hope of F according to principle of least square method, namely obtain the value of d, e, f.It can be in the hope of according to the value of d, e, f
The central coordinate of circle and radius of the second boundary circle are respectively as follows:
According to the central coordinate of circle and radius of the second boundary circle, that is, it can determine that the second boundary circle, Fig. 7 are the present invention
The determination result schematic diagram for the second boundary circle that embodiment provides.
It should be noted that when being carried out curve fitting according to the boundary point of the second boundary circle, it can be using minimum two
Multiplication can also be not specifically limited here using other curve fitting algorithms.
Step 104: according to first border circle and the second boundary circle, positioning the iris in the iris image.
At step 104, what is determined in the iris image according to step 103 is used to characterize the iris to be positioned
The first border circle and the second boundary circle of position, can position the iris in the iris image.
Specifically, according to first border circle and the second boundary circle, the iris in the iris image is positioned, is wrapped
It includes:
Annular region between first border circle and the second boundary circle is positioned as in the iris image
The position of iris.
Rule of thumb preset it should be noted that the first threshold can be respectively to the 6th threshold value, here this
In be not specifically limited.
Technical solution provided in an embodiment of the present invention, iris authentication system obtain iris image, wrap in the iris image
Containing iris to be positioned, pupil；Determine the position of the hot spot in the pupil, the hot spot injects the pupil by external light source
It is formed；According to the position of the hot spot and the grayscale information of the iris image, determine in the iris image for characterizing
The first border circle and the second boundary circle of the iris position to be positioned, first border circle include described first
The center of circle of border circle and radius, the second boundary circle information include the center of circle and the radius of the second boundary circle；According to described
First border circle and the second boundary circle, position the iris in the iris image.Iris authentication system can basis in this way
The grayscale information of the iris image got, by simply image processing techniques and curve fitting algorithm, in the iris figure
The position that iris is quickly located out as in, improves the working efficiency of the iris authentication system.
Embodiment 2
Fig. 8 is a kind of structural schematic diagram of Iris Location equipment provided in an embodiment of the present invention, the Iris Location equipment
It include: acquiring unit 801, the first determination unit 802, the second determination unit 803, positioning unit 804, in which:
Acquiring unit 801 includes iris to be positioned, pupil in the iris image for obtaining iris image；
First determination unit 802, for determining the position of the hot spot in the pupil, the hot spot is injected by external light source
The pupil is formed；
Second determination unit 803, for determining according to the position of the hot spot and the grayscale information of the iris image
It is described for characterizing the first border circle and the second boundary circle of the iris position to be positioned in the iris image
First border circle includes the center of circle and the radius of first border circle, the circle of the second boundary circle comprising the second boundary circle
The heart and radius；
Positioning unit 804, for positioning in the iris image according to first border circle and the second boundary circle
Iris.
In another embodiment of the invention, second determination unit 803 is according to the position of the hot spot and described
The grayscale information of iris image determines in the iris image for characterizing the first side of the iris position to be positioned
Boundary's circle, comprising:
According to the position of the hot spot, the hot spot is filled；
According to the position of the filled hot spot, setting row pixel is chosen in the iris image；
According to the gray value of the setting row pixel, determine that the gray value in every one-row pixels positioned at spot center two sides is jumped
Become maximum pixel；
It is carried out curve fitting using least square method to the pixel, determines the center of circle and half of first border circle
Diameter.
In another embodiment of the invention, second determination unit 803 determines in the iris image for characterizing
The second boundary circle of the iris position to be positioned, comprising:
According to the center of circle of first border circle, rectangular area is chosen in the iris image；
According to the rectangular area, the second boundary circle is determined.
Specifically, second determination unit 803 determines the second boundary circle according to the rectangular area, comprising:
In the rectangular area, setting row pixel is chosen；
According to the gray value of the setting row pixel, the ash for being located at first border circle two sides in every one-row pixels is determined
Angle value jumps maximum pixel；
According to the pixel, the boundary point of the second boundary circle is determined；
It is carried out curve fitting using boundary point of the least square method to the second boundary circle, determines the second boundary circle
The center of circle and radius.
Specifically, second determination unit 803 determines the boundary point of the second boundary circle according to the pixel,
Include:
Maximum two pictures are jumped for the gray value positioned at first border circle two sides determined in same one-row pixels
Vegetarian refreshments, determine respectively each described pixel to the center of circle of first border circle horizontal distance；
According to the horizontal distance, the boundary point of the second boundary circle is determined.
In another embodiment of the invention, the Iris Location equipment further include: image processing unit 805, in which:
Image pre-processing unit 805, for being smoothed to the iris image；
Histogram equalization processing is carried out to the iris image after the smoothing processing.
In another embodiment of the invention, the positioning unit 804 is according to first border circle and second side
Boundary's circle, positions the iris in the iris image, comprising:
Annular region between first border circle and the second boundary circle is positioned as in the iris image
The position of iris.
In another embodiment of invention, first determination unit 802 determines the position of the hot spot in the pupil, packet
It includes:
Binary conversion treatment is carried out to the iris image according to the threshold value of setting；
According to the iris image after the binary conversion treatment, light is detected from the iris image after the binary conversion treatment
Spot connected domain；
In the iris image, according to the grey value profile around the hot spot connected domain detected, determine described in
The position of hot spot.
A kind of Iris Location equipment provided according to the present invention, the acquiring unit is for obtaining iris image, the rainbow
It include iris to be positioned, pupil in film image；First determination unit is used to determine the position of the hot spot in the pupil,
The hot spot is injected the pupil by external light source and is formed；Second determination unit be used for according to the position of the hot spot and
The grayscale information of the iris image determines in the iris image for characterizing the of the iris position to be positioned
One border circle and the second boundary circle, the center of circle of first border circle comprising first border circle and radius, described second
Border circle information includes the center of circle and the radius of the second boundary circle；The positioning unit be used for according to first border circle and
The second boundary circle, positions the iris in the iris image.Iris authentication system can be according to the iris got in this way
The grayscale information of image, by simply image processing techniques and curve fitting algorithm, quickly positioning is appeared in the sky in iris image
The working efficiency of iris authentication system is improved in the position of film.
It will be understood by those skilled in the art that the embodiment of the present invention can provide as method, apparatus (equipment) or computer
Program product.Therefore, in terms of the present invention can be used complete hardware embodiment, complete software embodiment or combine software and hardware
Embodiment form.Moreover, it wherein includes the meter of computer usable program code that the present invention, which can be used in one or more,
The computer journey implemented in calculation machine usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of sequence product.
The present invention be referring to according to the method for the embodiment of the present invention, the flow chart of device (equipment) and computer program product
And/or block diagram describes.It should be understood that each process in flowchart and/or the block diagram can be realized by computer program instructions
And/or the combination of the process and/or box in box and flowchart and/or the block diagram.It can provide these computer programs to refer to
Enable the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to generate
One machine so that by the instruction that the processor of computer or other programmable data processing devices executes generate for realizing
The device for the function of being specified in one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from model of the invention by those skilled in the art
It encloses.In this way, if these modifications and changes of the present invention is within the scope of the claims of the present invention and its equivalent technology, then
The present invention is also intended to include these modifications and variations.
Claims (7)
1. a kind of iris locating method characterized by comprising
Iris image is obtained, includes iris to be positioned, pupil in the iris image；
Determine the position of the hot spot in the pupil, the hot spot is injected the pupil by external light source and formed；
According to the position of the hot spot and the grayscale information of the iris image, determine in the iris image for characterizing institute
The first border circle and the second boundary circle of iris position to be positioned are stated, first border circle includes first side
The center of circle of boundary's circle and radius, the center of circle of the second boundary circle comprising the second boundary circle and radius；
According to first border circle and the second boundary circle, the iris in the iris image is positioned；
Wherein it is determined that for characterizing the second boundary circle of the iris position to be positioned in the iris image, comprising:
Below the center of circle of first border circle, rectangular area is chosen in the iris image；According to the rectangular area, determine
The second boundary circle；
According to the rectangular area, the second boundary circle is determined, comprising:
In the rectangular area, setting row pixel is chosen；
According to the gray value of the setting row pixel, the gray value for being located at first border circle two sides in every one-row pixels is determined
Jump maximum pixel；
According to the pixel, the boundary point of the second boundary circle is determined；
It is carried out curve fitting using boundary point of the least square method to the second boundary circle, determines the circle of the second boundary circle
The heart and radius；
According to the pixel, the boundary point of the second boundary circle is determined, comprising:
In the setting row pixel, for two pixels found in same one-row pixels, firstly, determining each respectively
The pixel also, determines described two pixels to described first to the horizontal distance in the center of circle of first border circle
Within the set range whether two horizontal distances in the center of circle of border circle；Then, it is determined that described two pixels are to described first
The difference of the horizontal distance in the center of circle of border circle, and the difference of the horizontal distance is made comparisons with the 5th threshold value；
When the difference of the horizontal distance is less than the 5th threshold value, and described two horizontal distances within the set range when, determine institute
State the boundary point that two pixels are the second boundary circles；
When the difference of the horizontal distance is greater than the 5th threshold value, and a horizontal distance among described two horizontal distances is being set
Determine in range, another horizontal distance not within the set range when, remove the pixel of the horizontal distance not within the set range
Point determines that the pixel of the horizontal distance within the set range is the boundary point of the second boundary circle；
When the horizontal distance difference be greater than the 5th threshold value, and described two horizontal distances all within the set range when, determine
Described two pixels are the unknown boundary points of the second boundary circle；
According to the boundary point of determining the second boundary circle, the round boundary point of the second boundary is calculated to first boundary
The average level distance in the round center of circle；
The horizontal distance in the center of circle by the unknown boundary point to first border circle is made comparisons with the average level distance；
When the horizontal distance in the center of circle of the unknown boundary point to first border circle and the average level are small apart from its difference
When six threshold values, determine that the unknown boundary point is the boundary point of the second boundary circle.
2. iris locating method as described in claim 1, which is characterized in that according to the position of the hot spot and the iris
The grayscale information of image determines in the iris image for characterizing the first boundary of the iris position to be positioned
Circle, comprising:
According to the position of the hot spot, the hot spot is filled；
According to the position of the filled hot spot, setting row pixel is chosen in the iris image；
According to the gray value of the setting row pixel, determine that the gray value in every one-row pixels positioned at spot center two sides jumps most
Big pixel；
It is carried out curve fitting using least square method to the pixel, determines the center of circle and the radius of first border circle.
3. iris locating method as described in claim 1, which is characterized in that for characterizing institute in determining the iris image
Before the second boundary circle for stating iris position to be positioned, the method also includes:
The iris image is smoothed；
Histogram equalization processing is carried out to the iris image after the smoothing processing.
4. iris locating method as described in any one of claims 1 to 3, which is characterized in that according to first border circle and
The second boundary circle, positions the iris in the iris image, comprising:
Annular region between first border circle and the second boundary circle is positioned as the iris in the iris image
Position.
5. iris locating method as described in claim 1, which is characterized in that determine the position of the hot spot in the pupil, wrap
It includes:
Binary conversion treatment is carried out to the iris image according to the threshold value of setting；
According to the iris image after the binary conversion treatment, glossing up is detected from the iris image after the binary conversion treatment and is connected
Logical domain；
In the iris image, according to the grey value profile around the hot spot connected domain detected, the hot spot is determined
Position.
6. a kind of Iris Location equipment characterized by comprising
Acquiring unit includes iris to be positioned, pupil in the iris image for obtaining iris image；
First determination unit, for determining the position of the hot spot in the pupil, the hot spot injects the pupil by external light source
Hole is formed；
Second determination unit, for determining the rainbow according to the position of the hot spot and the grayscale information of the iris image
For characterizing the first border circle and the second boundary circle of the iris position to be positioned, first side in film image
The boundary center of circle of the circle comprising first border circle and radius, the center of circle of the second boundary circle comprising the second boundary circle and half
Diameter；
Positioning unit, for positioning the iris in the iris image according to first border circle and the second boundary circle；
Wherein it is determined that for characterizing the second boundary circle of the iris position to be positioned in the iris image, comprising:
Below the center of circle of first border circle, rectangular area is chosen in the iris image；According to the rectangular area, determine
The second boundary circle；
According to the rectangular area, the second boundary circle is determined, comprising:
In the rectangular area, setting row pixel is chosen；
According to the gray value of the setting row pixel, the gray value for being located at first border circle two sides in every one-row pixels is determined
Jump maximum pixel；
According to the pixel, the boundary point of the second boundary circle is determined；
It is carried out curve fitting using boundary point of the least square method to the second boundary circle, determines the circle of the second boundary circle
The heart and radius；
According to the pixel, the boundary point of the second boundary circle is determined, comprising:
In the setting row pixel, for two pixels found in same one-row pixels, firstly, determining each respectively
The pixel also, determines described two pixels to described first to the horizontal distance in the center of circle of first border circle
Within the set range whether two horizontal distances in the center of circle of border circle；Then, it is determined that described two pixels are to described first
The difference of the horizontal distance in the center of circle of border circle, and the difference of the horizontal distance is made comparisons with the 5th threshold value；
When the difference of the horizontal distance is less than the 5th threshold value, and described two horizontal distances within the set range when, determine institute
State the boundary point that two pixels are the second boundary circles；
When the difference of the horizontal distance is greater than the 5th threshold value, and a horizontal distance among described two horizontal distances is being set
Determine in range, another horizontal distance not within the set range when, remove the pixel of the horizontal distance not within the set range
Point determines that the pixel of the horizontal distance within the set range is the boundary point of the second boundary circle；
When the horizontal distance difference be greater than the 5th threshold value, and described two horizontal distances all within the set range when, determine
Described two pixels are the unknown boundary points of the second boundary circle；
According to the boundary point of determining the second boundary circle, the round boundary point of the second boundary is calculated to first boundary
The average level distance in the round center of circle；
The horizontal distance in the center of circle by the unknown boundary point to first border circle is made comparisons with the average level distance；
When the horizontal distance in the center of circle of the unknown boundary point to first border circle and the average level are small apart from its difference
When six threshold values, determine that the unknown boundary point is the boundary point of the second boundary circle.
7. Iris Location equipment as claimed in claim 6, which is characterized in that second determination unit is according to the hot spot
The grayscale information of position and the iris image determines and is used to characterize the iris institute to be positioned in the iris image
The first border circle in position, comprising:
According to the position of the hot spot, the hot spot is filled；
According to the position of the filled hot spot, setting row pixel is chosen in the iris image；
According to the gray value of the setting row pixel, determine that the gray value in every one-row pixels positioned at spot center two sides jumps most
Big pixel；
It is carried out curve fitting using least square method to the pixel, determines the center of circle and the radius of first border circle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610556166.0A CN106203358B (en) | 2016-07-14 | 2016-07-14 | A kind of iris locating method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610556166.0A CN106203358B (en) | 2016-07-14 | 2016-07-14 | A kind of iris locating method and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106203358A CN106203358A (en) | 2016-12-07 |
| CN106203358B true CN106203358B (en) | 2019-11-19 |
Family
ID=57474289
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610556166.0A Active CN106203358B (en) | 2016-07-14 | 2016-07-14 | A kind of iris locating method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106203358B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106778689A (en) * | 2017-01-13 | 2017-05-31 | 深圳市明天科创科技有限公司 | A kind of iris capturing recognition methods of dual camera and device |
| CN109426770B (en) * | 2017-08-24 | 2022-02-18 | 合肥虹慧达科技有限公司 | Iris identification method |
| CN107870323A (en) * | 2017-11-06 | 2018-04-03 | 深圳市杉川机器人有限公司 | De-jittering method and device |
| CN108280403B (en) * | 2017-12-27 | 2020-08-04 | 北京七鑫易维信息技术有限公司 | Method and device for determining pupil position |
| 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 |
| CN114764943A (en) * | 2020-12-30 | 2022-07-19 | 北京眼神智能科技有限公司 | Method and device for positioning strabismus pupil, computer readable storage medium and equipment |
| CN112816187B (en) * | 2021-01-06 | 2022-12-13 | 北京工业大学 | Quality judgment method for laser spots |
| CN113378790A (en) * | 2021-07-08 | 2021-09-10 | 中国电信股份有限公司 | Viewpoint positioning method, apparatus, electronic device and computer-readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2305697A1 (en) * | 1997-10-10 | 1999-04-22 | Visx Incorporated | Eye tracking device for laser eye surgery using corneal margin detection |
| CN1549188A (en) * | 2003-05-13 | 2004-11-24 | 范科峰 | Estimation of irides image quality and status discriminating method based on irides image identification |
| CN1584917A (en) * | 2004-06-11 | 2005-02-23 | 清华大学 | Living body iris patterns collecting method and collector |
| 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 |
| CN101246544A (en) * | 2008-01-24 | 2008-08-20 | 电子科技大学中山学院 | Iris locating method based on boundary point search and SUSAN edge detection |
-
2016
- 2016-07-14 CN CN201610556166.0A patent/CN106203358B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2305697A1 (en) * | 1997-10-10 | 1999-04-22 | Visx Incorporated | Eye tracking device for laser eye surgery using corneal margin detection |
| CN1549188A (en) * | 2003-05-13 | 2004-11-24 | 范科峰 | Estimation of irides image quality and status discriminating method based on irides image identification |
| CN1584917A (en) * | 2004-06-11 | 2005-02-23 | 清华大学 | Living body iris patterns collecting method and collector |
| 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 |
| CN101246544A (en) * | 2008-01-24 | 2008-08-20 | 电子科技大学中山学院 | Iris locating method based on boundary point search and SUSAN edge detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106203358A (en) | 2016-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106203358B (en) | A kind of iris locating method and equipment | |
| US11749025B2 (en) | Eye pose identification using eye features | |
| CN105046250B (en) | The glasses removing method of recognition of face | |
| JP5107045B2 (en) | Method for identifying a pixel representing an iris in an image acquired for the eye | |
| CN104463159B (en) | A kind of image processing method and device for positioning iris | |
| US8755607B2 (en) | Method of normalizing a digital image of an iris of an eye | |
| US20160019421A1 (en) | Multispectral eye analysis for identity authentication | |
| US20170091550A1 (en) | Multispectral eye analysis for identity authentication | |
| US20150193666A1 (en) | Spoof detection for biometric authentication | |
| CN107748869A (en) | 3D face identity authentications and device | |
| TWI692729B (en) | Method and device for determining pupil position | |
| US8854446B2 (en) | Method of capturing image data for iris code based identification of vertebrates | |
| WO2016010720A1 (en) | Multispectral eye analysis for identity authentication | |
| US11449590B2 (en) | Device and method for user authentication on basis of iris recognition | |
| CN107844736A (en) | iris locating method and device | |
| CN109376518A (en) | Privacy leakage method and relevant device are prevented based on recognition of face | |
| CN105550625B (en) | A kind of living body iris detection method and terminal | |
| KR102369412B1 (en) | Device and method to recognize iris | |
| Garagad et al. | A novel technique of iris identification for biometric systems | |
| KR101582467B1 (en) | Pupil acquisition method using binary of adjacent sum and control device for extracting pupil using the same | |
| CN113792718A (en) | Method for positioning face area in depth map, electronic device and storage medium | |
| CN109614858A (en) | A kind of detection method and device of pupil center | |
| CN107153806A (en) | A kind of method for detecting human face and device | |
| JP7078386B2 (en) | Image processing equipment | |
| CN104463096B (en) | binocular iris image detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |