CN112308014B - High-speed accurate searching and positioning method for pupil and cornea reflecting spot of two eyes - Google Patents
High-speed accurate searching and positioning method for pupil and cornea reflecting spot of two eyes Download PDFInfo
- Publication number
- CN112308014B CN112308014B CN202011291428.8A CN202011291428A CN112308014B CN 112308014 B CN112308014 B CN 112308014B CN 202011291428 A CN202011291428 A CN 202011291428A CN 112308014 B CN112308014 B CN 112308014B
- Authority
- CN
- China
- Prior art keywords
- eyes
- pupils
- image
- center
- gray
- 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
- 210000001747 pupil Anatomy 0.000 title claims abstract description 135
- 210000004087 cornea Anatomy 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 18
- 230000006978 adaptation Effects 0.000 claims description 6
- 230000005484 gravity Effects 0.000 claims description 6
- 230000004424 eye movement Effects 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 6
- 238000012360 testing method Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000004397 blinking Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000003920 cognitive function Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
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
- G06V40/19—Sensors therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Eye Examination Apparatus (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a high-speed accurate searching and positioning method for pupil and cornea reflecting points of two eyes, and belongs to the field of image processing. The invention comprises the following steps: collecting gray images of two eyes; selecting a first threshold value set based on searching for the pupil boundary of the two eyes according to the gray value of the gray image, and converting the current gray image into a binary image according to the first threshold value; calculating the boundary of the two-eye pupils according to the binary image, and calculating the center point coordinates of the two-eye pupils according to the boundary of the two-eye pupils; and simultaneously, selecting a second threshold value set based on searching the cornea reflecting points of the two eyes according to the gray value of the gray image, searching a position exceeding the second threshold value on the gray image according to the second threshold value, and calculating the center coordinates of the cornea reflecting points of the two eyes according to the position. The invention can quickly find the accurate positions of the boundary and the center of the pupils of the eyes and the accurate positions of the reflective spots of the cornea of the eyes on each frame of image at the frame rate of 1018-1020fps, and the processing speed is far higher than the eye movement speed.
Description
Technical Field
The invention relates to the field of image processing, in particular to a high-speed accurate searching and positioning method for pupil and cornea reflecting points of two eyes.
Background
At present, some mature algorithms exist for searching and positioning pupils (such as OpenCV) through image analysis, and through sufficient tests, the mature algorithm libraries are powerful and very stable, but at present, the mature algorithms all have efficiency problems, and the boundary point of the pupils cannot be quickly found in 1408 x 290 resolution images within 600 microseconds, and parameters such as the center point coordinates of the pupils, the diameter and the area of the pupils cannot be directly calculated.
The well-established algorithm library also needs custom development to find the cornea reflecting points near the pupil areas in the images captured by the cameras, and the algorithm has the same efficiency problem, and can not find two cornea reflecting points near the pupil areas of the eyes in 1408 x 290 resolution images within 200 microseconds.
According to the actual situation, the algorithm needs to support simultaneous positioning of both eyes or positioning of only one eye, anchor the position of the pupil of the eye, and smooth the data of the eye position, and the customization is not available in a mature image processing algorithm library.
Disclosure of Invention
The invention aims to provide a high-speed accurate searching and positioning method for a binocular pupil and a cornea reflecting point, which can quickly find the accurate positions of the boundary and the center of the binocular pupil and the accurate positions of the binocular cornea reflecting point on each frame of image at a frame rate of 1018-1020fps, and the processing speed is far higher than the eye movement speed.
The invention solves the technical problems and adopts the following technical scheme: the high-speed accurate searching and positioning method for the pupil and cornea reflecting points of the eyes comprises the following steps:
Collecting gray images of two eyes;
Selecting a first threshold value set based on searching for the pupil boundary of the two eyes according to the gray value of the gray image, and converting the current gray image into a binary image according to the first threshold value;
Calculating the boundary of the two-eye pupils according to the binary image, and calculating the center point coordinates of the two-eye pupils according to the boundary of the two-eye pupils;
And simultaneously, selecting a second threshold value set based on searching the cornea reflecting points of the two eyes according to the gray value of the gray image, searching a position exceeding the second threshold value on the gray image according to the second threshold value, and calculating the center coordinates of the cornea reflecting points of the two eyes according to the position.
As a preferable scheme, before the gray level images of the eyes are acquired, a light source corresponding to an image acquisition device for acquiring the gray level images of the eyes is installed, and the light source faces the direction and the position of the eyes to be tested.
As a preferred solution, the image acquisition device is an industrial camera, and the industrial camera can support outputting an image with a maximum frame rate of 1018-1020fps through a data acquisition card.
As a preferable mode, the selecting based on the gray value of the gray image is based on finding a threshold value of one set by the pupil boundary of both eyes:
extracting and selecting a threshold value for the current gray image adaptation based on gray histogram features of the image; or alternatively
A self-defined threshold is manually set or selected on the parameter setting interface.
As a preferable solution, the calculating the boundary of the pupil of the two eyes according to the binary image, and calculating the coordinates of the center point of the pupil of the two eyes according to the boundary of the pupil of the two eyes specifically includes the following steps:
Positioning the boundary of the pupils of the eyes based on a ray algorithm of horizontal rays and vertical rays from inside to outside;
Fitting each positioned pupil boundary into a circle or ellipse by adopting a least square fitting circle algorithm;
And finding the position of the circle center by adopting a least square fitting circle algorithm, namely the calculated center point coordinates of the pupils of the eyes.
As a preferred scheme, the diameter and the area of the pupils of the eyes are calculated simultaneously when the coordinates of the central points of the pupils of the eyes are calculated.
As a preferable scheme, after calculating the coordinates of the central points of the pupils of the two eyes, drawing the central position of the pupils of the two eyes in a video image window by using vertical lines with the length being the radius of the pupils of the two eyes, wherein the central point of each pupil is positioned at the middle position of the corresponding vertical line;
after the center position of the pupils of the two eyes is drawn, connecting the center points of the pupils of the two eyes by a straight line in a video image window;
and drawing a vertical line at the center of the straight line connecting the center points of the pupils of the two eyes, wherein the length of the vertical line is the longitudinal height difference of the centers of the pupils of the two eyes, so that whether the two eyes are positioned at the horizontal position can be observed or judged more easily.
As a preferable mode, when the gray value selection based on the finding of the threshold value two set by the corneal reflection point of the eyes is based on the gray value of the gray image:
extracting and selecting a threshold value for the current gray image adaptation based on gray histogram features of the image; or alternatively
A self-defined threshold is manually set or selected on the parameter setting interface.
As a preferable scheme, the searching for a position exceeding the threshold value two on the gray level image according to the threshold value two, and calculating the central coordinate of the reflecting point of the cornea of the two eyes according to the position, which specifically refers to:
And calculating the mass center or the gravity center of the binocular cornea reflecting point through the position, wherein the mass center or the gravity center is the central coordinate of the binocular cornea reflecting point.
As a preferred scheme, after calculating the center coordinates of the two-eye cornea reflection points, the center positions of the two-eye cornea reflection points are drawn by crosses in the video image window.
The invention has the advantages that the condition of eye movement change can be captured very fast through the high-speed accurate searching and positioning method of the pupil and cornea reflecting points of the two eyes, and the speed of the eye movement is completely faster than that of the eye movement, so that a good foundation can be laid for the subsequent research of the biological characteristics of the eye movement, and meanwhile, the early preparation work is made for the research of the physiological and cognitive function level of the brain.
Drawings
Fig. 1 is a flowchart of a method for precisely searching and positioning pupil and cornea reflection points at high speed in an embodiment of the invention.
Detailed Description
The technical scheme of the invention is described in detail below with reference to the accompanying drawings and the embodiments.
Examples
The embodiment provides a high-speed accurate searching and positioning method for pupil and cornea reflecting points of two eyes, the flow chart of which is shown in figure 1, wherein the method comprises the following steps:
And S1, installing a light source corresponding to an image acquisition device for acquiring gray level images of the two eyes, wherein the light source faces the direction and the position of the two eyes to be tested.
Here, in order to allow the camera to capture a clear picture in a relatively closed device environment, a suitable light source is required, which also forms two corneal glistenings on the surface of the eyes, and what is seen on the camera picture is two small bright spots.
And S2, installing an industrial grade professional camera and a data acquisition card, capturing binocular image data through the camera, wherein the image data is a gray level image in the embodiment, and transmitting the data to a corresponding processing module for calculating the center point coordinates of pupils of the eyes and the center coordinates of reflection points of the cornea of the eyes through the data acquisition card.
Here, the industrial camera supports and outputs the image with the highest frame rate of 1018-1020fps through the data acquisition card, and the embodiment can efficiently and accurately calculate the center point coordinates of the pupils of the eyes and the center coordinates of the reflection points of the cornea of the eyes in real time.
And S3, calculating the boundary of the pupils of the eyes and the coordinates of the central points of the pupils of the eyes, and simultaneously, calculating the central coordinates of the reflective spots of the cornea of the eyes.
For calculating the boundary of the pupils of the eyes and the coordinates of the central points of the pupils of the eyes, the method specifically comprises the following steps:
Selecting a first threshold value set based on searching for the pupil boundary of the two eyes according to the gray value of the gray image, and converting the current gray image into a binary image according to the first threshold value; and calculating the boundary of the two-eye pupils according to the binary image, and calculating the center point coordinates of the two-eye pupils according to the boundary of the two-eye pupils.
Wherein, selecting a threshold value based on searching for the pupil boundary of the two eyes according to the gray value of the gray image: the threshold value for the current gray image adaptation may be extracted and selected based on the gray histogram features of the image; or manually set or select a self-defined threshold on the parameter setting interface.
The method for calculating the boundary of the two-eye pupils according to the binary image and calculating the center point coordinates of the two-eye pupils according to the boundary of the two-eye pupils specifically comprises the following steps:
Positioning the boundary of the pupils of the eyes based on a ray algorithm of horizontal rays and vertical rays from inside to outside;
Fitting each positioned pupil boundary into a circle or ellipse by adopting a least square fitting circle algorithm;
And finding the position of the circle center by adopting a least square fitting circle algorithm, namely the calculated center point coordinates of the pupils of the eyes.
It should be noted that, when calculating the center point coordinates of the pupils of both eyes, the diameter and the area of the pupils of both eyes may be calculated at the same time.
In addition, after the coordinates of the central points of the pupils of the two eyes are calculated, the central position of the pupils of the two eyes can be drawn by using vertical lines with the length being the radius of the pupils of the two eyes in the video image window, and the central point of each pupil is positioned at the middle position of the corresponding vertical line; when the center position of the pupils of the eyes is drawn, a straight line is used for connecting the center points of the pupils of the eyes in the video image window, a vertical line is drawn at the center of the straight line connecting the center points of the pupils of the eyes, and the length of the vertical line is the longitudinal height difference of the centers of the pupils of the eyes, so that a main test person can conveniently observe whether the eyes keep horizontal or not when using the system, if the connecting line between the pupils of the eyes at the positions which are not horizontal, some distortion can occur, and meanwhile, a straight line segment is seen in the middle of the connecting line between the centers of the pupils of the eyes (the most ideal case is that the straight line segment cannot be seen, namely, the eyes are positioned at the horizontal position).
For calculating the center coordinates of the glistenings of the cornea, it is specifically:
And selecting a second threshold value set based on searching for the cornea reflecting points of the two eyes according to the gray value of the gray image, searching for a position exceeding the second threshold value on the gray image according to the second threshold value, and calculating the center coordinates of the cornea reflecting points of the two eyes according to the position.
Here, when the second threshold value set based on finding the corneal reflection point of both eyes is selected based on the gradation value of the gradation image: the threshold value for the current gray image adaptation may be extracted and selected based on the gray histogram features of the image; or manually set or select a self-defined threshold on the parameter setting interface.
And searching a position exceeding the threshold value II on the gray level image according to the threshold value II, and calculating the center coordinate of the reflecting point of the cornea of the eyes according to the position, which is specifically: and calculating the mass center or the gravity center of the binocular cornea reflecting point through the position, wherein the mass center or the gravity center is the central coordinate of the binocular cornea reflecting point.
In this embodiment, after the center coordinates of the glistenings points of the cornea of the eyes are calculated, the center positions of the glistenings points of the cornea of the eyes can be drawn by crosses in the video image window.
In summary, in this embodiment, after receiving the tested binocular image data, the algorithm library for locating the pupil and the reflective spot of the cornea of the binocular may perform analysis according to the image gray scale value of the image data, find the position of the pupil of the binocular, gradually find the boundary point of the pupil of the binocular, find the position coordinates of the center point of the pupil of the binocular according to the boundary point of the pupil of the binocular, calculate the number of pixel points within the range of the pupil of the binocular according to the gray scale value of the pupil of the binocular, and calculate the radius and diameter of the pupil of the binocular according to the center point and the boundary of the pupil of the binocular.
And searching and positioning the pupil and the reflective spot of the cornea of the eyes, and after receiving the tested image data of the eyes, analyzing according to the gray level of the image data to find out the position coordinates of the reflective spot of the cornea of the eyes. And drawing the center of the binocular pupils by using a vertical line (the length is the radius of the binocular pupils) in a video image window according to the center point of the binocular pupils and the positions of the binocular cornea reflecting points found by an algorithm for searching and positioning the binocular pupils and the binocular cornea reflecting points, and drawing the center position of the binocular cornea reflecting points by using a cross.
If the two-eye pupils are selected to be searched and positioned simultaneously, if the two-eye pupils are found simultaneously, the center positions of the two-eye pupils are required to be connected by a straight line in the video image window, a vertical line is drawn at the center of the straight line connecting the center points of the two-eye pupils, and the length of the vertical line is the longitudinal height difference of the centers of the two-eye pupils, so that a main test person can conveniently observe whether the two eyes keep horizontal or not when using the system, if the connecting line between the two-eye pupils at the positions which are not horizontal, some distortion can occur, and meanwhile, a straight line segment is seen in the middle of the connecting line between the centers of the two-eye pupils (the most ideal case is that the straight line segment cannot be seen, namely, the two eyes are positioned at the horizontal position).
Finally, searching an algorithm library for positioning the binocular pupils and the binocular cornea reflecting points and finally uploading the found coordinate positions (horizontal direction X and vertical direction Y) of the center points of the pupils, the diameters of the pupils, the areas of the pupils and the coordinate positions (horizontal direction X and vertical direction Y) of the cornea reflecting points to an upper layer application, namely, a system for analyzing eye movement data.
Therefore, the invention solves the problem that the time consumption of the existing pupil positioning algorithms is too long, simultaneously solves the self-needs of people to find the two-eye pupils and the two-eye cornea reflecting points at the same time, marks the real-time position of the two-eye pupils and the real-time position of the two-eye cornea reflecting points in a real-time video image window of a camera, and provides parameters such as the center position coordinates (horizontal X coordinate and vertical Y coordinate) of the two-eye pupils, the area and the diameter of the two-eye pupils, the center coordinates (horizontal X coordinate and vertical Y coordinate) of the two-eye cornea reflecting points, the marks whether the two-eye pupils are positioned, the marks whether the two-eye cornea reflecting points are found and the like for upper layer application.
That is, the present embodiment can support the highest frame rate (1018-1020 fps) output by the industrial-level camera, and quickly find the accurate position of the pupil center of the binocular and the accurate position of the binocular cornea reflection point on each frame of image, and mark the pupil boundary point of the binocular and the position of the binocular cornea reflection point, if both the pupils are found, the center points of the pupils of the binocular are also required to be connected by a straight line, and a vertical line is drawn at the center of the straight line connecting the center points of the pupils of the binocular, and the length is the longitudinal height difference of the centers of the pupils of the binocular, so that whether the eyes are in the horizontal position is convenient to observe. At present, the accurate positions of the eyes and the cornea reflection points of each frame of image can be found without throwing one frame under the condition of no blinking, and the frame rate is always kept between 1018 and 1020 fps.
Claims (6)
1. The high-speed accurate searching and positioning method for the pupil and cornea reflecting points of the eyes is characterized by comprising the following steps:
Collecting gray images of two eyes through an image collecting device; the image acquisition equipment is an industrial camera, and the industrial camera can support to output the gray level image with the highest frame rate of 1018-1020fps through a data acquisition card;
Under the condition that the frame rate is always kept between 1018-1020fps and one frame is not lost, selecting a first threshold value set based on searching for the pupil boundary of the two eyes according to the gray value of the gray image, and converting the current gray image into a binary image according to the first threshold value;
Calculating the boundary of the two-eye pupils according to the binary image, and calculating the center point coordinates of the two-eye pupils according to the boundary of the two-eye pupils, comprising: positioning the boundary of the pupils of the eyes based on a ray algorithm of horizontal rays and vertical rays from inside to outside; fitting each positioned pupil boundary into a circle or ellipse by adopting a least square fitting circle algorithm; finding the position of the circle center by adopting a least square fitting circle algorithm, namely, calculating the center point coordinates of the pupils of the eyes; when calculating the coordinates of the central points of the pupils of the two eyes, calculating the diameter and the area of the pupils simultaneously; the center point coordinates of the pupils of the eyes comprise X coordinates in the horizontal direction and Y coordinates in the vertical direction;
Meanwhile, selecting a second threshold value set based on searching for the cornea reflecting points of the two eyes according to the gray value of the gray image, searching for a position exceeding the second threshold value on the gray image according to the second threshold value, and calculating the center coordinates of the cornea reflecting points of the two eyes according to the position; the central coordinates of the two-eye cornea reflecting points comprise X coordinates in the horizontal direction and Y coordinates in the vertical direction;
After the coordinates of the central points of the pupils of the two eyes are calculated, the central position of the pupils of the two eyes is drawn in a video image window by using vertical lines with the length being the radius of the pupils, and the central point of each pupil is positioned at the middle position of the corresponding vertical line; after the center position of the pupils of the two eyes is drawn, connecting the center points of the pupils of the two eyes by a straight line in a video image window; drawing a vertical line at the center of a straight line connecting the center points of the pupils of the eyes, wherein the length of the vertical line is the longitudinal height difference of the centers of the pupils of the eyes;
The center point coordinates of the pupils of the both eyes, the area and the diameter of the pupils of the both eyes, and the center coordinates of the glints of the cornea of the both eyes for each frame are provided to an upper layer application.
2. The high-speed accurate searching and positioning method for pupil and cornea reflecting points of two eyes according to claim 1, wherein before the gray level images of the two eyes are acquired, a light source corresponding to an image acquisition device for acquiring the gray level images of the two eyes is required to be installed, and the light source faces the direction and the position of the two eyes to be tested.
3. The method for high-speed accurate search and positioning of binocular pupils and corneal glints according to claim 1, wherein the gray value selection based on finding a threshold value set by the boundary of the binocular pupils is one:
extracting and selecting a threshold value for the current gray image adaptation based on gray histogram features of the image; or alternatively
A self-defined threshold is manually set or selected on the parameter setting interface.
4. The method for high-speed accurate searching and positioning of the two-eye pupil and cornea reflecting points according to claim 1, wherein when the gray value selection based on finding the threshold value two set by the two-eye cornea reflecting points according to the gray image:
extracting and selecting a threshold value for the current gray image adaptation based on gray histogram features of the image; or alternatively
A self-defined threshold is manually set or selected on the parameter setting interface.
5. The method for high-speed accurate searching and positioning of the pupil and the corneal glints according to claim 1 or 4, wherein the searching for a position exceeding the threshold value two on the gray level image according to the threshold value two and calculating the center coordinates of the corneal glints according to the position are specifically:
And calculating the mass center or the gravity center of the binocular cornea reflecting point through the position, wherein the mass center or the gravity center is the central coordinate of the binocular cornea reflecting point.
6. The high-speed accurate search positioning method for a binocular pupil and a corneal reflection point according to claim 5, wherein the center position of the binocular corneal reflection point is drawn with a cross in a video image window after the center coordinates of the binocular corneal reflection point are calculated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011291428.8A CN112308014B (en) | 2020-11-18 | 2020-11-18 | High-speed accurate searching and positioning method for pupil and cornea reflecting spot of two eyes |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011291428.8A CN112308014B (en) | 2020-11-18 | 2020-11-18 | High-speed accurate searching and positioning method for pupil and cornea reflecting spot of two eyes |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112308014A CN112308014A (en) | 2021-02-02 |
CN112308014B true CN112308014B (en) | 2024-05-14 |
Family
ID=74334984
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011291428.8A Active CN112308014B (en) | 2020-11-18 | 2020-11-18 | High-speed accurate searching and positioning method for pupil and cornea reflecting spot of two eyes |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112308014B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114004880B (en) * | 2021-04-08 | 2023-04-25 | 四川大学华西医院 | Point cloud and strong reflection target real-time positioning method of binocular camera |
CN114129126B (en) * | 2022-01-29 | 2022-05-27 | 北京九辰智能医疗设备有限公司 | Cornea center positioning method, device, equipment and storage medium |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107536598A (en) * | 2016-06-29 | 2018-01-05 | 沈阳新松机器人自动化股份有限公司 | Binocular vision pupil positioning method and relevant device |
CN107833251A (en) * | 2017-11-13 | 2018-03-23 | 京东方科技集团股份有限公司 | Pupil positioning device and method, the display driver of virtual reality device |
CN108229392A (en) * | 2018-01-02 | 2018-06-29 | 京东方科技集团股份有限公司 | A kind of pupil positioning method, device, equipment and medium |
CN108921010A (en) * | 2018-05-15 | 2018-11-30 | 北京环境特性研究所 | A kind of pupil detection method and detection device |
CN109525774A (en) * | 2017-09-19 | 2019-03-26 | 三星电子株式会社 | For correcting the electronic device of image and operating the method for the electronic device |
CN109857254A (en) * | 2019-01-31 | 2019-06-07 | 京东方科技集团股份有限公司 | Pupil positioning method and device, VR/AR equipment and computer-readable medium |
WO2019144710A1 (en) * | 2018-01-23 | 2019-08-01 | 北京七鑫易维信息技术有限公司 | Method and apparatus for determining position of pupil |
CN110623629A (en) * | 2019-07-31 | 2019-12-31 | 毕宏生 | Visual attention detection method and system based on eyeball motion |
CN111462156A (en) * | 2020-03-30 | 2020-07-28 | 温州医科大学 | Image processing method for acquiring corneal vertex |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160019420A1 (en) * | 2014-07-15 | 2016-01-21 | Qualcomm Incorporated | Multispectral eye analysis for identity authentication |
KR102478952B1 (en) * | 2016-01-05 | 2022-12-20 | 삼성전자주식회사 | Method for storing image and electronic device thereof |
-
2020
- 2020-11-18 CN CN202011291428.8A patent/CN112308014B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107536598A (en) * | 2016-06-29 | 2018-01-05 | 沈阳新松机器人自动化股份有限公司 | Binocular vision pupil positioning method and relevant device |
CN109525774A (en) * | 2017-09-19 | 2019-03-26 | 三星电子株式会社 | For correcting the electronic device of image and operating the method for the electronic device |
CN107833251A (en) * | 2017-11-13 | 2018-03-23 | 京东方科技集团股份有限公司 | Pupil positioning device and method, the display driver of virtual reality device |
CN108229392A (en) * | 2018-01-02 | 2018-06-29 | 京东方科技集团股份有限公司 | A kind of pupil positioning method, device, equipment and medium |
WO2019144710A1 (en) * | 2018-01-23 | 2019-08-01 | 北京七鑫易维信息技术有限公司 | Method and apparatus for determining position of pupil |
CN108921010A (en) * | 2018-05-15 | 2018-11-30 | 北京环境特性研究所 | A kind of pupil detection method and detection device |
CN109857254A (en) * | 2019-01-31 | 2019-06-07 | 京东方科技集团股份有限公司 | Pupil positioning method and device, VR/AR equipment and computer-readable medium |
CN110623629A (en) * | 2019-07-31 | 2019-12-31 | 毕宏生 | Visual attention detection method and system based on eyeball motion |
CN111462156A (en) * | 2020-03-30 | 2020-07-28 | 温州医科大学 | Image processing method for acquiring corneal vertex |
Non-Patent Citations (5)
Title |
---|
A Fast and Accurate Pupil Localization Method Using Gray Gradient Differential and Curve Fitting;Lin, Y 等;《Proceedings of the 4th International Conference on Computer Engineering and Networks》;第355卷;第495–503页 * |
Detection of Pupil and Corneal Reflection Using High-speed Camera for Gaze Detection Under Face Intense Illumination and a Solution of Glass Reflection Problem by Improving Light Source;Kiyotaka Fukumoto 等;《HCI International 2015 - Posters’ Extended Abstracts》;20150807;第475–480页 * |
动基座下双目鱼眼视觉系统目标定位算法研究;王博宇;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20190815;C036-63 * |
基于虹膜采集定位系统的研究;宗瑞山;《中国优秀硕士学位论文全文数据库 信息科技辑》;I138-810 * |
角膜曲率和瞳孔直径数字化检测方法研究;黄国林;《中国优秀硕士学位论文全文数据库 医药卫生科技辑》;E073-104 * |
Also Published As
Publication number | Publication date |
---|---|
CN112308014A (en) | 2021-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108918519B (en) | Cell smear image acquisition and analysis system | |
US6997556B2 (en) | Method for detecting, evaluating, and analyzing look sequences | |
CN112308014B (en) | High-speed accurate searching and positioning method for pupil and cornea reflecting spot of two eyes | |
CN109977813A (en) | A kind of crusing robot object localization method based on deep learning frame | |
CN104469152B (en) | The automatic camera method and system of Wearable | |
CN109429060B (en) | Pupil distance measuring method, wearable eye equipment and storage medium | |
CN103674839A (en) | Visual sample positioning operating system and method based on light spot detection | |
CN109431452B (en) | Unmanned eye health screening instrument | |
CN110736748A (en) | Immunohistochemical nuclear plasma staining section diagnosis method and system | |
CN110850723A (en) | Fault diagnosis and positioning method based on transformer substation inspection robot system | |
JP2002505134A (en) | Exercise pattern evaluation method and apparatus | |
CN102799878B (en) | Iris face fusion acquisition device | |
CN105180802B (en) | A kind of dimension of object information identifying method and device | |
CN111128382A (en) | Artificial intelligence multimode imaging analytical equipment | |
CN110145692A (en) | Sewage conduct CCTV detection system and method | |
CN109106333A (en) | A kind of self-service vision drop system of automatic adjustable and device | |
CN116358841B (en) | Microscope lens self-identification calibration system | |
CN109905641A (en) | A kind of target monitoring method, apparatus, equipment and system | |
CN111579466B (en) | Household sperm detection device and detection method | |
CN110472546B (en) | Infant non-contact eye movement feature extraction device and method | |
WO2022247067A1 (en) | Intelligent eye examination method, device and system | |
JP2004062393A (en) | Method and device for determining attention | |
CN112182300A (en) | Automatic tracking device and method | |
CN115661453B (en) | Tower crane object detection and segmentation method and system based on downward view camera | |
CN115471552B (en) | Shooting positioning method and system for portable mydriasis-free fundus camera |
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 |