CN109614858A - A kind of detection method and device of pupil center - Google Patents
A kind of detection method and device of pupil center Download PDFInfo
- Publication number
- CN109614858A CN109614858A CN201811291708.1A CN201811291708A CN109614858A CN 109614858 A CN109614858 A CN 109614858A CN 201811291708 A CN201811291708 A CN 201811291708A CN 109614858 A CN109614858 A CN 109614858A
- Authority
- CN
- China
- Prior art keywords
- pupil
- region
- point
- boundary point
- center
- 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
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/193—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a kind of detection method of pupil center and devices, and pupil region locating for pupil is extracted specially from facial image；The preliminary multiple boundary points for extracting pupil region；False border interference point is rejected from multiple boundary points, obtains true pupil boundary point set；Elliptical parameter is determined according to true pupil boundary point set, and by ellipse fitting method, and ellipse is the central point of pupil.Due to wherein carrying out noise spot rejecting to the pupil boundary points of extraction, and then the position of pupil center is calculated by ellipse fitting method, to improve the accuracy that pupil center is detected under occlusion state.
Description
Technical field
The present invention relates to tracking technique field is realized, more particularly to the detection method and device of a kind of pupil center.
Background technique
The key of visual trace technology is the accurate detection to pupil center.However, in the image of actual photographed, pupil
Shape is simultaneously irregular, and the often interference by eyelid, eyelashes, hot spot and blink etc..What pupil detection generallyd use
Method is ellipse fitting to be carried out according to the boundary point of pupil region, but for the pupil under occlusion state, extracted
Boundary point can partly be distorted, if directly using these boundary points carry out ellipse fitting, cause extract pupil center not
Accurately, so that calculated direction of visual lines be made to have bigger deviation.
Summary of the invention
In view of this, the present invention provides a kind of detection method of pupil center and device, with solve practical sight with
The problem for causing pupil center's detection error larger because being blocked when track.
To solve the above-mentioned problems, the invention discloses a kind of detection methods of pupil center, are applied to eye tracking system
In system, pupil center's detection method comprising steps of
Pupil region locating for pupil is extracted from facial image；
Tentatively extract multiple boundary points of the pupil region；
False border interference point is rejected from the multiple boundary point, obtains true pupil boundary point set；
Elliptical parameter is determined according to the true pupil boundary point set, and by ellipse fitting method, and the ellipse is
For the central point of the pupil.
It is optionally, described that pupil region locating for pupil is extracted from facial image, comprising:
Binary conversion treatment is carried out to the facial image, obtains binary image；
The binary image is extracted, the pupil region of binaryzation is obtained.
Optionally, the multiple boundary points for tentatively extracting the pupil region, comprising:
Tentatively it is set to according to center of the pupil region to the pupil, obtains rough central point；
The pupil region is split to connection labeling algorithm using eight, multiple connected regions are obtained, according to each
The area accounting and its region mass center of the connected region calculate credible pupil region at a distance from the rough central point；
The profile of the credible pupil region is extracted, and regard borderline multiple points of the profile as the multiple side
Boundary's point
It is optionally, described that false border interference point is rejected from the multiple boundary point, comprising:
It for each boundary point in the multiple boundary point, is successively detected in default neighborhood, extracts first most
Big edge strength determines boundary point as first if the first maximal margin intensity is greater than the first preset threshold；
By it is each it is described just determine boundary point in the default neighborhood and detect, the second maximal margin intensity of extraction, such as
Second maximal margin intensity described in fruit is greater than the second preset threshold, then described just will determine boundary point and be denoted as the true pupil boundary
One element of point set.
A kind of detection device of pupil center is additionally provided, is applied in gaze tracking system, pupil center's detection
Method comprising steps of
Region extraction module, for extracting pupil region locating for pupil from facial image；
Border points extraction module, for tentatively extracting multiple boundary points of the pupil region；
Noise spot rejects module, for rejecting false border interference point from the multiple boundary point, obtains true
Pupil boundary point set；
Center point calculation module for according to the true pupil boundary point set, and is determined by ellipse fitting method ellipse
Round parameter, the central point of the oval as pupil.
Optionally, the region extraction module includes:
Binarization unit obtains binary image for carrying out binary conversion treatment to the facial image；
It extracts execution unit and obtains the pupil region of binaryzation for extracting to the binary image.
Optionally, the border points extraction unit includes:
The thick order member of central point, for being tentatively set to according to center of the pupil region to the pupil, obtains
Rough central point；
Area calculation unit obtains multiple for being split to connection labeling algorithm to the pupil region using eight
Connected region calculates at a distance from the rough central point according to the area accounting of each connected region and its region mass center
Credible pupil region；
Contours extract unit, for extracting the profile of the credible pupil region, and by the borderline more of the profile
A point is as the multiple boundary point
Optionally, the noise spot rejecting module includes:
First selection unit, for for each boundary point in the multiple boundary point, successively in default neighborhood into
Row detection, extracts the first maximal margin intensity, if the first maximal margin intensity is greater than the first preset threshold, is made
Just to determine boundary point；
Second selection unit, for by it is each it is described just determine boundary point in the default neighborhood and detect, extraction the
Two maximal margin intensity just determine boundary point note for described if the second maximal margin intensity is greater than the second preset threshold
For an element of the true pupil boundary point set.
It can be seen from the above technical proposal that the present invention provides a kind of detection method of pupil center and devices, specifically
To extract pupil region locating for pupil from facial image；The preliminary multiple boundary points for extracting pupil region；From multiple boundaries
False border interference point is rejected in point, obtains true pupil boundary point set；According to true pupil boundary point set, and by ellipse
Circle approximating method determines elliptical parameter, and ellipse is the central point of pupil.Due to wherein being carried out to the pupil boundary points of extraction
Noise spot is rejected, and then the position of pupil center is calculated by ellipse fitting method, to improve pupil under occlusion state
The accuracy of Spot detection.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of flow chart of the detection method of pupil center provided by the embodiments of the present application；
Fig. 2 is a kind of block diagram of the detection device of pupil center provided by the embodiments of the present application.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Embodiment one
Fig. 1 is a kind of flow chart of the detection method of pupil center provided by the embodiments of the present application.
Shown in referring to Fig.1, detection method provided in this embodiment is for examining the center of the pupil in facial image
It surveys, so as to be tracked according to the center to sight therein, which specifically includes step:
S1, pupil region locating for pupil is extracted from facial image.
In the present embodiment, examined using the facial image that binarization method obtains picture pick-up device or camera installation
It surveys, obtains the pupil region.
In original human eye gray scale image, pupil position shows the very low ellipse of gray value or the part that is blocked
The elliptical shape in region, other position gray values are higher, and the noise spot gray value that wherein eyelash is formed is also very low, but due to
It counts less, does not influence the preresearch estimates to pupil position.
When carrying out pupil region extraction, firstly, carrying out image binaryzation processing by selected fixed threshold T, make pupil
The profile in region highlights.
Wherein, f (x, y) is eye grayscale image, and g (x, y) is the facial image after binaryzation post-processing.
After obtaining the facial image of binaryzation, the binaryzation of pupil is extracted by image segmentation, denoising, edge detection
Pupil region.
S2, the preliminary multiple boundary points for extracting pupil region.
First according to the pupil image obtained after binary conversion treatment, coarse localization is carried out to pupil center, is obtained in rough
Heart point.The position for defining rough central point is O (x, y), and sets (xn,yn) it is image various point locations, then have:
Secondly, reject binaryzation after by the formation such as eyelashes interference region, use eight to connection labeling algorithm to image into
Row segmentation, divides the image into several connected regions, by the area accounting and each region center of mass point that compare each connected region
The Distance Judgment of position and rough central point O (x, y) goes out credible pupil region.
Then, the profile of pupil region is extracted using Sobel edge detection algorithm, and multiple boundary points of profile are stored
For point set C.
Border interference point in S3, the multiple boundary points of rejecting.
So-called border interference point refers in multiple boundary points obtained above because blocking the false boundary point to be formed.Really
Pupil boundary points, between pupil and iris；The pupil boundary points of distortion, be often positioned in pupil and eyelid or hot spot it
Between；So true pupil boundary points have two attributes:
To consistency in 1.；
2. export-oriented step evolution, and step degree is less than the step degree of distortion pupil boundary points, i.e. P (iris)-P (pupil)
< P (eyelid)-P (pupil), P (iris)-P (pupil) < P (hot spot)-P (pupil), in which:
It is introversive: the direction from boundary point to pupil center
It is export-oriented: with it is interior in the opposite direction
P (iris): the gray value of iris
P (eyelid): the gray value of eyelid
P (pupil): the gray value of pupil
P (hot spot): the gray value of hot spot
Definition threshold value T1 is P (eyelid)-P (pupil), and T2 is P (hot spot)-P (pupil), and pupil center's point rough position is O
(x,y).Following detection process is carried out to boundary point:
Firstly, choosing certain boundary point CiAs starting point, in CiIt is detected in the neighborhood in the direction O, extracts the first maximal margin
Intensity Ei1。
If Ei1Less than the first preset threshold T1, then to CiIn OCiIt is detected in the neighborhood in direction, extracts the second maximum side
Edge intensity Ei2If Ei2Less than the second preset threshold T2, then Ci is saved to true pupil boundary point set NC, as therein one
A element.
And so on, each boundary point is subjected to above-mentioned detection, the boundary point then conduct to above-mentioned condition is unsatisfactory for
Interference boundary point is rejected, until traversing all boundary points.
By boundary points detection, the noise spot that eyelid, hot spot can be blocked to generation is rejected, and point set NC is to retain after rejecting
Effective pupil boundary point set.
S4, the central point that pupil is calculated according to true pupil boundary point set.
Ellipse fitting is carried out according to true pupil boundary point set NC, finds out pupil center's point position.Pupil is by pupil boundary
Point set NC is as ellipse fitting boundary point, with ellipse representation pupil shape, stealthy equation are as follows:
ax2+bxy+cy2+ dx+ey+f=0
By specifying constraint, criterion is minimised as to elliptical algebraic distance quadratic sum with each boundary point, using most
Small square law principle finds out coefficient vector [a, b, c, d, e, f]T, to calculate the position elliptical center point E (x, y):
Elliptical center point position is to reject pupil center's point position after interference.
It can be seen from the above technical proposal that present embodiments provide a kind of detection method of pupil center, specially from
Pupil region locating for pupil is extracted in facial image；The preliminary multiple boundary points for extracting pupil region；From multiple boundary points
False border interference point is rejected, true pupil boundary point set is obtained；According to true pupil boundary point set, and by oval quasi-
Conjunction method determines elliptical parameter, and ellipse is the central point of pupil.Due to wherein interfering the pupil boundary points of extraction
Point is rejected, and then the position of pupil center is calculated by ellipse fitting method, to improve pupil center under occlusion state
The accuracy of detection.
It should be noted that for simple description, therefore, it is stated as a series of action groups for embodiment of the method
It closes, but those skilled in the art should understand that, embodiment of that present invention are not limited by the describe sequence of actions, because according to
According to the embodiment of the present invention, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art also should
Know, the embodiments described in the specification are all preferred embodiments, and the related movement not necessarily present invention is implemented
Necessary to example.
Embodiment two
Fig. 2 is a kind of block diagram of the detection device of pupil center provided by the embodiments of the present application.
Referring to shown in Fig. 2, detection device provided in this embodiment is for examining the center of the pupil in facial image
It surveys, so as to be tracked according to the center to sight therein, which specifically includes region extraction module 10, side
Boundary's point extraction module 20, noise spot reject module 30 and center point calculation module 40.
Region extraction module is used to extract pupil region locating for pupil from facial image.
In the present embodiment, examined using the facial image that binarization method obtains picture pick-up device or camera installation
It surveys, obtains the pupil region.
In original human eye gray scale image, pupil position shows the very low ellipse of gray value or the part that is blocked
The elliptical shape in region, other position gray values are higher, and the noise spot gray value that wherein eyelash is formed is also very low, but due to
It counts less, does not influence the preresearch estimates to pupil position.
The module includes binarization unit and extracts execution unit, and when carrying out pupil region extraction, binarization unit is logical
It crosses selected fixed threshold T and carries out image binaryzation processing, highlight the profile of pupil region.
Wherein, f (x, y) is eye grayscale image, and g (x, y) is the facial image after binaryzation post-processing.
It extracts execution unit to be used for after obtaining the facial image of binaryzation, be mentioned by image segmentation, denoising, edge detection
Take the pupil region of the binaryzation of pupil.
Border points extraction module is for tentatively extracting multiple boundary points of pupil region.
The module specifically includes the thick order member of central point, area calculation unit and contours extract unit.The thick order of central point
Member is for carrying out coarse localization to pupil center, obtaining rough central point according to the pupil image obtained after binary conversion treatment.It is fixed
The position of adopted rough central point is O (x, y), and sets (xn,yn) it is image various point locations, then have:
Area calculation unit is used to reject the interference region after binaryzation by formation such as eyelashes, and use eight is calculated to connection label
Method is split image, divides the image into several connected regions, by comparing the area accounting of each connected region and each
The Distance Judgment of region mass center point position and rough central point O (x, y) goes out credible pupil region.
Contours extract unit is used to extract the profile of pupil region using Sobel edge detection algorithm, and by the more of profile
A boundary point is stored as point set C.
Noise spot rejects module and is used to reject the border interference point in multiple boundary points.
So-called border interference point refers in multiple boundary points obtained above because blocking the false boundary point to be formed.Really
Pupil boundary points, between pupil and iris；The pupil boundary points of distortion, be often positioned in pupil and eyelid or hot spot it
Between；So true pupil boundary points have two attributes:
To consistency in 1.；
2. export-oriented step evolution, and step degree is less than the step degree of distortion pupil boundary points, i.e. P (iris)-P (pupil)
< P (eyelid)-P (pupil), P (iris)-P (pupil) < P (hot spot)-P (pupil), in which:
It is introversive: the direction from boundary point to pupil center
It is export-oriented: with it is interior in the opposite direction
P (iris): the gray value of iris
P (eyelid): the gray value of eyelid
P (pupil): the gray value of pupil
P (hot spot): the gray value of hot spot
Definition threshold value T1 is P (eyelid)-P (pupil), and T2 is P (hot spot)-P (pupil), and pupil center's point rough position is O
(x,y).The module specifically includes the first selection unit and the second selection unit.
First selection unit is for choosing certain boundary point CiAs starting point, in CiIt is detected, is extracted in the neighborhood in the direction O
First maximal margin intensity Ei1。
If the second selection unit is used for Ei1Less than the first preset threshold T1, then to CiIn OCiIt is examined in the neighborhood in direction
It surveys, extracts the second maximal margin intensity Ei2If Ei2Less than the second preset threshold T2, then Ci is saved to true pupil boundary points
Collect NC, as one of element.
And so on, each boundary point is detected using said two units, to the side for being unsatisfactory for above-mentioned condition
Boundary's point is then rejected as interference boundary point, until traversing all boundary points.
By boundary points detection, the noise spot that eyelid, hot spot can be blocked to generation is rejected, and point set NC is to retain after rejecting
Effective pupil boundary point set.
Center point calculation module is used to calculate the central point of pupil according to true pupil boundary point set.
Ellipse fitting is carried out according to true pupil boundary point set NC, finds out pupil center's point position.Pupil is by pupil boundary
Point set NC is as ellipse fitting boundary point, with ellipse representation pupil shape, stealthy equation are as follows:
ax2+bxy+cy2+ dx+ey+f=0
By specifying constraint, criterion is minimised as to elliptical algebraic distance quadratic sum with each boundary point, using most
Small square law principle finds out coefficient vector [a, b, c, d, e, f]T, to calculate the position elliptical center point E (x, y):
Elliptical center point position is to reject pupil center's point position after interference.
It can be seen from the above technical proposal that present embodiments provide a kind of detection device of pupil center, specially from
Pupil region locating for pupil is extracted in facial image；The preliminary multiple boundary points for extracting pupil region；From multiple boundary points
False border interference point is rejected, true pupil boundary point set is obtained；According to true pupil boundary point set, and by oval quasi-
Conjunction method determines elliptical parameter, and ellipse is the central point of pupil.Due to wherein interfering the pupil boundary points of extraction
Point is rejected, and then the position of pupil center is calculated by ellipse fitting method, to improve pupil center under occlusion state
The accuracy of detection.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple
Place illustrates referring to the part of embodiment of the method.
All the embodiments in this specification are described in a progressive manner, the highlights of each of the examples are with
The difference of other embodiments, the same or similar parts between the embodiments can be referred to each other.
It should be understood by those skilled in the art that, the embodiment of the embodiment of the present invention can provide as method, apparatus or calculate
Machine program product.Therefore, the embodiment of the present invention can be used complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.Moreover, the embodiment of the present invention can be used one or more wherein include computer can
With in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form of the computer program product of implementation.
The embodiment of the present invention be referring to according to the method for the embodiment of the present invention, terminal device (system) and computer program
The flowchart and/or the block diagram of product describes.It should be understood that flowchart and/or the block diagram can be realized by computer program instructions
In each flow and/or block and flowchart and/or the block diagram in process and/or box combination.It can provide these
Computer program instructions are set to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminals
Standby processor is to generate a machine, so that being held by the processor of computer or other programmable data processing terminal devices
Capable instruction generates for realizing in one or more flows of the flowchart and/or one or more blocks of the block diagram
The device of specified function.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing terminal devices
In computer-readable memory operate in a specific manner, so that instruction stored in the computer readable memory generates packet
The manufacture of command device is included, which realizes in one side of one or more flows of the flowchart and/or block diagram
The function of being specified in frame or multiple boxes.
These computer program instructions can also be loaded into computer or other programmable data processing terminal devices, so that
Series of operation steps are executed on computer or other programmable terminal equipments to generate computer implemented processing, thus
The instruction executed on computer or other programmable terminal equipments is provided for realizing in one or more flows of the flowchart
And/or in one or more blocks of the block diagram specify function the step of.
Although the preferred embodiment of the embodiment of the present invention has been described, once a person skilled in the art knows bases
This creative concept, then additional changes and modifications can be made to these embodiments.So the following claims are intended to be interpreted as
Including preferred embodiment and fall into all change and modification of range of embodiment of the invention.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap
Those elements are included, but also including other elements that are not explicitly listed, or further includes for this process, method, article
Or the element that terminal device is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited
Element, it is not excluded that there is also other identical elements in process, method, article or the terminal device for including the element.
Technical solution provided by the present invention is described in detail above, specific case used herein is to this hair
Bright principle and embodiment is expounded, method of the invention that the above embodiments are only used to help understand and its
Core concept；At the same time, for those skilled in the art, according to the thought of the present invention, in specific embodiment and application
There will be changes in range, in conclusion the contents of this specification are not to be construed as limiting the invention.
Claims (8)
1. a kind of detection method of pupil center is applied in gaze tracking system, which is characterized in that pupil center's detection
Method comprising steps of
Pupil region locating for pupil is extracted from facial image；
Tentatively extract multiple boundary points of the pupil region；
False border interference point is rejected from the multiple boundary point, obtains true pupil boundary point set；
Elliptical parameter, the oval as institute are determined according to the true pupil boundary point set, and by ellipse fitting method
State the central point of pupil.
2. detection method as described in claim 1, which is characterized in that described to extract pupil locating for pupil from facial image
Region, comprising:
Binary conversion treatment is carried out to the facial image, obtains binary image；
The binary image is extracted, the pupil region of binaryzation is obtained.
3. detection method as described in claim 1, which is characterized in that the multiple boundaries for tentatively extracting the pupil region
Point, comprising:
Tentatively it is set to according to center of the pupil region to the pupil, obtains rough central point；
The pupil region is split to connection labeling algorithm using eight, multiple connected regions are obtained, according to each described
The area accounting and its region mass center of connected region calculate credible pupil region at a distance from the rough central point；
The profile of the credible pupil region is extracted, and regard borderline multiple points of the profile as the multiple boundary
Point.
4. detection method as described in claim 1, which is characterized in that it is described rejected from the multiple boundary point it is false
Border interference point, comprising:
It for each boundary point in the multiple boundary point, is successively detected in default neighborhood, extracts the first maximum side
Edge intensity determines boundary point as first if the first maximal margin intensity is greater than the first preset threshold；
By it is each it is described just determine boundary point in the default neighborhood and detect, the second maximal margin intensity of extraction, if institute
The second maximal margin intensity is stated greater than the second preset threshold, then it will described just determining boundary point be denoted as the true pupil boundary point set
An element.
5. a kind of detection device of pupil center is applied in gaze tracking system, which is characterized in that pupil center's detection
Method comprising steps of
Region extraction module, for extracting pupil region locating for pupil from facial image；
Border points extraction module, for tentatively extracting multiple boundary points of the pupil region；
Noise spot rejects module and obtains true pupil for rejecting false border interference point from the multiple boundary point
Boundary point set；
Center point calculation module for according to the true pupil boundary point set, and is determined by ellipse fitting method elliptical
Parameter, the central point of the oval as pupil.
6. detection device as claimed in claim 5, which is characterized in that the region extraction module includes:
Binarization unit obtains binary image for carrying out binary conversion treatment to the facial image；
It extracts execution unit and obtains the pupil region of binaryzation for extracting to the binary image.
7. detection device as claimed in claim 5, which is characterized in that the border points extraction unit includes:
The thick order member of central point obtains rough for being tentatively set to according to center of the pupil region to the pupil
Central point；
Area calculation unit obtains multiple connections for being split to connection labeling algorithm to the pupil region using eight
Region calculates at a distance from the rough central point credible according to the area accounting of each connected region and its region mass center
Pupil region；
Contours extract unit, for extracting the profile of the credible pupil region, and by borderline multiple points of the profile
As the multiple boundary point.
8. detection device as claimed in claim 5, which is characterized in that the noise spot rejects module and includes:
First selection unit, for successively being examined in default neighborhood for each boundary point in the multiple boundary point
It surveys, extracts the first maximal margin intensity, if the first maximal margin intensity is greater than the first preset threshold, as first
Determine boundary point；
Second selection unit, for by it is each it is described just determine boundary point in the default neighborhood and detect, extraction second is most
Big edge strength described just will determine boundary point and be denoted as institute if the second maximal margin intensity is greater than the second preset threshold
State an element of true pupil boundary point set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811291708.1A CN109614858B (en) | 2018-10-31 | 2018-10-31 | Pupil center detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811291708.1A CN109614858B (en) | 2018-10-31 | 2018-10-31 | Pupil center detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109614858A true CN109614858A (en) | 2019-04-12 |
| CN109614858B CN109614858B (en) | 2021-01-15 |
Family
ID=66002747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811291708.1A Active CN109614858B (en) | 2018-10-31 | 2018-10-31 | Pupil center detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109614858B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112434675A (en) * | 2021-01-26 | 2021-03-02 | 西南石油大学 | Pupil positioning method for global self-adaptive optimization parameters |
| CN113342161A (en) * | 2021-05-27 | 2021-09-03 | 常州工学院 | Sight tracking method based on near-to-eye camera |
| CN115546143A (en) * | 2022-09-30 | 2022-12-30 | 杭州长川科技股份有限公司 | Method and device for positioning center point of wafer, storage medium and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040174496A1 (en) * | 2003-03-06 | 2004-09-09 | Qiang Ji | Calibration-free gaze tracking under natural head movement |
| CN103996020A (en) * | 2014-04-10 | 2014-08-20 | 中航华东光电（上海）有限公司 | Head mounted eye tracker detection method |
| 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 |
| CN105955465A (en) * | 2016-04-25 | 2016-09-21 | 华南师范大学 | Desktop portable sight line tracking method and apparatus |
| CN106022315A (en) * | 2016-06-17 | 2016-10-12 | 北京极创未来科技有限公司 | Pupil center positioning method for iris recognition |
| US9760774B2 (en) * | 2014-08-29 | 2017-09-12 | Alps Electric Co., Ltd. | Line-of-sight detection apparatus |
-
2018
- 2018-10-31 CN CN201811291708.1A patent/CN109614858B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040174496A1 (en) * | 2003-03-06 | 2004-09-09 | Qiang Ji | Calibration-free gaze tracking under natural head movement |
| 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 |
| CN103996020A (en) * | 2014-04-10 | 2014-08-20 | 中航华东光电（上海）有限公司 | Head mounted eye tracker detection method |
| US9760774B2 (en) * | 2014-08-29 | 2017-09-12 | Alps Electric Co., Ltd. | Line-of-sight detection apparatus |
| CN105955465A (en) * | 2016-04-25 | 2016-09-21 | 华南师范大学 | Desktop portable sight line tracking method and apparatus |
| CN106022315A (en) * | 2016-06-17 | 2016-10-12 | 北京极创未来科技有限公司 | Pupil center positioning method for iris recognition |
Non-Patent Citations (2)
| Title |
|---|
| SALAH RABBA等: "Pupil localization for gaze estimation using unsupervised graph-based model", 《2017 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS)》 * |
| 胡畔等: "基于视线跟踪技术的眼控鼠标", 《天津师范大学学报（自然科学版）》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112434675A (en) * | 2021-01-26 | 2021-03-02 | 西南石油大学 | Pupil positioning method for global self-adaptive optimization parameters |
| CN113342161A (en) * | 2021-05-27 | 2021-09-03 | 常州工学院 | Sight tracking method based on near-to-eye camera |
| CN113342161B (en) * | 2021-05-27 | 2022-10-14 | 常州工学院 | Sight tracking method based on near-to-eye camera |
| CN115546143A (en) * | 2022-09-30 | 2022-12-30 | 杭州长川科技股份有限公司 | Method and device for positioning center point of wafer, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109614858B (en) | 2021-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101317183B (en) | Method for localizing pixels representing an iris in an image acquired of an eye | |
| KR101808467B1 (en) | Feature extraction and matching and template update for biometric authentication | |
| US7929734B2 (en) | Method and apparatus for detecting eyes in face region | |
| Kang et al. | Real-time image restoration for iris recognition systems | |
| Sutra et al. | The Viterbi algorithm at different resolutions for enhanced iris segmentation | |
| CN101317184A (en) | Method for extracting features of an iris in images | |
| CN111914665B (en) | Face shielding detection method, device, equipment and storage medium | |
| CN109614858A (en) | A kind of detection method and device of pupil center | |
| CN103778406B (en) | Method for checking object and equipment | |
| CN106203358B (en) | A kind of iris locating method and equipment | |
| JP2007188504A (en) | Method for filtering pixel intensity in image | |
| CN106570447B (en) | Based on the matched human face photo sunglasses automatic removal method of grey level histogram | |
| CN103198301B (en) | iris locating method and device | |
| Asmuni et al. | An improved multiscale retinex algorithm for motion-blurred iris images to minimize the intra-individual variations | |
| CN109446935B (en) | Iris positioning method for iris recognition in long-distance traveling | |
| Fazilov et al. | Algorithm for Extraction of the Iris Region in an Eye Image | |
| Soelistio et al. | Circle-based eye center localization (CECL) | |
| KR100794361B1 (en) | The eyelid detection and eyelash interpolation method for the performance enhancement of iris recognition | |
| KR20180072517A (en) | Method for detecting borderline between iris and sclera | |
| Kovoor et al. | Iris biometric recognition system employing canny operator | |
| Sreecholpech et al. | A robust model-based iris segmentation | |
| CN110502996A (en) | A kind of dynamic identifying method towards fuzzy finger vein image | |
| KR102466084B1 (en) | Image-based pupil detection method | |
| James | A Review of Daugman’s Algorithm in Iris Segmentation | |
| JP7452677B2 (en) | Focus determination device, iris authentication device, focus determination method, and program |
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 |