CN107256388A - A kind of method and device for obtaining front face image - Google Patents
A kind of method and device for obtaining front face image Download PDFInfo
- Publication number
- CN107256388A CN107256388A CN201710377635.7A CN201710377635A CN107256388A CN 107256388 A CN107256388 A CN 107256388A CN 201710377635 A CN201710377635 A CN 201710377635A CN 107256388 A CN107256388 A CN 107256388A
- Authority
- CN
- China
- Prior art keywords
- facial
- image
- rotation
- around
- front face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Studio Devices (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of method and device for obtaining front face image.This method includes:Step 1, the facial parameter of the facial image of this shooting is obtained;Step 2, based on the facial parameter, the mass fraction of this facial image shot is calculated;Step 3, if shooting facial image to current time interval for the first time is less than default shooting time, mass fraction based on this facial image shot, update front face image, and obtain the facial parameter of the facial image shot next time, above-mentioned calculating and renewal process are repeated, until the time interval is equal to the default shooting time.The present invention realizes the front face image for simply and efficiently obtaining the person of being taken, without shooting repeatedly, and posture during to the person of being taken in face of camera or candid photograph camera lens is not also limited, and improves the experience sense for the person of being taken.
Description
Technical field
The present invention relates to technical field of image processing, more particularly, to a kind of method for obtaining front face image and
Device.
Background technology
With microelectronics, the development of computer and network technologies, face recognition technology has reached its maturity.Face recognition technology
Because overcoming traditional authentication identifying method, such as identification number, magnetic card, IC-card presence possibility it is stolen the problem of, and by
It is widely used.
Face alignment, mainly by gathering facial image and carrying out face alignment realization with image in image library.Existing skill
In art, the man face image acquiring mode based on USB camera is generally shone by one front face of USB camera shooting
Piece, is compared for the photo that is read with the image in database or from identity document.
In the above method, the acquisition of front face photo needs the person of being taken to keep just to camera and stop a moment.When
, it is necessary to which the person of being taken keeps just to shooting again when the front face photo of collection does not meet the requirement of face alignment picture quality
Head is simultaneously stopped a moment, until picture quality reaches requirement, and whether picture quality meets requirement, generally needs artificial subjectivity to enter again
Row judges.It can so cause the process for gathering front face photo cumbersome and time consuming.
The content of the invention
The present invention provides a kind of method and device for obtaining front face image, and positive dough figurine is gathered in the prior art to overcome
The problem of face photo is cumbersome and time consuming.
According to the first aspect of the invention there is provided a kind of method for obtaining front face image, this method includes:Step 1,
Obtain the facial parameter of the facial image of this shooting;Step 2, based on the facial parameter, the people that this shoots is calculated
The mass fraction of face image;Step 3, if shooting facial image to current time interval for the first time is less than default shooting time,
Based on the mass fraction of this facial image shot, front face image is updated, and obtain the face shot next time
The facial parameter of image, repeats above-mentioned calculating and renewal process, until the time interval is equal to the default shooting time.
The first possible implementation with reference to first aspect, in second of possible implementation, methods described also includes:
Image in the front face image and image library of renewal is compared.
The first possible implementation with reference to first aspect, it is described to be based on described in the third possible implementation
The mass fraction of the facial image of secondary shooting, updating front face image includes:When the matter of this facial image shot
The mass fraction that fraction is more than current front face image is measured, the current front face image is replaced with into this described shooting
Facial image;When the mass fraction of this facial image shot is less than or equal to the current front face image
Mass fraction, the current front face image is not replaced.
The first possible implementation with reference to first aspect, it is in step 1, described in the 4th kind of possible implementation
Facial parameter includes:Width, height, picture quality and the facial angle of face;The facial angle is included around the x-axis anglec of rotation
Degree, around the y-axis anglec of rotation and around the z-axis anglec of rotation.
With reference to the 4th kind of possible implementation of first aspect, in the 5th kind of possible implementation, based on this described bat
Fuzziness, acutance and the bright-dark degree for the facial image taken the photograph, obtain described image quality.
With reference to the 4th kind of possible implementation of first aspect, in the 6th kind of possible implementation, the step 2 includes:
Based on the width, height and standard faces area, the area ratio of this facial image shot is obtained;Based on described
Around the x-axis anglec of rotation, around the y-axis anglec of rotation and around the z-axis anglec of rotation, the face angle of this facial image shot is obtained
Angle value;Based on the area ratio, picture quality and facial angle value, the quality point of this facial image shot is obtained
Number.
It is described around the x-axis anglec of rotation in the 7th kind of possible implementation with reference to the 6th kind of possible implementation of first aspect
Degree, around the y-axis anglec of rotation and around the z-axis anglec of rotation, obtaining facial angle value includes:When described around the x-axis anglec of rotation, around y-axis
The anglec of rotation and around the z-axis anglec of rotation be respectively less than predetermined angle when, the facial angle value be the first preset value.
It is described around the x-axis anglec of rotation in the 8th kind of possible implementation with reference to the 7th kind of possible implementation of first aspect
Degree, around the y-axis anglec of rotation and around the z-axis anglec of rotation, obtaining facial angle value also includes:When described around the x-axis anglec of rotation, around y
The axle anglec of rotation and in the z-axis anglec of rotation unspecified angle be more than or equal to the predetermined angle when, the facial angle value is
Second preset value.
With reference to any possible implementation in the six to eight kind of first aspect, in the 9th kind of possible implementation, institute
State based on the area ratio, picture quality and facial angle value, obtain the mass fraction of this facial image shot
Including:The weighted value of the area ratio, picture quality and facial angle value is calculated, the facial image that this shoots is obtained
Mass fraction.
According to the second aspect of the invention there is provided a kind of device for obtaining front face image, including:Parameter acquiring mould
Block, mass fraction acquisition module and update module;The parameter acquisition module, the face of the facial image for obtaining this shooting
Portion's parameter;The mass fraction acquisition module, for based on the facial parameter, calculating this facial image shot
Mass fraction;The update module, if be less than default shoot for first time shooting facial image to current time interval
Between, based on the mass fraction of this facial image shot, front face image is updated, and obtain the people shot next time
The facial parameter of face image, repeats above-mentioned calculating and renewal process, until the time interval is equal to the default shooting time.
The method and device proposed by the present invention for obtaining front face image, by obtaining this facial image shot
Facial parameter, based on the facial parameter, calculates the mass fraction of this facial image shot, if shooting people for the first time
Face image to current time interval is less than default shooting time, based on the mass fraction of this facial image shot,
Front face image is updated, and obtains the facial parameter of the facial image shot next time, above-mentioned calculating and renewal process is repeated,
Until the time interval is equal to the default shooting time, the front face figure for simply and efficiently obtaining the person of being taken is realized
Picture, without shooting repeatedly, posture during to the person of being taken in face of camera or candid photograph camera lens is not also limited, and is improved and is taken
The experience sense of person.
Brief description of the drawings
Fig. 1 is a kind of method flow diagram of acquisition front face image according to the embodiment of the present invention;
Fig. 2 is a kind of method flow diagram of acquisition front face image according to the embodiment of the present invention;
Fig. 3 is the face direction of rotation schematic diagram according to the embodiment of the present invention;
Fig. 4 is the schematic device of the acquisition front face image according to the embodiment of the present invention.
Embodiment
With reference to the accompanying drawings and examples, the embodiment to the present invention is described in further detail.Implement below
Example is used to illustrate the present invention, but is not limited to the scope of the present invention.
In the prior art, the man face image acquiring mode based on USB camera, generally passes through USB camera shooting
One front face photo, for being compared with the image in database.
The acquisition of front face photo needs the person of being taken to keep just to camera and stop a moment in the above method.When adopting
, it is necessary to which the person of being taken keeps just to camera again when the front face photo of collection does not meet the requirement of face alignment picture quality
And stop a moment, until picture quality reaches requirement.It can so cause the process for gathering front face photo cumbersome and time consuming.
To solve the above problems, as shown in figure 1, the invention provides a kind of method for obtaining front face image, the party
Method includes:Step 1, the facial parameter of the facial image of this shooting is obtained;Step 2, based on the facial parameter, calculate described
The mass fraction of this facial image shot;Step 3, it is less than in advance if shooting facial image to current time interval for the first time
If shooting time, based on the mass fraction of this facial image shot, front face image is updated, and obtain next time
The facial parameter of the facial image of shooting, repeats above-mentioned calculating and renewal process, until the time interval is equal to described preset
Shooting time.
The method proposed by the present invention for obtaining front face image, is joined by the face for obtaining this facial image shot
Number, based on the facial parameter, calculates the mass fraction of this facial image shot, if shooting facial image for the first time
It is less than default shooting time to current time interval, based on the mass fraction of this facial image shot, updates just
Dough figurine face image, and the facial parameter of the facial image shot next time is obtained, above-mentioned calculating and renewal process are repeated, until institute
Time interval is stated equal to the default shooting time, the front face image for simply and efficiently obtaining the person of being taken, nothing is realized
It need to shoot repeatedly, posture during to the person of being taken in face of camera or candid photograph camera lens is not also limited, and improves the person's of being taken
Experience sense.
As a kind of alternative embodiment, methods described also includes:By the figure in the front face image and image library of renewal
As being compared.
As a kind of alternative embodiment, the mass fraction based on this facial image shot updates front
Facial image includes:When the mass fraction of this facial image shot is more than the quality point of current front face image
Number, the facial image that this shoots is replaced with by the current front face image;When the face figure that this shoots
The mass fraction of picture is less than or equal to the mass fraction of the current front face image, and the current front face figure is not replaced
Picture.
As a kind of alternative embodiment, in step 1, the facial parameter includes:The width of face, height, image matter
Amount and facial angle;The facial angle is included around the x-axis anglec of rotation, around the y-axis anglec of rotation and around the z-axis anglec of rotation.
As a kind of alternative embodiment, based on fuzziness, acutance and the bright-dark degree of this facial image shot,
Obtain described image quality.
As a kind of alternative embodiment, the step 2 includes:Based on the width, height and standard faces area, obtain
The area ratio of this facial image shot;Based on described around the x-axis anglec of rotation, around the y-axis anglec of rotation and around z-axis rotation
Gyration, obtains the facial angle value of this facial image shot;Based on the area ratio, picture quality and face
Angle value, obtains the mass fraction of this facial image shot.
It is described around the x-axis anglec of rotation as a kind of alternative embodiment, around the y-axis anglec of rotation and around the z-axis anglec of rotation, obtain
Facial angle value is taken to include:When described around the x-axis anglec of rotation, preset angle is respectively less than around the y-axis anglec of rotation and around the z-axis anglec of rotation
When spending, the facial angle value is the first preset value.
It is described around the x-axis anglec of rotation as a kind of alternative embodiment, around the y-axis anglec of rotation and around the z-axis anglec of rotation, obtain
Facial angle value is taken also to include:When described around the x-axis anglec of rotation, around the y-axis anglec of rotation and the unspecified angle in the z-axis anglec of rotation
During more than or equal to the predetermined angle, the facial angle value is the second preset value.
It is described to be based on the area ratio, picture quality and facial angle value as a kind of alternative embodiment, obtain described
The mass fraction of this facial image shot includes:Calculate the weighting of the area ratio, picture quality and facial angle value
Value, obtains the mass fraction of this facial image shot.
Above-mentioned all optional technical schemes, can form the alternative embodiment of the present invention, herein no longer using any combination
Repeat one by one.
The method provided based on above-mentioned Fig. 1 correspondence embodiments, front face figure is obtained the embodiments of the invention provide one kind
The method of picture.Referring to Fig. 2, this method includes:
101, obtain the facial parameter of the facial image of this shooting;
102, based on the facial parameter, calculate the mass fraction of this facial image shot;
103, if shooting facial image to current time interval for the first time is less than default shooting time, when this described bat
The mass fraction for the facial image taken the photograph is more than the mass fraction of current front face image, and the current front face image is replaced
It is changed to the facial image that this shoots;When the mass fraction of this facial image shot is less than or equal to described work as
The mass fraction of preceding front face image, the current front face image is not replaced;
104, the facial parameter of the facial image shot next time is obtained, 102 to 103 are repeated until reaching the default bat
Take the photograph the time;
105, the image in the front face image and image library of renewal is compared.
Wherein, 101, obtain the facial parameter of the facial image of this shooting.
Need by face carry out authentication when, identity person to be verified close to camera or other can be in the short time
The interior equipment for obtaining multiple facial images, video camera or equipment just start to shoot facial image and start timing.To clap for the first time
The facial image that the facial image taken the photograph is shot as this, when getting the facial image shot for the first time, by the face figure
As input facial parameter acquisition algorithm just obtains facial parameter.Do not limited herein for facial parameter acquisition algorithm the present embodiment
It is fixed.The equipment for meeting photographing request can be equipped with according to real needs for capture apparatus, the present embodiment is not also limited herein.
The facial parameter obtained in this step at least includes:Width, height, picture quality and the facial angle of face.
Wherein, the width of face and height are obtained especially by coordinate position of the face in the facial image of input;Picture quality by
The fuzziness of the facial image of input, acutance, bright-dark degree together decide on;Facial angle includes the angle that face rotates around 3 axles
Degree, i.e., around the x-axis anglec of rotation, around the y-axis anglec of rotation and around the z-axis anglec of rotation, the direction of rotation along each axle is as shown in Figure 3.With
It is that x-axis z-axis place plane is formed with face around the x-axis anglec of rotation when face rotates around x-axis exemplified by the x-axis anglec of rotation
Angle less than 90 degree.
102, based on the facial parameter, calculate the mass fraction of this facial image shot;
In order to improve the accuracy rate for obtaining front face image, facial image is quantified, i.e., based on the face
Parameter, calculates the mass fraction of this facial image shot.Specifically, the mass fraction of this facial image shot
For the weighted value of area ratio, picture quality and facial angle value.Wherein, in facial image of the area ratio for this shooting
The ratio of face area and default standard faces area, further, the face area in this facial image shot are behaved
The product of face width and height in face parameter;Facial angle value be based on it is described around the x-axis anglec of rotation, around the y-axis anglec of rotation and
Obtain, specifically include around the z-axis anglec of rotation:It is around the y-axis anglec of rotation and equal around the z-axis anglec of rotation when described around the x-axis anglec of rotation
During less than predetermined angle, the facial angle value is the first preset value;When described around the x-axis anglec of rotation, around the y-axis anglec of rotation and
When unspecified angle is more than or equal to the predetermined angle in the z-axis anglec of rotation, the facial angle value is the second preset value.Its
In, predetermined angle, the first preset value and the second preset value can be determined according to actual conditions, in this embodiment, it is preferred that, in advance
If angle is 15 degree, the first preset value is 1, and the second preset value is 0.
In addition, area ratio, picture quality and each self-corresponding weight coefficient of facial angle value can rule of thumb be set, root
According to current test result, preferable value is followed successively by 0.4,0.3,0.3.
103, if shooting facial image to current time interval for the first time is less than default shooting time, when this described bat
The mass fraction for the facial image taken the photograph is more than the mass fraction of current front face image, by the current front face image more
The new facial image for this shooting;When the mass fraction of this facial image shot is less than or equal to described work as
The mass fraction of preceding front face image, the current front face image is not updated.
After the mass fraction of this facial image shot is obtained, judge to shoot facial image for the first time to current
Time interval is less than default shooting time, if so, the current front face image is updated into the face that this shoots
Image;If it is not, not updating current front face image.Wherein, default shooting time can be set according to actual conditions, herein
It is not particularly limited.But in order to reduce residence time of the client before capture apparatus as far as possible, the default shooting time is typically set
For 1-2 seconds.The frequency per second for obtaining facial image is not also limited herein, for example, can be 20 per second.
104, the facial parameter of the facial image shot next time is obtained, 102 to 103 are repeated until reaching the default bat
Take the photograph the time.
After the renewal of step 103 is completed, the facial image of shooting is obtained again, the facial image is inputted into face
Parameter acquiring algorithm just obtains facial parameter, and then calculates the mass fraction of the facial image, and shoots face figure in first time
During as being less than default shooting time to current time interval, front face image is updated, or facial image is shot in first time
When being equal to default shooting time to current time interval, using current front face image as final front face image, use
In follow-up face alignment.
As shown in figure 4, the present invention provides a kind of device for obtaining front face image, including:Parameter acquisition module, quality
Fraction acquisition module and update module;The parameter acquisition module, the facial parameter of the facial image for obtaining this shooting;
The mass fraction acquisition module, for based on the facial parameter, calculating the quality point of this facial image shot
Number;The update module, if shooting facial image to current time interval for first time is less than default shooting time, is based on
The mass fraction of this facial image shot, updates front face image, and obtain the facial image shot next time
Facial parameter, above-mentioned calculating and renewal process are repeated, until the time interval is equal to the default shooting time.
The device proposed by the present invention for obtaining front face image, by parameter acquisition module, obtains the people of this shooting
The facial parameter of face image, by mass fraction acquisition module, based on the facial parameter, calculates the face that this shoots
The mass fraction of image, by update module, if shooting facial image to current time interval for the first time is less than default shooting
Time, based on the mass fraction of this facial image shot, front face image is updated, and obtain what is shot next time
The facial parameter of facial image, repeats above-mentioned calculating and renewal process, until when the time interval is equal to the default shooting
Between, the front face image for simply and efficiently obtaining the person of being taken is realized, without shooting repeatedly, to the person of being taken in face of shooting
Posture when head or candid photograph camera lens is not also limited, and improves the experience sense for the person of being taken.
As a kind of alternative embodiment, described device also includes comparing module, for by the front face image of renewal and
Image in image library is compared.
It is used as a kind of alternative embodiment, the update module, specifically for when the matter of this facial image shot
The mass fraction that fraction is more than current front face image is measured, the current front face image is replaced with into this described shooting
Facial image;When the mass fraction of this facial image shot is less than or equal to the current front face image
Mass fraction, the current front face image is not replaced.
As a kind of alternative embodiment, the facial parameter that the parameter acquisition module is obtained includes:Width, the height of face
Degree, picture quality and facial angle;The facial angle is included around the x-axis anglec of rotation, around the y-axis anglec of rotation and around z-axis rotation
Gyration.
As a kind of alternative embodiment, the parameter acquisition module is specifically based on the fuzziness of the facial image, acutance
And bright-dark degree, obtain described image quality.
It is used as a kind of alternative embodiment, the mass fraction acquisition module, specifically for based on the width, height and mark
Quasi- face area, obtains the area ratio of the facial image;The update module, is specifically additionally operable to based on described around x-axis rotation
Gyration, around the y-axis anglec of rotation and around the z-axis anglec of rotation, obtains facial angle value;The update module, is specifically additionally operable to base
In the area ratio, picture quality and facial angle value, the mass fraction of the facial image is obtained.
As a kind of alternative embodiment, the mass fraction acquisition module, further specifically for:When described around x-axis rotation
Gyration, around the y-axis anglec of rotation and around the z-axis anglec of rotation be respectively less than predetermined angle when, the facial angle value is set to first
Preset value.
As a kind of alternative embodiment, the mass fraction acquisition module is further specifically additionally operable to:When described around x-axis
The anglec of rotation, when unspecified angle is more than or equal to the predetermined angle around the y-axis anglec of rotation and in the z-axis anglec of rotation, by institute
State facial angle value and be set to the second preset value.
As a kind of alternative embodiment, the mass fraction acquisition module is further specifically additionally operable to:Calculate the area
The weighted value of ratio, picture quality and facial angle value, obtains the mass fraction of the facial image.
Finally, method of the invention is only preferably embodiment, is not intended to limit the scope of the present invention.It is all
Within the spirit and principles in the present invention, any modification, equivalent substitution and improvements made etc. should be included in the protection of the present invention
Within the scope of.
Claims (10)
1. a kind of method for obtaining front face image, it is characterised in that including:
Step 1, the facial parameter of the facial image of this shooting is obtained;
Step 2, based on the facial parameter, the mass fraction of this facial image shot is calculated;
Step 3, if shooting facial image to current time interval for the first time is less than default shooting time, based on this described bat
The facial parameter for the facial image that the mass fraction for the facial image taken the photograph, renewal front face image, and acquisition are shot next time,
Above-mentioned renewal process is repeated, until the time interval is equal to the default shooting time.
2. according to the method described in claim 1, it is characterised in that methods described also includes:By the front face image of renewal
It is compared with the image in image library.
3. according to the method described in claim 1, it is characterised in that the quality based on this facial image shot
Fraction, updating front face image includes:
When the mass fraction of this facial image shot is more than the mass fraction of current front face image, described it will work as
Preceding front face image replaces with the facial image that this shoots;
When the mass fraction of this facial image shot is less than or equal to the quality point of the current front face image
Number, the current front face image is not replaced.
4. according to the method described in claim 1, it is characterised in that in step 1, the facial parameter includes:The width of face
Degree, height, picture quality and facial angle;The facial angle is included around the x-axis anglec of rotation, around the y-axis anglec of rotation and around z
The axle anglec of rotation.
5. method according to claim 4, it is characterised in that the fuzziness based on this facial image shot,
Acutance and bright-dark degree, obtain described image quality.
6. method according to claim 4, it is characterised in that the step 2 includes:
Based on the width, height and standard faces area, the area ratio of this facial image shot is obtained;
Based on described around the x-axis anglec of rotation, around the y-axis anglec of rotation and around the z-axis anglec of rotation, the face that this shoots is obtained
The facial angle value of image;
Based on the area ratio, picture quality and facial angle value, the quality point of this facial image shot is obtained
Number.
7. method according to claim 6, it is characterised in that described around the x-axis anglec of rotation, around the y-axis anglec of rotation and around z
The axle anglec of rotation, obtaining facial angle value includes:
When described around the x-axis anglec of rotation, around the y-axis anglec of rotation and around the z-axis anglec of rotation be respectively less than predetermined angle when, the face
Angle value is the first preset value.
8. method according to claim 7, it is characterised in that described around the x-axis anglec of rotation, around the y-axis anglec of rotation and around z
The axle anglec of rotation, obtaining facial angle value also includes:
When described around the x-axis anglec of rotation, unspecified angle is more than or equal to described around the y-axis anglec of rotation and in the z-axis anglec of rotation
During predetermined angle, the facial angle value is the second preset value.
9. the method according to any one of claim 6-8, it is characterised in that described to be based on the area ratio, image
Quality and facial angle value, obtaining the mass fraction of this facial image shot includes:
The weighted value of the area ratio, picture quality and facial angle value is calculated, the facial image that this shoots is obtained
Mass fraction.
10. a kind of device for obtaining front face image, it is characterised in that including:Parameter acquisition module, mass fraction obtain mould
Block and update module;
The parameter acquisition module, the facial parameter of the facial image for obtaining this shooting;
The mass fraction acquisition module, for based on the facial parameter, calculating the matter of this facial image shot
Measure fraction;
The update module, if shooting facial image to current time interval for first time is less than default shooting time, base
In the mass fraction of this facial image shot, front face image is updated, and obtain the face figure shot next time
The facial parameter of picture, repeats above-mentioned calculating and renewal process, until the time interval is equal to the default shooting time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710377635.7A CN107256388B (en) | 2017-05-25 | 2017-05-25 | Method and device for acquiring front face image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710377635.7A CN107256388B (en) | 2017-05-25 | 2017-05-25 | Method and device for acquiring front face image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107256388A true CN107256388A (en) | 2017-10-17 |
CN107256388B CN107256388B (en) | 2020-10-27 |
Family
ID=60028008
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710377635.7A Active CN107256388B (en) | 2017-05-25 | 2017-05-25 | Method and device for acquiring front face image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107256388B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109035246A (en) * | 2018-08-22 | 2018-12-18 | 浙江大华技术股份有限公司 | A kind of image-selecting method and device of face |
CN109816628A (en) * | 2018-12-20 | 2019-05-28 | 深圳云天励飞技术有限公司 | Face evaluation method and Related product |
CN110196924A (en) * | 2019-05-31 | 2019-09-03 | 银河水滴科技(北京)有限公司 | The building in characteristic information library, the method for tracing of target object and device |
CN111178117A (en) * | 2018-11-09 | 2020-05-19 | 浙江宇视科技有限公司 | Data processing method and device |
CN111277746A (en) * | 2018-12-05 | 2020-06-12 | 杭州海康威视***技术有限公司 | Indoor face snapshot method and system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090080716A1 (en) * | 2007-09-25 | 2009-03-26 | Casio Computer Co., Ltd. | Image recognition device for performing image recognition including object identification on each of input images |
CN103595914A (en) * | 2013-11-04 | 2014-02-19 | 华为终端有限公司 | Photographing method and mobile terminal |
CN103605971A (en) * | 2013-12-04 | 2014-02-26 | 深圳市捷顺科技实业股份有限公司 | Method and device for capturing face images |
CN104182741A (en) * | 2014-09-15 | 2014-12-03 | 联想(北京)有限公司 | Image acquisition prompt method and device and electronic device |
CN105868613A (en) * | 2016-06-08 | 2016-08-17 | 广东欧珀移动通信有限公司 | Biometric feature recognition method, biometric feature recognition device and mobile terminal |
-
2017
- 2017-05-25 CN CN201710377635.7A patent/CN107256388B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090080716A1 (en) * | 2007-09-25 | 2009-03-26 | Casio Computer Co., Ltd. | Image recognition device for performing image recognition including object identification on each of input images |
CN103595914A (en) * | 2013-11-04 | 2014-02-19 | 华为终端有限公司 | Photographing method and mobile terminal |
CN103605971A (en) * | 2013-12-04 | 2014-02-26 | 深圳市捷顺科技实业股份有限公司 | Method and device for capturing face images |
CN104182741A (en) * | 2014-09-15 | 2014-12-03 | 联想(北京)有限公司 | Image acquisition prompt method and device and electronic device |
CN105868613A (en) * | 2016-06-08 | 2016-08-17 | 广东欧珀移动通信有限公司 | Biometric feature recognition method, biometric feature recognition device and mobile terminal |
Non-Patent Citations (1)
Title |
---|
高修峰等: ""人脸图像质量评估标准"", 《小型微型计算机***》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109035246A (en) * | 2018-08-22 | 2018-12-18 | 浙江大华技术股份有限公司 | A kind of image-selecting method and device of face |
WO2020038242A1 (en) * | 2018-08-22 | 2020-02-27 | Zhejiang Dahua Technology Co., Ltd. | Systems and methods for selecting a best facial image of a target human face |
CN109035246B (en) * | 2018-08-22 | 2020-08-04 | 浙江大华技术股份有限公司 | Face image selection method and device |
US11557147B2 (en) | 2018-08-22 | 2023-01-17 | Zhejiang Dahua Technology Co., Ltd. | Systems and methods for selecting a best facial image of a target human face |
CN111178117A (en) * | 2018-11-09 | 2020-05-19 | 浙江宇视科技有限公司 | Data processing method and device |
CN111178117B (en) * | 2018-11-09 | 2023-09-22 | 浙江宇视科技有限公司 | Data processing method and device |
CN111277746A (en) * | 2018-12-05 | 2020-06-12 | 杭州海康威视***技术有限公司 | Indoor face snapshot method and system |
CN111277746B (en) * | 2018-12-05 | 2021-07-23 | 杭州海康威视***技术有限公司 | Indoor face snapshot method and system |
CN109816628A (en) * | 2018-12-20 | 2019-05-28 | 深圳云天励飞技术有限公司 | Face evaluation method and Related product |
CN110196924A (en) * | 2019-05-31 | 2019-09-03 | 银河水滴科技(北京)有限公司 | The building in characteristic information library, the method for tracing of target object and device |
Also Published As
Publication number | Publication date |
---|---|
CN107256388B (en) | 2020-10-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107256388A (en) | A kind of method and device for obtaining front face image | |
TWI662433B (en) | Living body detection method and device, and identity authentication method and device | |
CN101482919B (en) | Face collation apparatus | |
CN105229671B (en) | Facial positions automatic tracing and facial automatic identifying method and system | |
CN109446981A (en) | A kind of face's In vivo detection, identity identifying method and device | |
CN103226694B (en) | A kind of portrait in real time obtains comparison and early warning cloth Ore-controlling Role and using method thereof | |
CN109271950A (en) | A kind of human face in-vivo detection method based on mobile phone forward sight camera | |
TW201203134A (en) | Facial expression capturing method and apparatus therewith | |
JP5170094B2 (en) | Spoofing detection system, spoofing detection method, and spoofing detection program | |
JP5592040B1 (en) | Fraud detection in biometric type access control systems | |
CN106462738B (en) | Method for constructing a model of a person's face, method and apparatus for analyzing a pose using such a model | |
CN109858375A (en) | Living body faces detection method, terminal and computer readable storage medium | |
JP2000251078A (en) | Method and device for estimating three-dimensional posture of person, and method and device for estimating position of elbow of person | |
CN107944395A (en) | A kind of method and system based on neutral net verification testimony of a witness unification | |
CN110751728B (en) | Virtual reality equipment with BIM building model mixed reality function and method | |
EP3726424A1 (en) | Determination of audience attention | |
CN114894337B (en) | Temperature measurement method and device for outdoor face recognition | |
CN108765014A (en) | A kind of intelligent advertisement put-on method based on access control system | |
CN111199029B (en) | Face recognition device and face recognition method | |
CN102486816A (en) | Device and method for calculating human body shape parameters | |
KR20180094554A (en) | Apparatus and method for reconstructing 3d image | |
CN110910449B (en) | Method and system for identifying three-dimensional position of object | |
CN106845365A (en) | For the method for detecting human face of student attendance | |
JP3970573B2 (en) | Facial image recognition apparatus and method | |
CN111275901A (en) | Control method and device of express delivery cabinet, storage medium and computer equipment |
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 |