CN109872378A - Facial expression image eye mapping method based on infrared camera - Google Patents
Facial expression image eye mapping method based on infrared camera Download PDFInfo
- Publication number
- CN109872378A CN109872378A CN201711262477.7A CN201711262477A CN109872378A CN 109872378 A CN109872378 A CN 109872378A CN 201711262477 A CN201711262477 A CN 201711262477A CN 109872378 A CN109872378 A CN 109872378A
- Authority
- CN
- China
- Prior art keywords
- iris
- intersection point
- center
- facial expression
- image
- 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.)
- Pending
Links
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Analysis (AREA)
Abstract
A kind of facial expression image eye mapping method based on infrared camera, the facial expression image is all-purpose card role's threedimensional model, it is acted by user's current face and is generated in real time, the infrared camera can shoot user's eyes image, image segmentation algorithm divides to obtain human eye area, iris region and pupil region in user's eyes image, and the ocular of facial expression image generates in real time according to user's eyes image data.User's eyes image data include eyelid opening degree, iris position in human eye area, pupil position, iris shape, pupil shape, iris diameter and pupil diameter in iris.
Description
Technical field
The present invention relates to technical field of image processing, and in particular to a kind of facial expression image eye based on infrared camera reflects
Shooting method.
Background technique
Interaction is assisted when in the prior art, in order to achieve the purpose that iris capturing, iris image acquiring interface can be direct
The realtime graphic for showing camera acquisition, the scheme for separately having a kind of auxiliary interaction are iris image acquiring interfaces using animation shape
As in the scheme for showing animating image in iris capturing at present, the ocular of animating image is generally directly by camera institute
The eye image filling of acquisition is entered, and is kept iris image acquiring interface uncoordinated, is reduced user experience.
There are also a kind of generation methods of full animation expression in the prior art, can acquire user's face movement and generate corresponding expression
Three-dimensional animation model, but the eye movement that the ocular of three-dimensional animation model described in the prior art is scaled without direction of visual lines pupil
Feature, therefore expression in the eyes is not lively enough.
Summary of the invention
In order to solve the above technical problem, the present invention provides a kind of facial expression image eye mapping side based on infrared camera
Method.
The present invention is realized by following steps: the table in the facial expression image eye mapping method based on infrared camera
Feelings image is all-purpose card role's threedimensional model, is acted by user's current face and is generated in real time, which is characterized in that the infrared photography
Head can shoot user's eyes image, and image segmentation algorithm divides to obtain human eye area in user's eyes image, iris region
And pupil region, the ocular of facial expression image generate in real time according to user's eyes image data.
The present invention is based on the improvement of the facial expression image eye mapping method of infrared camera to be, user's eyes image
Data include eyelid opening degree, iris position in human eye area, pupil position, iris shape, pupil shape, iris are straight in iris
Diameter and pupil diameter.
The present invention is based on the facial expression image eye mapping method of infrared camera further improvement lies in that, the eyelid is opened
It is right to be determined by human eye area length-width ratio.
The present invention is based on the facial expression image eye mapping method of infrared camera further improvement lies in that, the iris position
The determination method set comprising steps of image segmentation algorithm is fitted to obtain the iris outer circle in user's eyes image, by iris outside
The round center of circle determines horizontal and vertical two straight lines, and two linear extensions are ended to human eye area profile point of intersection;It will
The intersection point of intersection point and right side on the left of horizontal linear and human eye area profile, the intersection point of vertical straight line and human eye area profile top
With the intersection point of lower part and the center of circle of iris outer circle, it is referred to as left intersection point, right intersection point, upper intersection point, lower intersection point and the center of circle, it is left
Intersection point is referred to as distance 1 at a distance from the center of circle, and right intersection point is referred to as distance 2 at a distance from the center of circle, and upper intersection point is referred to as at a distance from the center of circle
Distance 3, lower intersection point are referred to as distance 4 at a distance from the center of circle, calculate the proportionate relationship of distance 1 and distance 2, the ratio of distance 3 and distance 4
Example relationship, determines iris position.
The present invention is based on the facial expression image eye mapping method of infrared camera further improvement lies in that, the iris position
The determination method set is comprising steps of determine center by human eye area profile, using center as origin, establishes coordinate system, coordinate system with
The left intersection point of human eye area profile, right intersection point, upper intersection point, lower intersecting point coordinate be respectively (X00,0), (X01,0), (0, Y00), (0,
Y01), image segmentation algorithm is fitted to obtain the iris outer circle in user's eyes image, determine iris outer circle central coordinate of circle (X0,
Y0);Center is determined by the ocular profile of facial expression image, using center as origin, establishes coordinate system, coordinate system and facial expression image
The left intersection point of ocular profile, right intersection point, upper intersection point, lower intersecting point coordinate be respectively (X10,0), (X11,0), (0, Y10),
(0, Y11);Iris center (X1, Y1) in the ocular of facial expression image is determined according to (X0, the Y0).
The present invention is based on the facial expression image eye mapping method of infrared camera further improvement lies in that, the expression figure
Iris center (X1, the Y1) method of determination includes step in the ocular of picture, if (X0, Y0) is located at first quartile, then X1=X0*
X01/X11,Y1=Y0*Y00/Y10;If (X0, Y0) is located at the second quadrant, then X1=X0*X00/X10, Y1=Y0*Y00/Y10;If
(X0, Y0) is located at third quadrant, then X1=X0*X00/X10, Y1=Y0*Y01/Y11;If (X0, Y0) is located at fourth quadrant, then X1
=X0*X01/X11、Y1=Y0*Y01/Y11。
The present invention can make the more natural coordination of the interaction of the animation image in iris capturing interface, for the animation table generated in real time
Feelings add expression in the eyes information, more vividly.
Detailed description of the invention
Fig. 1 is human eye area schematic diagram.
Fig. 2 is iris position mapping method schematic diagram.
Specific embodiment
As shown in Figure 1, image segmentation algorithm segmentation user's eyes image obtains human eye area 10, iris outer circle 11 and iris
Inner circle 12.The iris inner circle is pupil region profile.
Iris position mapping method is as shown in Fig. 2, specific steps include:
Center o is found in human eye area 21 first, establishes coordinate system by origin of o, in the present embodiment coordinate system and human eye
The right intersection point of region contour, upper intersecting point coordinate are respectively (11,0) b, and the coordinate of a (0,5), iris outer circle center of circle c are c (4,0.5).
According to the shape and default conditions of the ocular 22 of facial expression image, default center point o1 is established by origin of o1
Coordinate system, the right intersection point of the ocular profile of coordinate system and facial expression image, upper intersecting point coordinate are respectively b1 in the present embodiment
(14,0), a1 (0,18).
It is right in the coordinate system that the ocular center o1 using facial expression image is established by origin to calculate iris outer circle center of circle c
Answer coordinate c1(x, y).
Calculation method are as follows: x=14*4/11=5.1, y=18*0.5/5=1.8.
C1 (5.1,1.8) is determined in the coordinate system that the ocular center o1 using facial expression image is established by origin.
Iris outer circle is established by the center of circle of c1.
Iris patterns according to iris shape distortion in human eye area and pupil shape distortion data, in facial expression image
With corresponding distortion is made on the basis of pupil pattern, establish the iris shape and pupil shape of facial expression image.
By iris diameter in human eye area and pupil diameter according to preset ratio relationship to the iris and pupil of facial expression image
Size is configured.
It is inclined in iris to pupil corresponding in facial expression image according to the degree of eccentricity of the pupil in human eye area in iris
Heart degree is configured.
It is another be iris method for determining position described in example comprising steps of image segmentation algorithm is fitted to obtain user
Iris outer circle in eyes image, the center of circle by iris outer circle determine that horizontal and vertical two straight lines, two straight lines prolong
It extends to and ends with human eye area profile point of intersection;By the intersection point of intersection point and right side on the left of horizontal linear and human eye area profile,
The intersection point of the intersection point and lower part on vertical straight line and human eye area profile top and the center of circle of iris outer circle, are referred to as left friendship
Point, right intersection point, upper intersection point, lower intersection point and the center of circle, left intersection point are referred to as distance 1 at a distance from the center of circle, and right intersection point is at a distance from the center of circle
Referred to as distance 2, upper intersection point are referred to as distance 3 at a distance from the center of circle, and lower intersection point is referred to as distance 4 at a distance from the center of circle, calculate distance 1 with
The proportionate relationship of distance 2, the proportionate relationship of distance 3 and distance 4 determine iris position.
Claims (6)
1. a kind of facial expression image eye mapping method based on infrared camera, the facial expression image is all-purpose card role's three-dimensional mould
Type is acted by user's current face and is generated in real time, which is characterized in that and the infrared camera can shoot user's eyes image,
Image segmentation algorithm divides to obtain human eye area, iris region and pupil region in user's eyes image, the eye of facial expression image
Portion region generates in real time according to user's eyes image data.
2. the facial expression image eye mapping method according to claim 1 based on infrared camera, which is characterized in that described
User's eyes image data include eyelid opening degree, iris position in human eye area, pupil position, iris shape, pupil in iris
Hole shape, iris diameter and pupil diameter.
3. the facial expression image eye mapping method according to claim 2 based on infrared camera, which is characterized in that described
Eyelid opening degree is determined by human eye area length-width ratio.
4. the facial expression image eye mapping method according to claim 2 based on infrared camera, which is characterized in that described
Iris method for determining position passes through comprising steps of image segmentation algorithm is fitted to obtain the iris outer circle in user's eyes image
The center of circle of iris outer circle determines horizontal and vertical two straight lines, and two linear extensions are cut to human eye area profile point of intersection
Only;By the intersection point of intersection point and right side on the left of horizontal linear and human eye area profile, vertical straight line and human eye area profile top
Intersection point and lower part intersection point and iris outer circle the center of circle, be referred to as left intersection point, right intersection point, upper intersection point, lower intersection point and circle
The heart, left intersection point are referred to as distance 1 at a distance from the center of circle, and right intersection point is referred to as distance 2 at a distance from the center of circle, and upper intersection point is at a distance from the center of circle
Referred to as distance 3, lower intersection point are referred to as distance 4 at a distance from the center of circle, calculate the proportionate relationship of distance 1 and distance 2, distance 3 and distance 4
Proportionate relationship, determine iris position.
5. the facial expression image eye mapping method according to claim 2 based on infrared camera, which is characterized in that described
Iris method for determining position is comprising steps of determine that center, the center refer to that human eye faces camera by human eye area profile
When, the center of circle of iris outer circle;Using center as origin, establish coordinate system, coordinate system and the left intersection point of human eye area profile, right intersection point,
Upper intersection point, lower intersecting point coordinate are respectively (X00,0), (X01,0), (0, Y00), (0, Y01), and image segmentation algorithm, which is fitted, to be used
Iris outer circle in the eyes image of family determines the central coordinate of circle (X0, Y0) of iris outer circle;By the ocular profile of facial expression image
Determine center, using center as origin, establish coordinate system, the left intersection point of the ocular profile of coordinate system and facial expression image, right intersection point,
Upper intersection point, lower intersecting point coordinate are respectively (X10,0), (X11,0), (0, Y10), (0, Y11);Table is determined according to (X0, the Y0)
Iris center (X1, Y1) in the ocular of feelings image.
6. the facial expression image eye mapping method according to claim 5 based on infrared camera, which is characterized in that described
Iris center (X1, the Y1) method of determination includes step in the ocular of facial expression image, if (X0, Y0) is located at first quartile, then
X1=X0*X01/X11,Y1=Y0*Y00/Y10;If (X0, Y0) is located at the second quadrant, then X1=X0*X00/X10, Y1=Y0*Y00/
Y10;If (X0, Y0) is located at third quadrant, then X1=X0*X00/X10, Y1=Y0*Y01/Y11;If (X0, Y0) is located at four-quadrant
It limits, then X1=X0*X01/X11, Y1=Y0*Y01/Y11.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711262477.7A CN109872378A (en) | 2017-12-04 | 2017-12-04 | Facial expression image eye mapping method based on infrared camera |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711262477.7A CN109872378A (en) | 2017-12-04 | 2017-12-04 | Facial expression image eye mapping method based on infrared camera |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109872378A true CN109872378A (en) | 2019-06-11 |
Family
ID=66915638
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711262477.7A Pending CN109872378A (en) | 2017-12-04 | 2017-12-04 | Facial expression image eye mapping method based on infrared camera |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109872378A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110150334A1 (en) * | 2008-07-23 | 2011-06-23 | Indian University & Technology Corporation | System and method for non-cooperative iris image acquisition |
CN103366157A (en) * | 2013-05-03 | 2013-10-23 | 马建 | Method for judging line-of-sight distance of human eye |
CN106056092A (en) * | 2016-06-08 | 2016-10-26 | 华南理工大学 | Gaze estimation method for head-mounted device based on iris and pupil |
-
2017
- 2017-12-04 CN CN201711262477.7A patent/CN109872378A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110150334A1 (en) * | 2008-07-23 | 2011-06-23 | Indian University & Technology Corporation | System and method for non-cooperative iris image acquisition |
CN103366157A (en) * | 2013-05-03 | 2013-10-23 | 马建 | Method for judging line-of-sight distance of human eye |
CN106056092A (en) * | 2016-06-08 | 2016-10-26 | 华南理工大学 | Gaze estimation method for head-mounted device based on iris and pupil |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10650539B2 (en) | Methods and systems to modify a two dimensional facial image to increase dimensional depth and generate a facial image that appears three dimensional | |
CN105654537B (en) | It is a kind of to realize and the expression cloning method and device of virtual role real-time interactive | |
AU2015348151B2 (en) | Real-time visual feedback for user positioning with respect to a camera and a display | |
US9269194B2 (en) | Method and arrangement for 3-dimensional image model adaptation | |
CN105354876B (en) | A kind of real-time volume fitting method based on mobile terminal | |
US9348950B2 (en) | Perceptually guided capture and stylization of 3D human figures | |
WO2021004257A1 (en) | Line-of-sight detection method and apparatus, video processing method and apparatus, and device and storage medium | |
CN110688948B (en) | Method and device for transforming gender of human face in video, electronic equipment and storage medium | |
US20230206531A1 (en) | Avatar display device, avatar generating device, and program | |
CN109272566A (en) | Movement expression edit methods, device, equipment, system and the medium of virtual role | |
JP7456670B2 (en) | 3D face model construction method, 3D face model construction device, computer equipment, and computer program | |
WO2021036314A1 (en) | Facial image processing method and apparatus, image device, and storage medium | |
JP2018538593A (en) | Head mounted display with facial expression detection function | |
US20200380780A1 (en) | Method to produce 3d model from one or several images | |
JPH0962865A (en) | Face picture processing method and face picture processor | |
CN114219878A (en) | Animation generation method and device for virtual character, storage medium and terminal | |
KR102264803B1 (en) | Method for generating character animation through extracting a character from an image and device using thereof | |
CN112232310B (en) | Face recognition system and method for expression capture | |
CA2796966A1 (en) | Method and system for facial expression transfer | |
WO2023066120A1 (en) | Image processing method and apparatus, electronic device, and storage medium | |
CN109522786B (en) | Dynamic human face registration method based on 3D camera | |
Danieau et al. | Automatic generation and stylization of 3d facial rigs | |
CN107103646B (en) | Expression synthesis method and device | |
JP6818219B1 (en) | 3D avatar generator, 3D avatar generation method and 3D avatar generation program | |
KR101701199B1 (en) | System and method for virtual cosmetic surgery by using mesh warping |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190611 |
|
WD01 | Invention patent application deemed withdrawn after publication |