CN110276324A - The elliptical method of pupil is determined in a kind of iris image - Google Patents
The elliptical method of pupil is determined in a kind of iris image Download PDFInfo
- Publication number
- CN110276324A CN110276324A CN201910566465.6A CN201910566465A CN110276324A CN 110276324 A CN110276324 A CN 110276324A CN 201910566465 A CN201910566465 A CN 201910566465A CN 110276324 A CN110276324 A CN 110276324A
- Authority
- CN
- China
- Prior art keywords
- pupil
- edge
- edge line
- iris image
- elliptical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06V40/197—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The present patent application, which discloses, determines the elliptical method of pupil in a kind of iris image, this method comprises: determining the elliptical method of pupil in a kind of iris image, this method comprises: (1) obtains iris image, determine pupil candidate region by threshold method；(2) edge of pupil candidate region is detected and determined；(3) concave, convex detection and classification are carried out to pixel each on edge；(4) screening of edge line；(5) the elliptical center of pupil, half long and short axis and oval direction are calculated using the position of the point on edge line；(6) the pupil ellipse obtained to upper step is tested and is confirmed.The selection of technical scheme model of ellipse fitting of the present patent application more meets actual scene, according to edge line convex-concave property and elliptic geometry property, realizes the determination of pupil elliptic parameter, improves iris segmentation and accuracy of identification.
Description
Technical field
The technical solution of the application belongs to biological information field of image processing, in particular to be iris image in human body
The middle elliptical method of determining pupil.
Background technique
The development of modern society proposes higher want to the accuracy of mankind itself's identification, safety and usability
It asks.And identification is the Universal Problems encountered in people's daily life, often needs to prove in life
The things such as the identity of oneself, the identity for identifying others.When oneself warp of the personal identification method of traditional dependence photo lags far behind
The requirement in generation, the mankind must seek safer reliable, easy to use identification new way.Based on living things feature recognition
Identity authentication technology, which has the advantage that, to be not easy to forget or lose, and anti-counterfeiting performance is good, is not easy to forge or be stolen, carries, with
When can be used everywhere.Biometrics identification technology refers to the physiological characteristic or behavioural characteristic intrinsic using human body itself, has not
The features such as reproducibility, uniqueness, generality and stability.And iris recognition technology has random minutia and texture special
Sign, and keep quite high stability；With inherent isolation and protective capability, in terms of not needing the physiology such as contact acquisition
A little, there are extensive market prospects and scientific research value.
During carrying out iris recognition, it is necessary first to which acquisition meets necessarily required iris image, then to iris image
It is split and obtains lesser ring of Merkel, iris area, along image-regions such as eyelashes areas.During image segmentation, how pupil is obtained
Region understands, accurate image is the key that subsequent progress image recognition.
Currently, when pupil image included in human eye iris image is positioned, is divided, it usually needs in human eye figure
It is found as in and determines several marginal points of pupil image and guess the position of pupil center, further according to pupil center and each
Marginal point fits model of ellipse, marks the position of emergent pupil hole image on eye image by the model of ellipse of fitting.It is this
In method, since there may be the points of much noise caused by eyelashes, eyelid in each marginal point, according to determining each edge
When point fitted ellipse model, more noise spot may include in the model of ellipse of fitting, eye image can not be carried
Pupil image is accurately positioned.
Summary of the invention
For the influence in iris image identification due to noise factors such as human eye eyelashes, the pupillogram being easy to cause in image
As determining inaccuracy, so as to cause the deviation of biometric information, pupil is carried out using model of ellipse present applicant proposes a kind of
The method that the detection of elliptical edge point, fitting obtain pupil elliptical image.This method after gray value statistical distribution, screening by obtaining
Preliminary edge line finally obtains the higher pupil elliptic region of accuracy using ellipse fitting and subsequent survey program.
Realize the technical solution of foregoing invention purpose are as follows: the elliptical method of pupil, this method are determined in a kind of iris image
Include the following steps:
(1) iris image is obtained, pupil candidate region is determined by threshold method；
(2) edge of pupil candidate region is detected and determined；
(3) concave, convex detection and classification are carried out to pixel each on edge；
(4) screening of edge line；
(5) the elliptical center of pupil, half long and short axis and oval direction are calculated using the position of the point on edge line；
(6) the pupil ellipse obtained to upper step is tested and is confirmed.
In the above-mentioned steps of the application, preliminary pupil candidate region has been filtered out first, has been mentioned for subsequent detection and analysis
Basis is supplied.The screening step of its threshold method are as follows:
(1-1) counts the grey level histogram that the pixel number on the different gray values of iris image obtains: H={ Hi,0
<=255 <=i }, wherein HiIt is the number for the pixel that gray value is i in iris image；
The pixel ratio that (1-2) presets pupil region and iris image is q, then divide the threshold epsilon of pupil candidate region by
Following formula determines:Wherein N is the number of iris image pixel, and the i when above formula takes equal sign is threshold value
ε；
It is pupil candidate region that (1-3), which selects the gray value of iris image pixel to be less than the region of threshold value,.
Above-mentioned threshold method more accurately obtains the initial range of pupil using gray-scale statistical as object is judged, can
When excluding directly using gray scale as threshold value, the inaccuracy of the information change as caused by noise.
It is subsequent to need to detect the pupil edge being located in pupil candidate region after pupil candidate region has been determined
And determination, that is, determine the edge line of pupil, the application determines edge line by the gradient value size and Orientation variation of pixel
Point, improve the accuracy of edge line detection.Its detailed process are as follows:
(2-1) calculates horizontal, vertical direction shade of gray Dx and Dy on each pixel in pupil candidate region；
(2-2) is if the absolute value of horizontal gradient or vertical gradient on the pixel of pupil candidate region is less than in advance
The threshold value η of setting, then the gray scale of the pixel is 0, otherwise is 255, and what the pixel that gray scale is 255 was formed by connecting is pupil
The edge M of candidate region.
The marginal position that pupil region is judged using the shade of gray on pixel is a kind of new judgment method, this is sentenced
Disconnected method is thought more accurately, to overcome the defect directly demarcated with gray scale in accuracy.
It completes to need to judge the concave, convex detection of edge line after the determination at edge, classify, can determine with this elliptical first
Shape is walked, the specific steps of which are as follows: (3-1) calculates the product of the shade of gray Dx and Dy of edge each point, if being recessed when jack per line
Property edge, otherwise be convexity edge, and
(3-2) carries out quadrant classification to edge line, specifically: taking one section of beginning and end of convexity edge line is diagonal line,
Building one includes rectangle, should be divided into two parts by this section of edge line comprising rectangle, area is less than above convexity edge line
When area under, this section of edge line is located at first quartile, and otherwise edge line is in third quadrant；Equally take one section of concavity edge line
Beginning and end is diagonal line, and building one includes rectangle, should be divided into two parts, concavity by this section of edge line comprising rectangle
When area is less than area under above edge line, this section of edge line is located at the second quadrant, and otherwise edge line is in fourth quadrant.
Pass through above-mentioned judgement back edge line being classified as follows in each quadrant: A: belonging to the chimb edge of first quartile；B: belong to
In the concave edge edge of the second quadrant；C: belong to the chimb edge of third quadrant；D: belong to the concave edge edge of fourth quadrant.Again to above-mentioned difference
The edge line length computation in region, edge length < Lmin is deleted, and Lmin is preset length value, close to 0.
After above-mentioned four step, pupil edge line has been substantially achieved determination, and the subsequent point according on these edge lines is
It can be fitted and determine the elliptical center of circle, semi-minor axis and semi-major axis and direction.Detailed process is as follows for it:
(5-1) is to aaOne section of edge line is divided into two sections from midpoint and obtains three point P1,P12,P2, point m1,m2It is line segment respectively
P1P12,P12P2Midpoint, pointIt is point P respectively1,P12,P2The point of intersection of tangents, obtain straight line l using aforementioned ellipse properties1,
l2To central point C12；
(5-2) selects one section of edge line ab, using the available central point C of (5-1) same method34；
(5-3) obtains multiple central points using the method for (5-1) repeatedly, after be averaged to each central point after obtain pupil
The elliptical center in hole；The above-mentioned specific calculation formula for calculating (5-1) are as follows: assuming that { xi,yi,θi| i=1,2 } it respectively indicates a little
P1,P2, xi,yi,θiIt is the abscissa, ordinate and gradient direction angle of corresponding points, i.e. arctan (dy/dx) respectively；Central pointIt is to be calculated according to following formula:
(5-4) calculates elliptical long semi-minor axis and deflection: setting A, B, ρ are oval major semiaxis, semi-minor axis, ellipse side respectively
To angle, { xi,yi,θiRespectively indicate point on edge, then:
The ratio for remembering semi-minor axis and major semiaxis is N:
The tangent value for remembering oval deflection is K:K=tan ρ
N, K have following relationship:
The above method is also suitble to other two o'clocks on edge line, then has following relationship:
Above formula is written as: α K2+ β K- α=0, α=s1s2-s3s4, β=s2s4(s3-s1)+s1s3(s4-s2)+(s1+s2-s3-s4),
Solve the true defining K value of equation:
Point (x on elliptical edge linei,yi) point (x with the coordinate system of elliptical center origino,yo) there are following relationships:
According to above formula, obtain:
It thereby determines that:To obtain major semiaxis A, semi-minor axis B, oval deflection ρ.
In the above method, the parameter for obtaining elliptic curve is directly fitted using the position of multiple points on edge line,
It is more simple and convenient, accurate to calculate.
Elliptic curve is obtained to above-mentioned fitting and needs to examine and judge whether it is appropriate suitable curve, is divided in the application
Not Cai Yong lenth ratio proof method or ellipse fitting fraction method judged.Wherein, the detailed process of the proof method of lenth ratio
Are as follows: the Rectangular Bounding Volume of the edge line of pupil candidate region, the perimeter half and pupil oval half of the bounding box are surrounded in setting
The ratio of the sum of length measures, i.e. bounding box is having a size of W × H, then ratioIf Q is greater than preset threshold
Value, then it is assumed that be ellipse, otherwise give up the curve；The detailed process of ellipse fitting fraction method are as follows: by ellipse on
The ratio of the point point all with edge line is as ellipse fitting score S, if S is greater than preset threshold value, then it is assumed that be ellipse
Circle, otherwise gives up the curve.
Above-mentioned proposed pupil ellipse fitting judgment method has much not on image processing method with traditional method
Same place, technical method is unique, calculates easy, judgement accuracy rate and precision is high, be the one of image recognition and analysis field
Secondary innovation.
Detailed description of the invention
Fig. 1 is the method flow schematic diagram of technical solution of the present invention；
Fig. 2 is that the pupil ellipse center of circle determines schematic diagram；
Fig. 3 is that pupil ellipse direction determines schematic diagram.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments, based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
As shown in Figure 1, determining the elliptical flow diagram of pupil, method packet in a kind of iris image disclosed by the invention
Include following steps:
(1) iris image is obtained, pupil candidate region is determined by threshold method；
(2) edge of pupil candidate region is detected and determined；
(3) concave, convex detection and classification are carried out to pixel each on edge；
(4) screening of edge line；
(5) the elliptical center of pupil, half long and short axis and oval direction are calculated using the position of the point on edge line；
(6) the pupil ellipse obtained to upper step is tested and is confirmed.
Determine that pupil candidate region method is as follows by threshold method in above-mentioned steps (1):
(1-1) counts the grey level histogram that the pixel number on the different gray values of iris image obtains: H={ Hi,0
<=255 <=i }, wherein HiIt is the number for the pixel that gray value is i in iris image；
The pixel ratio that (1-2) presets pupil region and iris image is q, then divide the threshold epsilon of pupil candidate region by
Following formula determines:Wherein N is the number of iris image pixel, and the i when above formula takes equal sign is threshold value
ε；
It is pupil candidate region that (1-3), which selects the gray value of iris image pixel to be less than the region of threshold value,.
Above-mentioned steps (2) determine the process of the point on edge line are as follows:
(2-1) calculates horizontal, vertical direction shade of gray Dx and Dy on each pixel in pupil candidate region；
(2-2) is if the absolute value of horizontal gradient or vertical gradient on the pixel of pupil candidate region is less than in advance
The threshold value η of setting, then the gray scale of the pixel is 0, otherwise is 255, and what the pixel that gray scale is 0 was formed by connecting is that pupil is waited
The edge M of favored area.
It completes to need to judge the concave, convex detection of edge line after the determination at edge, classify, can determine with this elliptical first
Shape is walked, the specific steps of which are as follows: (3-1) calculates the product of the shade of gray Dx and Dy of edge each point, if being recessed when jack per line
Property edge, otherwise be convexity edge, and
(3-2) carries out quadrant classification to edge line, specifically: taking one section of beginning and end of convexity edge line is diagonal line,
Building one includes rectangle, should be divided into two parts by this section of edge line comprising rectangle, area is less than above convexity edge line
When area under, this section of edge line is located at first quartile, and otherwise edge line is in third quadrant；Equally take one section of concavity edge line
Beginning and end is diagonal line, and building one includes rectangle, should be divided into two parts, concavity by this section of edge line comprising rectangle
When area is less than area under above edge line, this section of edge line is located at the second quadrant, and otherwise edge line is in fourth quadrant.
Pass through above-mentioned judgement back edge line being classified as follows in each quadrant: A: belonging to the chimb edge of first quartile；B: belong to
In the concave edge edge of the second quadrant；C: belong to the chimb edge of third quadrant；D: belong to the concave edge edge of fourth quadrant.Again to above-mentioned difference
The edge line length computation in region, edge length < Lmin is deleted, and Lmin is preset length value, close to 0.
After above-mentioned four step, pupil edge line has been substantially achieved determination, and the subsequent point according on these edge lines is
It can be fitted and determine the elliptical center of circle, semi-minor axis and semi-major axis and direction.As shown in Fig. 2, giving the calculation method in the oval center of circle.
That is:
(5-1) is to aaOne section of edge line is divided into two sections from midpoint and obtains three point P1,P12,P2, point m1,m2It is line segment respectively
P1P12,P12P2Midpoint, pointIt is point P respectively1,P12,P2The point of intersection of tangents, obtain straight line l using aforementioned ellipse properties1,
l2To central point C12；
(5-2) selects one section of edge line ab, using the available central point C of (5-1) same method34；
(5-3) obtains multiple central points using the method for (5-1) repeatedly, after be averaged to each central point after obtain pupil
The elliptical center in hole；The above-mentioned specific calculation formula for calculating (5-1) are as follows: assuming that { xi,yi,θi| i=1,2 } it respectively indicates a little
P1,P2, xi,yi,θiIt is the abscissa, ordinate and gradient direction angle of corresponding points, i.e. arctan (dy/dx) respectively；Central pointIt is to be calculated according to following formula:
After completing elliptical center of circle fitting, start to carry out oval major semiaxis as shown in Figure 2, semi-minor axis, oval direction
The fitting at angle.The specific method is as follows for it:
If { xi,yi,θiRespectively indicate point on edge, then:
The ratio for remembering semi-minor axis and major semiaxis is N:
The tangent value for remembering oval deflection is K:K=tan ρ
N, K have following relationship:
The above method is also suitble to other two o'clocks on edge line, then has following relationship:
Above formula is written as: α K2+ β K- α=0, α=s1s2-s3s4, β=s2s4(s3-s1)+s1s3(s4-s2)+(s1+s2-s3-s4),
Solve the true defining K value of equation:
Point (x on elliptical edge linei,yi) point (x with the coordinate system of elliptical center origino,yo) there are following relationships:
According to above formula, obtain:
It thereby determines that:To obtain major semiaxis A, semi-minor axis B, oval deflection ρ.
Finally, obtaining elliptic curve to above-mentioned fitting needs to examine and judge whether it is appropriate suitable curve, this Shen
Please in lenth ratio proof method is respectively adopted or ellipse fitting fraction method is judged.Wherein, the tool of the proof method of lenth ratio
Body process are as follows: the Rectangular Bounding Volume of the edge line of pupil candidate region is surrounded in setting, and the perimeter half and pupil of the bounding box are ellipse
The ratio of circle the sum of half shaft length measures, i.e. bounding box is having a size of W × H, then ratioIt is set in advance if Q is greater than
Fixed threshold value, then it is assumed that be ellipse, otherwise give up the curve；The detailed process of ellipse fitting fraction method are as follows: ellipse by what is arrived
The ratio of point and all points of edge line on circle is recognized as ellipse fitting score S if S is greater than preset threshold value
To be ellipse, otherwise give up the curve.
The foregoing is merely presently preferred embodiments of the present invention, is only used to illustrate the technical scheme of the present invention, and is not intended to limit
Determine protection scope of the present invention.Any modification, equivalent substitution, improvement and etc. done all within the spirits and principles of the present invention,
It is included within the scope of protection of the present invention.
Claims (9)
1. determining the elliptical method of pupil in a kind of iris image, which is characterized in that this method comprises:
(1) iris image is obtained, pupil candidate region is determined by threshold method；
(2) edge of pupil candidate region is detected and determined；
(3) concave, convex detection and classification are carried out to pixel each on edge；
(4) screening of edge line；
(5) the elliptical center of pupil, half long and short axis and oval direction are calculated using the position of the point on edge line；
(6) the pupil ellipse obtained to upper step is tested and is confirmed.
2. determining the elliptical method of pupil in iris image according to claim 1, which is characterized in that lead in step (1)
It crosses threshold method and determines that pupil candidate region method is as follows:
(1-1) counts the grey level histogram that the pixel number on the different gray values of iris image obtains: H={ Hi, 0 <=i
<=255 }, wherein HiIt is the number for the pixel that gray value is i in iris image；
It is q that (1-2), which presets pupil region and the pixel ratio of iris image, then divides the threshold epsilon of pupil candidate region by following formula
It determines:Wherein N is the number of iris image pixel, and the i when above formula takes equal sign is threshold epsilon；
It is pupil candidate region that (1-3), which selects the gray value of iris image pixel to be less than the region of threshold value,.
3. determining the elliptical method of pupil in iris image according to claim 1, which is characterized in that right in step (2)
The edge of pupil candidate region is detected and determined, and the specific method is as follows:
The shade of gray Dx and Dy of level, vertical direction on (2-1) calculating each pixel in pupil candidate region；
(2-2) is preset if the absolute value of horizontal gradient or vertical gradient on the pixel of pupil candidate region is less than
Threshold value η, then the gray scale of the pixel is 0, otherwise is 255, and what the pixel that gray scale is 255 was formed by connecting is that pupil is candidate
The edge M in region.
4. determining the elliptical method of pupil in iris image according to claim 1, which is characterized in that right in step (3)
Each pixel carries out the step of concave, convex detection and classification on edge are as follows:
(3-1) calculates the product of the shade of gray Dx and Dy of edge each point, if being concavity edge, otherwise is convexity side when jack per line
Edge, and
(3-2) carries out quadrant classification to edge line, specifically: taking one section of beginning and end of convexity edge line is diagonal line, building
One includes rectangle, should be divided into two parts by this section of edge line comprising rectangle, area is less than lower section above convexity edge line
When area, this section of edge line is located at first quartile, and otherwise edge line is in third quadrant；Equally take one Duan Qidian of concavity edge line
It is diagonal line with terminal, building one includes rectangle, should be divided into two parts, concavity edge by this section of edge line comprising rectangle
When area is less than area under above line, this section of edge line is located at the second quadrant, and otherwise edge line is in fourth quadrant.
5. determining the elliptical method of pupil in iris image according to claim 1, which is characterized in that in step (4)
The screening of edge line；After above-mentioned steps (3), edge line is divided into following four class: A: belonging to the chimb edge of first quartile；B: belong to
In the concave edge edge of the second quadrant；C: belong to the chimb edge of third quadrant；D: belong to the concave edge edge of fourth quadrant；To above-mentioned not same district
The edge line length computation in domain, edge length < Lmin is deleted, and Lmin is preset length value, close to 0.
6. determining the elliptical method of pupil in iris image according to claim 1, which is characterized in that ellipse has following property
Matter: one section of arc on ellipse corresponds to the line at the midpoint of string by two oval points of intersection of tangents of two endpoints of arc with the arc
By elliptical center, therefore the specific steps of step (5) are as follows:
(5-1) is to aaOne section of edge line is divided into two sections from midpoint and obtains three point P1,P12,P2, point m1,m2It is line segment P respectively1P12,
P12P2Midpoint, point P1 a,It is point P respectively1,P12,P2The point of intersection of tangents, obtain straight line l using aforementioned ellipse properties1,l2From
And central point C12；
(5-2) selects one section of edge line ab, using the available central point C of (5-1) same method34；
(5-3) obtains multiple central points using the method for (5-1) repeatedly, after be averaged to each central point after acquisition pupil it is ellipse
Round center；The above-mentioned specific calculation formula for calculating (5-1) are as follows: assuming that { xi,yi,θi| i=1,2 } respectively indicate point P1,
P2, xi,yi,θiIt is the abscissa, ordinate and gradient direction angle of corresponding points, i.e. arctan (dy/dx) respectively；Central pointIt is to be calculated according to following formula:
(5-4) calculates elliptical long semi-minor axis and deflection: setting A, B, ρ are oval major semiaxis, semi-minor axis, oval direction respectively
Angle, { xi,yi,θiRespectively indicate point on edge, then:
The ratio for remembering semi-minor axis and major semiaxis is N:
The tangent value for remembering oval deflection is K:K=tan ρ
N, K have following relationship:
The above method is also suitble to other two o'clocks on edge line, then has following relationship:
Above formula is written as: α K2+ β K- α=0, α=s1s2-s3s4, β=s2s4(s3-s1)+s1s3(s4-s2)+(s1+s2-s3-s4), it solves
The true defining K value of equation:
Point (x on elliptical edge linei,yi) point (x with the coordinate system of elliptical center origino,yo) there are following relationships:
According to above formula, obtain:
It thereby determines that:To obtain major semiaxis A, semi-minor axis B, oval deflection ρ.
7. determining the elliptical method of pupil in iris image according to claim 1, which is characterized in that in step (6)
It includes: the proof method of lenth ratio or the proof method of ellipse fitting fraction method that pupil ellipse, which is tested with confirmation method,.
8. determining the elliptical method of pupil in iris image according to claim 7, which is characterized in that lenth ratio is tested
The detailed process of demonstration are as follows: the Rectangular Bounding Volume of the edge line of pupil candidate region, the perimeter half of the bounding box are surrounded in setting
And the ratio of the sum of pupil oval half length measures, i.e. bounding box is having a size of W × H, then ratioIf Q is big
In preset threshold value, then it is assumed that be ellipse, otherwise give up the curve.
9. determining the elliptical method of pupil in iris image according to claim 7, which is characterized in that ellipse fitting score
The detailed process of method are as follows: using to ellipse on point and all points of edge line ratio as ellipse fitting score S, such as
Fruit S is greater than preset threshold value, then it is assumed that is ellipse, otherwise gives up the curve.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910566465.6A CN110276324B (en) | 2019-06-27 | 2019-06-27 | Method for determining pupil ellipse in iris image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910566465.6A CN110276324B (en) | 2019-06-27 | 2019-06-27 | Method for determining pupil ellipse in iris image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110276324A true CN110276324A (en) | 2019-09-24 |
| CN110276324B CN110276324B (en) | 2021-06-22 |
Family
ID=67963461
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910566465.6A Active CN110276324B (en) | 2019-06-27 | 2019-06-27 | Method for determining pupil ellipse in iris image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110276324B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110929672A (en) * | 2019-11-28 | 2020-03-27 | 联想(北京)有限公司 | Pupil positioning method and electronic equipment |
| CN111160113A (en) * | 2019-12-10 | 2020-05-15 | 中山市奥珀金属制品有限公司 | Iris positioning method, device and storage medium |
| CN115187599A (en) * | 2022-09-09 | 2022-10-14 | 之江实验室 | Light-weight monocrystalline silicon elliptical parameter identification method and system based on geometric properties |
| CN115601825A (en) * | 2022-10-25 | 2023-01-13 | 扬州市职业大学(扬州开放大学)（Cn） | Method for evaluating reading capability based on visual positioning technology |
| WO2023088069A1 (en) * | 2021-11-19 | 2023-05-25 | 北京眼神智能科技有限公司 | Iris recognition method and apparatus, storage medium, and device |
| CN116503387A (en) * | 2023-06-25 | 2023-07-28 | 聚时科技(深圳)有限公司 | Image detection method, device, equipment, system and readable storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7286753B2 (en) * | 2004-03-04 | 2007-10-23 | Olympus Corporation | Image capturing apparatus |
| CN102411784A (en) * | 2011-07-13 | 2012-04-11 | 河南理工大学 | Simple and rapid extraction method of correlated information of ellipses in digital image |
| CN103136512A (en) * | 2013-02-04 | 2013-06-05 | 重庆市科学技术研究院 | Pupil positioning method and system |
| CN103366157A (en) * | 2013-05-03 | 2013-10-23 | 马建 | Method for judging line-of-sight distance of human eye |
| CN103598870A (en) * | 2013-11-08 | 2014-02-26 | 北京工业大学 | Optometry method based on depth-image gesture recognition |
| CN103679180A (en) * | 2012-09-19 | 2014-03-26 | 武汉元宝创意科技有限公司 | Sight tracking method based on single light source of single camera |
| CN104182720A (en) * | 2013-05-22 | 2014-12-03 | 北京三星通信技术研究有限公司 | Pupil detection method and device |
| CN105931252A (en) * | 2016-05-16 | 2016-09-07 | 大连理工大学 | Ellipse rapid detection method based on geometric constraint |
| CN105955465A (en) * | 2016-04-25 | 2016-09-21 | 华南师范大学 | Desktop portable sight line tracking method and apparatus |
| CN107301638A (en) * | 2017-05-27 | 2017-10-27 | 东南大学 | A kind of ellipse detection method based on arc support line segment |
| CN109145821A (en) * | 2018-08-16 | 2019-01-04 | 新智数字科技有限公司 | The method and device that pupil image is positioned in a kind of pair of eye image |
| CN109840484A (en) * | 2019-01-23 | 2019-06-04 | 张彦龙 | A kind of pupil detection method based on edge filter, oval evaluation and pupil verifying |
-
2019
- 2019-06-27 CN CN201910566465.6A patent/CN110276324B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7286753B2 (en) * | 2004-03-04 | 2007-10-23 | Olympus Corporation | Image capturing apparatus |
| CN102411784A (en) * | 2011-07-13 | 2012-04-11 | 河南理工大学 | Simple and rapid extraction method of correlated information of ellipses in digital image |
| CN103679180A (en) * | 2012-09-19 | 2014-03-26 | 武汉元宝创意科技有限公司 | Sight tracking method based on single light source of single camera |
| CN103136512A (en) * | 2013-02-04 | 2013-06-05 | 重庆市科学技术研究院 | Pupil positioning method and system |
| CN103366157A (en) * | 2013-05-03 | 2013-10-23 | 马建 | Method for judging line-of-sight distance of human eye |
| CN104182720A (en) * | 2013-05-22 | 2014-12-03 | 北京三星通信技术研究有限公司 | Pupil detection method and device |
| CN103598870A (en) * | 2013-11-08 | 2014-02-26 | 北京工业大学 | Optometry method based on depth-image gesture recognition |
| CN105955465A (en) * | 2016-04-25 | 2016-09-21 | 华南师范大学 | Desktop portable sight line tracking method and apparatus |
| CN105931252A (en) * | 2016-05-16 | 2016-09-07 | 大连理工大学 | Ellipse rapid detection method based on geometric constraint |
| CN107301638A (en) * | 2017-05-27 | 2017-10-27 | 东南大学 | A kind of ellipse detection method based on arc support line segment |
| CN109145821A (en) * | 2018-08-16 | 2019-01-04 | 新智数字科技有限公司 | The method and device that pupil image is positioned in a kind of pair of eye image |
| CN109840484A (en) * | 2019-01-23 | 2019-06-04 | 张彦龙 | A kind of pupil detection method based on edge filter, oval evaluation and pupil verifying |
Non-Patent Citations (1)
| Title |
|---|
| MICHELE FORNACIARI ET AL: "A fast and effective ellipse detector for embedded vision applications", 《PATTERN RECOGNITION》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110929672A (en) * | 2019-11-28 | 2020-03-27 | 联想(北京)有限公司 | Pupil positioning method and electronic equipment |
| CN110929672B (en) * | 2019-11-28 | 2024-03-01 | 联想(北京)有限公司 | Pupil positioning method and electronic equipment |
| CN111160113A (en) * | 2019-12-10 | 2020-05-15 | 中山市奥珀金属制品有限公司 | Iris positioning method, device and storage medium |
| WO2023088069A1 (en) * | 2021-11-19 | 2023-05-25 | 北京眼神智能科技有限公司 | Iris recognition method and apparatus, storage medium, and device |
| CN115187599A (en) * | 2022-09-09 | 2022-10-14 | 之江实验室 | Light-weight monocrystalline silicon elliptical parameter identification method and system based on geometric properties |
| CN115187599B (en) * | 2022-09-09 | 2022-12-13 | 之江实验室 | Light-weight monocrystalline silicon elliptical parameter identification method and system based on geometric properties |
| CN115601825A (en) * | 2022-10-25 | 2023-01-13 | 扬州市职业大学(扬州开放大学)（Cn） | Method for evaluating reading capability based on visual positioning technology |
| CN115601825B (en) * | 2022-10-25 | 2023-09-19 | 扬州市职业大学(扬州开放大学) | Method for evaluating reading ability based on visual positioning technology |
| CN116503387A (en) * | 2023-06-25 | 2023-07-28 | 聚时科技(深圳)有限公司 | Image detection method, device, equipment, system and readable storage medium |
| CN116503387B (en) * | 2023-06-25 | 2024-03-26 | 聚时科技(深圳)有限公司 | Image detection method, device, equipment, system and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110276324B (en) | 2021-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110276324A (en) | The elliptical method of pupil is determined in a kind of iris image | |
| TWI224287B (en) | Iris extraction method | |
| US9087238B2 (en) | Device and method for iris recognition using a plurality of iris images having different iris sizes | |
| Nair et al. | 3-D face detection, landmark localization, and registration using a point distribution model | |
| CN103473571B (en) | Human detection method | |
| CN101246544B (en) | Iris positioning method based on boundary point search and minimum kernel value similarity region edge detection | |
| WO2017059591A1 (en) | Finger vein identification method and device | |
| Johnson et al. | Quality in face and iris research ensemble (Q-FIRE) | |
| KR101632912B1 (en) | Method for User Authentication using Fingerprint Recognition | |
| CN102214291A (en) | Method for quickly and accurately detecting and tracking human face based on video sequence | |
| CN101593352A (en) | Driving safety monitoring system based on face orientation and visual focus | |
| CN110245626B (en) | Method for accurately detecting eyelash image in iris image | |
| CN102867179A (en) | Method for detecting acquisition quality of digital certificate photo | |
| CN109376708B (en) | Method for extracting ROI | |
| CN103034838A (en) | Special vehicle instrument type identification and calibration method based on image characteristics | |
| CN104680154B (en) | A kind of personal identification method merged based on face characteristic and palm print characteristics | |
| CN109871818A (en) | Face identification method based on normal vector distribution histogram and covariance description | |
| WO2023088069A1 (en) | Iris recognition method and apparatus, storage medium, and device | |
| KR101101142B1 (en) | A system and method for identifying the iris of persons in unrestricted condition | |
| CN109767436B (en) | Method and device for identifying authenticity of seal | |
| CN109766857A (en) | A kind of three-dimensional face identification method based on semantic alignment multizone template fusion | |
| CN104537334B (en) | A method of improving the iris recognition performance under non-ideal environment | |
| CN1319014C (en) | Personal identity recognising method based on pinna geometric parameter | |
| CN108288040A (en) | Multi-parameter face identification system based on face contour | |
| CN109801222A (en) | A kind of palate wrinkle tilted image antidote based on direction vector |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100081 Room 204, building 3, Fuhai center, Daliushu, Haidian District, Beijing Patentee after: Beijing wanlihong Technology Co.,Ltd. Address before: 100081 Room 204, building 3, Fuhai center, Daliushu, Haidian District, Beijing Patentee before: BEIJING SUPERRED TECHNOLOGY Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |