CN107784300A - Anti- eye closing photographic method and its system - Google Patents
Anti- eye closing photographic method and its system Download PDFInfo
- Publication number
- CN107784300A CN107784300A CN201711241882.0A CN201711241882A CN107784300A CN 107784300 A CN107784300 A CN 107784300A CN 201711241882 A CN201711241882 A CN 201711241882A CN 107784300 A CN107784300 A CN 107784300A
- Authority
- CN
- China
- Prior art keywords
- picture
- eyes
- eye
- image
- captured
- 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.)
- Withdrawn
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
- G06V40/19—Sensors therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
Abstract
The present invention relates to the method and its system that a kind of anti-eye closing is taken pictures, including:Pupil center's point is positioned according to eyes image;A plurality of ray is formed as starting point using pupil center's point;Calculated by the ray and determine pupil boundary points;Eye state is determined using the pupil boundary points.Eyes detection method provided by the invention, eye state is judged by the feature of pupil boundary points, this method is lacked to face, deflection angle, background, illumination, the restriction of eyelid, eyelashes and the conditions such as minute surface is reflective, and accuracy rate is higher, it is cheap without equipment costly, cost.
Description
Technical field
The present invention relates to shooting and field of image recognition, more particularly to a kind of anti-eye closing photographic method and its system.
Background technology
As the improvement of people's living standards, travelling, social activity occupy increasingly consequence in life.With intelligence
The popularization of machine, take pictures from traditional photo studio and shoot anywhere or anytime till now, shooting turns into the most universal most common row of people
For.Computer, multimedia, the high speed development of data communication technology, image recognition technology, be using computer to image at
Reason, analysis and understanding, to identify the target of various different modes and the technology to picture, image recognition technology obtains more and more wider
General application.
When photo is shot, the puzzlement of eye closing is frequently encountered, the photo of an eye closing can destroy excellent wink
Between remember, brought to user too late to regret sorry.Therefore the eye of human eye in shooting, can be detected by image processing techniques
The prevention eye closing of eyeball state is taken pictures.Currently, the method for eyes detection has many kinds, integrates as two classes, one kind be based on
The eyes detection method of signature analysis, mainly there are sciagraphy, detection pupil, detection iris etc.;Another kind of is based on pattern
The eyes detection method of classification, mainly there is neutral net, supporting vector, hidden Markov model etc..
These are anti-to close one's eyes that the method taken pictures is to face, deflection angle, background, illumination, eyelid, eyelashes and minute surface is reflective etc. has
Certain conditionality, and it is computationally intensive, and processing is slow.
The content of the invention
Therefore, to solve technological deficiency and deficiency existing for prior art, the present invention proposes a kind of anti-eye closing photographic method
And its system.
Specifically, a kind of anti-eye closing photographic method that one embodiment of the invention proposes, including:
Step 1, the picture to be captured for obtaining photographic subjects;
Facial image in step 2, the identification picture to be captured;
Step 3, according to the facial image position eyes image;
Step 4, eye state judged by the eyes image;
Step 5, the method for determining to take pictures according to the eye state.
In one embodiment of the invention, after step 1, in addition to:
When not identifying facial image in the picture to be captured, directly shoot and preserve shooting picture.
In one embodiment of the invention, step 4, including:
Step 41, pupil center point positioned according to eyes image;
Step 42, a plurality of gray value ray is formed as starting point using pupil center's point in the eyes image;
Step 43, determination pupil boundary points are calculated by the gray value ray;
Step 44, using the pupil boundary points determine that eyes are in eyes-open state or closed-eye state.
In one embodiment of the invention, step 5 includes:
When eye state is eyes-open state, directly shoots and preserve shooting picture;
When eye state is closed-eye state, step 1 is re-executed after time rating.
In one embodiment of the invention, the time rating is the 0.12-0.4 seconds.
Another anti-eye closing camera system that one embodiment of the invention proposes, including the first picture recognition module, second
Picture recognition module, image detection module and image processing module;Wherein,
Described first image identification module, for obtaining the picture to be captured of photographic subjects and identifying the picture to be captured
In facial image;
Second picture recognition module, for positioning eyes image according to the facial image;
Described image detection module, for judging eye state by the eyes image;
Described image processing module, the method for determining to take pictures according to the eye state.
In one embodiment of the invention, in addition to order sending module, for not having when in the picture to be captured
When identifying facial image, transmission directly shoots and preserves the order of shooting picture.
In one embodiment of the invention, described image processing module is additionally operable to:
When eye state is eyes-open state, directly shoots and preserve shooting picture;
When eye state is closed-eye state, the picture to be captured is reacquired after time rating, detects institute again
State eye state.
In one embodiment of the invention, the order sending module is additionally operable to when eye state is eyes-open state,
Transmission directly shoots and preserves the order of shooting picture.
Based on this, the present invention possesses following advantage:
The advantages of method and its system that anti-eye closing provided by the invention is taken pictures, has:
1) present invention can avoid occurring the state of eyes closed in the photo of shooting, lift effect of taking pictures, and optimize user
Experience Degree;
2) present invention lacks to face, deflection angle, background, illumination, the restriction of eyelid, eyelashes and the conditions such as minute surface is reflective,
Accuracy rate is higher;
3) present invention is without a large amount of training samples, and algorithm is easy, and computational efficiency is high;
4) present invention is cheap without equipment costly, cost.
By the detailed description below with reference to accompanying drawing, other side of the invention and feature become obvious.But it should know
Road, the accompanying drawing is only the purpose design explained, not as the restriction of the scope of the present invention, because it should refer to
Appended claims.It should also be noted that unless otherwise noted, it is not necessary to which scale accompanying drawing, they only try hard to concept
Ground illustrates structure and flow described herein.
Brief description of the drawings
Below in conjunction with accompanying drawing, the embodiment of the present invention is described in detail.
Fig. 1 is a kind of schematic diagram of anti-eye closing photographic method provided in an embodiment of the present invention;
Fig. 2 is in for a kind of eyes provided in an embodiment of the present invention and opens state pupil boundary points schematic diagram;
Fig. 3 is that a kind of eyes provided in an embodiment of the present invention are in closure state pupil boundary points schematic diagram;
Fig. 4 is that a kind of eyes provided in an embodiment of the present invention are intended in state pupil spy boundary point is narrowed;
Fig. 5 is a kind of anti-eye closing camera system schematic diagram provided in an embodiment of the present invention.
Embodiment
In order to facilitate the understanding of the purposes, features and advantages of the present invention, below in conjunction with the accompanying drawings to the present invention
Embodiment be described in detail.
Embodiment one
Fig. 1 is referred to, Fig. 1 is a kind of schematic diagram of anti-method taken pictures of closing one's eyes provided in an embodiment of the present invention.This method
Comprise the following steps:
Step 1, the picture to be captured for obtaining photographic subjects;
Facial image in step 2, the identification picture to be captured;
Step 3, according to the facial image position eyes image;
Step 4, eye state judged by the eyes image;
Step 5, the method for determining to take pictures according to the eye state.
Wherein, after step 1, can also include:
When not identifying facial image in the picture to be captured, directly shoot and preserve shooting picture.
Wherein, for step 4, can include:
Step 41, pupil center point positioned according to eyes image;
Step 42, a plurality of gray value ray is formed as starting point using pupil center's point in the eyes image;
Step 43, determination pupil boundary points are calculated by the gray value ray;
Step 44, using the pupil boundary points determine that eyes are in eyes-open state or closed-eye state.
Wherein, for step 5, can include:
When eye state is eyes-open state, directly shoots and preserve shooting picture;
When eye state is closed-eye state, step 1 is re-executed after time rating.
Wherein, it is the 0.12-0.4 seconds for time rating described in step 5.
Embodiment two
On the basis of above-described embodiment, the present embodiment is to the anti-method further explanation closed one's eyes and taken pictures.This method includes
Following steps:
When the camera applications in intelligent terminal receive shooting instruction, the picture to be captured of photographic subjects is obtained, wouldn't
Shot, identify in picture to be captured whether there is face by face recognition technology;If without face, directly clapped
Take the photograph, the picture photographing to be captured of photographic subjects is got off, and is stored in the photograph album in intelligent terminal.If have in picture to be captured
Face, eyes image is positioned according to facial image, eye state is judged by eyes image.Specifically, sentenced by following methods
Disconnected eye state:
Step 1, obtain eyes image
After obtaining eyes image, eyes image is handled, eyes are adjusted to horizontal level.
Eyes image is converted into eye gray-scale map, grey-scale contrast enhancing pretreatment, processing are carried out to eye gray-scale map
Method is:
F=c*log (1+double (f0))
Wherein, f0Original image is represented, f represents the enhanced image of contrast.
The enhanced image of contrast is done into Laplce's filtering process.
The differentiation that grey-scale contrast enhancing pretreatment is more beneficial for pupil and perimeter is carried out to eye gray-scale map;In addition
The non-directional denoising that all directions can be done to eyes image of Laplce's filtering.
Step 2, positioning pupil center point
Eye gray-scale map after being handled in step 1 is estimated into eye central area, searches eye central area gray value
Minimum point, if the point is located approximately at the midpoint of eye central area, is positioned as pupil center's point;Otherwise, continue to search for, directly
To finding the gray value smallest point that is located approximately near the midpoint of eye central area.
Step 3, using pupil center's point as starting point burnt hair angle value ray
It is starting point along upper eyelid direction emitting linear using pupil center's point, M bar gray value rays can be formed;Equally, with
Pupil center's point be starting point along lower eyelid direction emitting linear, N bar gray value rays can be formed.M and N can with it is equal can also
, M and N bar number are more, and testing result is more accurate.
Step 4, determine pupil boundary points
Pupil region gray scale is significantly lower than other regions, and violent in boundary position graded, the partial differential of gray value is:
Wherein, the gray value that f (i, j) is image f coordinates (i, j) place is made;
Then the shade of gray of the direction is:
The maximum points of D are extracted, are denoted as Dmax;Work as Dmax>Boundary point threshold value, then the point is pupil boundary points.Wherein, border
Point threshold value is chosen more than the shade of gray at pupil and skin interface and less than the spy of pupil and the shade of gray of white of the eye intersection
Definite value, according to individual difference self-defining.Pupil boundary points are at pupil portion and white of the eye part alternating.
Step 5, using pupil boundary points determine eye state
51), determine that method determines the pupil boundary points of directions of rays in step 3 by step 4 pupil boundary points, it is assumed that really
Surely X pupil boundary points are shared;
52) eyes closed degree, is calculated by eyes closed degree formula, is specially:
53) closure threshold value is chosen, selects the first closure threshold value and the second closure threshold value respectively,
When θ is more than the first closure threshold value, eye state is closure;
When θ is less than the second closure threshold value, eye state is to open;
Otherwise, eye state is to narrow;
Wherein, the first closure threshold value is bigger, and eyes more close, and the first closure threshold theory maximum is 1;
Second closure threshold value is smaller, and eyes are more opened, and the second closure threshold theory minimum value is 0;
Different closure threshold values can be selected according to individual difference and application demand.
The eye pupil of people is smaller, and gray scale is low, because of individual physiological factor pupil image will not be caused to be blocked by eyelid, when
Normal when opening state, pupil is complete, when being that through hole disappears in closure, when in open and close intermediate state when, pupil
Hole lower edges are blocked, therefore are closed using detecting pupil boundary and judging that eyes are opened.
Fig. 2 is referred to, Fig. 2 is in for eyes provided in an embodiment of the present invention and opens state pupil boundary points schematic diagram.Such as
Shown in figure, it is 0.8 to choose the first closure threshold value, and the second closure threshold value is 0.2, is starting point respectively along upper using pupil center's point
M (M takes 50) bar gray value ray is launched in eyelid direction, launches N (N takes 50) bar gray value ray along lower eyelid direction;In ray
Direction can determine X (90) individual pupil boundary points altogether, bring eyes closed degree formula into, try to achieve θ and be less than the second closure for 0.1, θ
It is 0.2 to spend threshold value, therefore eyes are in and open state.
Continuing with referring to Fig. 3, Fig. 3 is that eyes provided in an embodiment of the present invention are in the signal of closure state pupil boundary points
Figure.As illustrated, it is 0.8 to choose the first closure threshold value, the second closure threshold value is 0.2, using pupil center's point as starting point minute
Do not launch M (M takes 50) bar gray value ray along upper eyelid direction, launch N (N takes 50) bar gray value ray along lower eyelid direction;
X (10) individual pupil boundary points can be determined altogether in directions of rays, bring eyes closed degree formula into, θ is tried to achieve and is more than for 0.9, θ
One closure threshold value is 0.2, therefore eyes are in closure state.
Fig. 4 is referred to, Fig. 4 is that eyes provided in an embodiment of the present invention are anticipated in state pupil spy boundary point is narrowed
Figure.As illustrated, it is 0.8 to choose the first closure threshold value, the second closure threshold value is 0.2, using pupil center's point as starting point minute
Do not launch M (M takes 50) bar gray value ray along upper eyelid direction, launch N (N takes 50) bar gray value ray along lower eyelid direction;
X (60) individual pupil boundary points can be determined altogether in directions of rays, bring eyes closed degree formula into, θ is tried to achieve and is more than for 0.4, θ
Two closure threshold values are 0.2, are 0.8 less than the first closure threshold value, therefore eyes are in and narrow state.
Eyes detection method proposed by the present invention based on pupil feature, learn mould without substantial amounts of high-definition image
Plate, computational complexity can be preferably reduced, improve real-time, reliability is high, is with a wide range of applications, of the invention in addition
It is cheap without equipment costly, cost.
When the eye state in picture to be captured is eyes-open state, then the picture photographing to be captured is got off and is stored in
In photograph album in intelligent terminal.When the eye state in picture to be captured is closed-eye state, then ignore the picture to be captured,
The picture to be captured of photographic subjects is reacquired after time rating, and detection judges eye state in picture to be captured again,
It is recycled for judging eye state by eyes image afterwards, until detecting face eyes as when opening, shooting is to be captured
Picture simultaneously preserves.Avoid the human eye in photo from closed-eye state occur, effect of taking pictures is lifted, so as to lift Consumer's Experience.
Wherein, time rating is the default interval time for obtaining picture to be captured.Because human eye wink time is 0.12-
0.4 second, it is preferable that can select 0.2 second, 0.3 second, therefore, time rating is set to the arbitrary value in the 0.12-0.4 seconds, preferably
It ground, can select 0.2 second, 0.3 second, can be easy to avoid the blink state of human eye, shooting effect be lifted, so as to improve user's body
Test.
When reaching time rating, shoot picture to be captured and preserve.If the people in picture to be captured within time rating
When the eyes of thing are closed-eye state always, then it can not be shot always, Consumer's Experience is also bad.Therefore, when specified at this
Between within, when there is no shooting operation still, when reaching time rating, shoot picture to be captured and preserve.Now, user shoots
Photo in still may to have eye state be closed-eye state, but can at least shoot corresponding photo, avoid user
Photo can not be shot always.
Embodiment three
On the basis of above-described embodiment, the present embodiment illustrates the anti-method closed one's eyes and taken pictures by specific embodiment.
When user uses the camera function shooting image of intelligent machine, click on shooting push button and send shooting operation order;Intelligence
The background program of the camera applications of energy machine receives the shooting order, obtains picture to be captured, and identify wherein whether there is people
Face image;If without facial image, directly shot, picture photographing to be captured is got off, and be stored in the photograph album of mobile phone
In.If having facial image in picture to be captured, eyes image is positioned according to facial image, judges eye state.Eye state is sentenced
Method described in disconnected method reference implementation example two, here is omitted.When the eye state in picture to be captured is eye opening shape
During state, then the picture photographing to be captured is got off and is stored in the photograph album of mobile phone.When the eye state in picture to be captured is
During closed-eye state, then ignore the picture to be captured, picture to be captured is reacquired after the time rating of 0.3 second, due to this
Time rating is very short, and the scene before user plane varies less, i.e., after time rating, still has face to go out in picture to be captured
It is existing, therefore can no longer be identified in picture to be captured whether have the step of face, and directly again detection judge it is to be captured
Whether eye state is eyes-open state in picture, can reduce the hind computation amount of mobile phone camera application program, reduces power consumption, carries
Rise speed of taking pictures;If eye state is eyes-open state, shoots photo and preserve to mobile phone photo album;If being still closed-eye state,
Then continue to reacquire picture to be captured after 0.3 second, and again detection judge in picture to be captured eye state whether be
Eyes-open state.Circulate successively, until detecting eye state when opening, to shoot picture to be captured and preserving.Avoid in photo
Human eye there is closed-eye state, lifting is taken pictures effect, so as to lift Consumer's Experience.
Example IV
Fig. 5 is referred to, Fig. 5 is a kind of anti-system schematic taken pictures of closing one's eyes provided in an embodiment of the present invention.The system bag
Include the first picture recognition module 41, the second picture recognition module 42, image detection module 43 and image processing module 44;Wherein,
Described first image identification module 41, for obtaining the picture to be captured of photographic subjects and identifying the picture to be captured
Facial image in face;
Second picture recognition module 42, for positioning eyes image according to the facial image;
Described image detection module 43, for judging eye state by the eyes image;
Described image processing module 44, the method for determining to take pictures according to the eye state.
Further, the system also includes order sending module 45, for not identified when in the picture to be captured
During facial image, transmission directly shoots and preserves the order of shooting picture.
Further, described image processing module 44 is additionally operable to:
When eye state is eyes-open state, directly shoots and preserve shooting picture;
When eye state is closed-eye state, the picture to be captured is reacquired after time rating, detects institute again
State eye state.
Further, the order sending module 45 is additionally operable to when eye state is eyes-open state, is sent and is directly shot
And preserve the order of shooting picture.
In the present embodiment, when the picture to be captured for obtaining photographic subjects, wouldn't be shot, the first picture recognition module
41 identify in picture to be captured whether there is face by face recognition technology;If without face, order sending module 45 is direct
Shooting order is sent, is directly shot, mesh picture photographing to be captured is got off, and preserves.If having face in picture to be captured,
Eyes image is then positioned by the second picture recognition module 42, eye is judged by eyes image using the first image detection module 43
Eyeball state.Specifically, method of the eye state determination methods as described in embodiment two judges, repeats no more here.Work as image
When eye state in the picture to be captured that processing module 44 receives is eyes-open state, order sending module 45 directly transmits bat
Order is taken the photograph, the picture photographing to be captured is got off and preserved.When the eye state in picture to be captured is closed-eye state, image
Processing module 44 then ignores the picture to be captured, picture to be captured is reacquired after time rating, and detection judges again
Whether eye state is eyes-open state in picture to be captured, is recycled for procedure below afterwards:After a set time again
Picture to be captured is obtained, and detection judges whether eye state is eyes-open state in picture to be captured again, until detecting eye
Eyeball state is when opening, then order sending module 45 directly transmits shooting order, shoots picture to be captured and preserves.Avoid photo
In human eye there is closed-eye state, lifting is taken pictures effect, so as to lift Consumer's Experience.
Wherein, time rating is the interval time for obtaining picture to be captured.Because human eye wink time is the 0.12-0.4 seconds,
Preferably, can select 0.2 second, 0.3 second, therefore, time rating can be set to the arbitrary value in the 0.12-0.4 seconds, it is preferable that
It can select 0.2 second, 0.3 second, can be easy to avoid the blink state of human eye, shooting effect be lifted, so as to lift Consumer's Experience.
In summary, specific case used herein a kind of is entered to of the invention based on anti-eye closing photographic method and its system
Elaboration is gone, the explanation of above example is only intended to help the method and its core concept for understanding the present invention;Meanwhile for this
The those skilled in the art in field, according to the thought of the present invention, there will be changes in specific embodiments and applications,
In summary, this specification content should not be construed as limiting the invention, and protection scope of the present invention should be with appended right
It is required that it is defined.
Claims (9)
- A kind of 1. anti-eye closing photographic method, it is characterised in that including:Step 1, the picture to be captured for obtaining photographic subjects;Facial image in step 2, the identification picture to be captured;Step 3, according to the facial image position eyes image;Step 4, eye state judged by the eyes image;Step 5, the method for determining to take pictures according to the eye state.
- 2. according to the method for claim 1, it is characterised in that after step 1, in addition to:When not identifying facial image in the picture to be captured, directly shoot and preserve shooting picture.
- 3. according to the method for claim 1, it is characterised in that step 4 includes:Step 41, pupil center point positioned according to eyes image;Step 42, a plurality of gray value ray is formed as starting point using pupil center's point in the eyes image;Step 43, determination pupil boundary points are calculated by the gray value ray;Step 44, using the pupil boundary points determine that eyes are in eyes-open state or closed-eye state.
- 4. according to the method for claim 1, it is characterised in that step 5 includes:When eye state is eyes-open state, directly shoots and preserve shooting picture;When eye state is closed-eye state, step 1 is re-executed after time rating.
- 5. according to the method for claim 4, it is characterised in that the time rating is the 0.12-0.4 seconds.
- 6. a kind of anti-eye closing camera system, it is characterised in that including the first picture recognition module, the second picture recognition module, figure As detection module and image processing module;Wherein,Described first image identification module, for obtaining the picture to be captured of photographic subjects and identifying in the picture to be captured Facial image;Second picture recognition module, for positioning eyes image according to the facial image;Described image detection module, for judging eye state by the eyes image;Described image processing module, the method for determining to take pictures according to the eye state.
- 7. system according to claim 6, it is characterised in that also including order sending module, for when described to be captured When facial image is not identified in picture, transmission directly shoots and preserves the order of shooting picture.
- 8. system according to claim 6, it is characterised in that described image processing module is additionally operable to:When eye state is eyes-open state, directly shoots and preserve shooting picture;When eye state is closed-eye state, the picture to be captured is reacquired after time rating, detects the eye again Eyeball state.
- 9. system according to claim 8, it is characterised in that the order sending module is additionally operable to when eye state is to open During eye state, transmission directly shoots and preserves the order of shooting picture.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711241882.0A CN107784300A (en) | 2017-11-30 | 2017-11-30 | Anti- eye closing photographic method and its system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711241882.0A CN107784300A (en) | 2017-11-30 | 2017-11-30 | Anti- eye closing photographic method and its system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107784300A true CN107784300A (en) | 2018-03-09 |
Family
ID=61431529
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711241882.0A Withdrawn CN107784300A (en) | 2017-11-30 | 2017-11-30 | Anti- eye closing photographic method and its system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107784300A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109151304A (en) * | 2018-08-22 | 2019-01-04 | Oppo广东移动通信有限公司 | Image processing method, device, electronic equipment and computer-readable storage medium |
CN110084191A (en) * | 2019-04-26 | 2019-08-02 | 广东工业大学 | A kind of eye occlusion detection method and system |
CN110472546A (en) * | 2019-08-07 | 2019-11-19 | 南京大学 | A kind of contactless eye movement characteristics extraction element of infant and method |
CN112581474A (en) * | 2021-02-22 | 2021-03-30 | 常州微亿智造科技有限公司 | Industrial component visual edge detection method based on sinusoidal scanning |
-
2017
- 2017-11-30 CN CN201711241882.0A patent/CN107784300A/en not_active Withdrawn
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109151304A (en) * | 2018-08-22 | 2019-01-04 | Oppo广东移动通信有限公司 | Image processing method, device, electronic equipment and computer-readable storage medium |
CN109151304B (en) * | 2018-08-22 | 2021-09-14 | Oppo广东移动通信有限公司 | Image processing method and device, electronic equipment and computer readable storage medium |
CN110084191A (en) * | 2019-04-26 | 2019-08-02 | 广东工业大学 | A kind of eye occlusion detection method and system |
CN110084191B (en) * | 2019-04-26 | 2024-02-23 | 广东工业大学 | Eye shielding detection method and system |
CN110472546A (en) * | 2019-08-07 | 2019-11-19 | 南京大学 | A kind of contactless eye movement characteristics extraction element of infant and method |
CN110472546B (en) * | 2019-08-07 | 2024-01-12 | 南京大学 | Infant non-contact eye movement feature extraction device and method |
CN112581474A (en) * | 2021-02-22 | 2021-03-30 | 常州微亿智造科技有限公司 | Industrial component visual edge detection method based on sinusoidal scanning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107748869B (en) | 3D face identity authentication method and device | |
CN107609383B (en) | 3D face identity authentication method and device | |
CN108829900B (en) | Face image retrieval method and device based on deep learning and terminal | |
CN107633165B (en) | 3D face identity authentication method and device | |
WO2018188453A1 (en) | Method for determining human face area, storage medium, and computer device | |
CN107784300A (en) | Anti- eye closing photographic method and its system | |
CN105844128B (en) | Identity recognition method and device | |
US8515124B2 (en) | Method and apparatus for determining fake image | |
US6611613B1 (en) | Apparatus and method for detecting speaking person's eyes and face | |
CN104794465B (en) | A kind of biopsy method based on posture information | |
CN105868689A (en) | Cascaded convolutional neural network based human face occlusion detection method | |
WO2019137178A1 (en) | Face liveness detection | |
KR101172898B1 (en) | Method for detecting liveness for face recognition system | |
CN103218615B (en) | Face judgment method | |
CN102324025A (en) | Human face detection and tracking method based on Gaussian skin color model and feature analysis | |
CN106339676A (en) | Face authentication and face recognition method | |
WO2022062379A1 (en) | Image detection method and related apparatus, device, storage medium, and computer program | |
CN101661554A (en) | Front face human body automatic identity recognition method under long-distance video | |
CN109711309A (en) | A kind of method whether automatic identification portrait picture closes one's eyes | |
CN111914761A (en) | Thermal infrared face recognition method and system | |
CN110705454A (en) | Face recognition method with living body detection function | |
CN108985200A (en) | A kind of In vivo detection algorithm of the non-formula based on terminal device | |
CN112232204A (en) | Living body detection method based on infrared image | |
CN111860394A (en) | Gesture estimation and gesture detection-based action living body recognition method | |
CN111259757B (en) | Living body identification method, device and equipment based on image |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180309 |