CN106131409B - Image processing method and device - Google Patents
Image processing method and device Download PDFInfo
- Publication number
- CN106131409B CN106131409B CN201610547712.4A CN201610547712A CN106131409B CN 106131409 B CN106131409 B CN 106131409B CN 201610547712 A CN201610547712 A CN 201610547712A CN 106131409 B CN106131409 B CN 106131409B
- Authority
- CN
- China
- Prior art keywords
- outer profile
- point
- image
- ratio
- 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.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims description 18
- 210000005069 ears Anatomy 0.000 claims description 11
- 230000001815 facial effect Effects 0.000 claims description 8
- 240000006409 Acacia auriculiformis Species 0.000 claims description 7
- 238000003384 imaging method Methods 0.000 abstract description 30
- 230000000694 effects Effects 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 5
- 241000288673 Chiroptera Species 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- VIKNJXKGJWUCNN-XGXHKTLJSA-N norethisterone Chemical compound O=C1CC[C@@H]2[C@H]3CC[C@](C)([C@](CC4)(O)C#C)[C@@H]4[C@@H]3CCC2=C1 VIKNJXKGJWUCNN-XGXHKTLJSA-N 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of image processing methods, comprising: obtains the face outer profile and image center in close shot image；Keep the face outer profile in close shot image constant, pixel in outer profile is gathered to the pixel of image center, the portrait being amplified in outer profile is effectively reduced, the distortion and distortion of imaging descendant's picture caused by face and taking lens are closer when so as to reduce due to actual photographed, the ratio of portrait after making imaging more connects the ratio of practical face, improves the appreciation effect of close-range imaging descendant picture.
Description
Technical field
The present invention relates to technical field of image processing, more particularly, to a kind of image processing method and device.
Background technique
With digital camera, smart phone, camera etc. can camera terminal it is universal, multi-user increasingly like using
Terminal carries out self-timer.
However, existing terminal is when carrying out close shot shooting especially portrait self-timer, due between face and camera lens away from
It is close from relatively, therefore the actual range on face between each position and camera lens will affect position of each position in image
It sets.
Specifically, as shown in Figure 1, wherein S is taking lens, using the inside of the S triangle surrounded as vertex by dotted line
For the coverage of camera lens S.Practical face is located at the position of center side to the left of coverage.With the A ' point of actual persons on the face
For, it is to be understood that the position of the B ' point in Fig. 1 immediately below A ' point should be just the A ' for meeting the normal appreciation habit of people
The position of point.However in practical situations, after camera lens S shooting, since the image after imaging is plane, A ' point
Position in close-range imaging be located at the position C ' of face (be not shown in Fig. 1 imaging side the case where, due to imaging side with
Actual photographed side is proportional, thus by the schematic diagram of actual photographed side can learn actual persons on the face each
Position after the imaging of point in portrait).The each position and true face situation in the portrait after being imaged are allowed in this way
Compared to more to the outer profile of face it is close, cause the portrait in face outer profile to be amplified, generate distortion distortion, to influence to see
The effect of reward.
Summary of the invention
The distance between face and taking lens are relatively close when it is an object of the invention to solve due to close shot shooting, cause into
Face as after leads to the problem of distortion.
To solve the above problems, the present invention provides a kind of image processing method and devices.
In a first aspect, the present invention provides a kind of image processing methods, comprising:
Obtain the face outer profile and image center in close shot image；
It keeps the face outer profile in close shot image constant, the pixel in outer profile is gathered to the pixel of image center
Hold together；
The shape of the face outer profile is the shape of preset facial contour model；And where the crown in close shot image
Point, the left vertex of left ear, the right vertex of auris dextra be located on the face outer profile.
Optionally, the face outer profile is the round or ellipse with default length-width ratio.
Optionally, described to keep the face outer profile in close shot image constant, by the pixel in outer profile to picture centre
The pixel of point is gathered, comprising:
Obtain the first ratio of the point to be adjusted in close shot image in face outer profile；Wherein, first ratio be to
First distance and the second distance the ratio between of first outer profile point to image center of the adjustment point to image center；Described first
Outer profile point is the line of point to be adjusted and image center and the intersection point of face outer profile；
Keep the face outer profile in the close shot image constant, by the pixel in outer profile to the picture of image center
Element is gathered, so that first ratio is adjusted to original N times；Wherein, when N is actual photographed, point to be adjusted is in practical face
On corresponding points between camera lens the first object distance and the first outer profile point in actual persons corresponding points on the face between camera lens
The ratio between second object distance.
Optionally, the method also includes: obtain first object distance and second object distance, specifically include:
Focus of the camera lens in actual persons on the face when determining shooting；
According to preset model and camera lens to the object distance of the focus, the first object distance and the second object distance are determined；Wherein institute
Stating preset model is sphere model or head dummy model.
Optionally, described to keep the face outer profile in close shot image constant, by the pixel in outer profile to picture centre
The pixel of point is gathered, comprising:
Obtain the first ratio of the point to be adjusted in close shot image in face outer profile；Wherein, first ratio be to
First distance and the second distance the ratio between of first outer profile point to image center of the adjustment point to image center；Described first
Outer profile point is the line of point to be adjusted and image center and the intersection point of face outer profile；
Keep the face outer profile in the close shot image constant, by the pixel in outer profile to the picture of image center
Element is gathered, so that first ratio is adjusted to the second ratio；Wherein, second ratio is the point to be adjusted in prospect map
The third distance of corresponding points of the corresponding points to described image central point in distant view image as in and the first outer profile point
4th ratio of distances constant of corresponding points of the corresponding points to described image central point in distant view image in distant view image.
Optionally, described to keep the face outer profile in close shot image constant, by the pixel in outer profile to picture centre
The pixel of point is gathered, comprising:
When receiving the beginning adjustment instruction of user's input, the position of the outer profile pixel of the face in close shot image is kept
Set it is constant, keep close shot image in face outer profile it is constant, the pixel in outer profile is gathered to the pixel of image center；
Stop gathering when receiving the end adjustment instruction of user's input.
Second aspect, the present invention also provides a kind of image processing apparatus, comprising:
Portrait determination unit, for obtaining face outer profile and image center in close shot image；
Image processing unit, for keeping the face outer profile in close shot image constant, by the pixel in outer profile to figure
The pixel of inconocenter point is gathered.
The shape of the face outer profile is the shape of preset facial contour model；And where the crown in close shot image
Point, the left vertex of left ear, the right vertex of auris dextra be located on the face outer profile.
Optionally, the face outer profile is the round or ellipse with default length-width ratio.
Optionally, described device further include: distance acquiring unit,
The distance acquiring unit, for obtaining the first ratio of the point to be adjusted in close shot image in face outer profile；
Wherein, first ratio is first distance and first outer profile point to image center of the point to be adjusted to image center
The ratio between second distance；The first outer profile point is the line of point to be adjusted and image center and the intersection point of face outer profile；
Described image processing unit is further used for keeping the face outer profile in the close shot image constant, by foreign steamer
Pixel in exterior feature is gathered to the pixel of image center, so that first ratio is adjusted to original N times；Wherein, N is real
When border is shot, point to be adjusted actual persons corresponding points on the face between camera lens the first object distance and the first outer profile point in reality
Corresponding points on face are to the ratio between the second object distance between camera lens.
Optionally, the distance acquiring unit is also used to obtain first object distance and second object distance, specifically includes:
Focus of the camera lens in actual persons on the face when for determining shooting；
For, to the object distance of the focus, determining the first object distance and the second object distance according to preset model and camera lens；Its
Described in preset model be sphere model or head dummy model.
Optionally,
The distance acquiring unit, for obtaining the first ratio of the point to be adjusted in close shot image in face outer profile；
Wherein, first ratio is first distance and first outer profile point to image center of the point to be adjusted to image center
The ratio between second distance；The first outer profile point is the line of point to be adjusted and image center and the intersection point of face outer profile；
Described image processing unit is further used for keeping the face outer profile in the close shot image constant, by foreign steamer
Pixel in exterior feature is gathered to the pixel of image center, so that first ratio is adjusted to the second ratio；Wherein, described
Two ratios are corresponding points corresponding points to described image central point in distant view image of the point to be adjusted in distant view image
Corresponding points in distant view image of third distance and the first outer profile point to described image central point in distant view image
Corresponding points the 4th ratio of distances constant.
Optionally, described image processing unit is also used to keep close when receiving the beginning adjustment instruction of user's input
The position of the outer profile pixel of face in scape image is constant, keeps the face outer profile in close shot image constant, by outer profile
Interior pixel is gathered to the pixel of image center；Stop gathering when receiving the end adjustment instruction of user's input.
In image processing method provided by the invention, by keeping the face outer profile of image constant, and will be in outer profile
Pixel gather to the pixel of image center so that close to the excessive people of ratio of image center in original close shot image
Face image can effectively be reduced, each position of face and the object of taking lens when so as to effectively reduce due to actual photographed
Lead to distortion and distortion that descendant's picture is imaged away from difference, the human face ratio after making imaging more connects the ratio of practical face, improves
The appreciation effect of close-range imaging descendant's picture.
Detailed description of the invention
Can be more clearly understood characteristic information and advantage of the invention by reference to attached drawing, attached drawing be schematically without
It is interpreted as carrying out any restrictions to the present invention, in the accompanying drawings:
Fig. 1 is prior art two-shot image imaging schematic diagram；
Fig. 2 is image processing method embodiment flow chart provided by the invention；
Fig. 3 is that image processing method facial image provided by the invention gathers schematic diagram；
Fig. 4 is a kind of embodiment flow chart of image processing method provided by the invention；
Fig. 5 is the method number of people shown in Fig. 4 and close-range imaging schematic diagram；
Fig. 6 is image processing method another kind embodiment flow chart provided by the invention；
Fig. 7 is image processing apparatus structural schematic diagram provided by the invention.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying mode, the present invention is further described in detail.It should be noted that in the absence of conflict, the implementation of the application
Feature in example and embodiment can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, still, the present invention may be used also
To be implemented using other than the one described here other modes, therefore, protection scope of the present invention is not by described below
Specific embodiment limitation.
In a first aspect, the present invention provides a kind of image processing method embodiments, as shown in Figure 2, comprising:
Face outer profile and image center in S1, acquisition close shot image；
S2, keep the face outer profile in close shot image constant, by the pixel in outer profile to the pixel of image center
Gather.
Wherein, the shape of face outer profile here is the shape of preset facial contour model；And in close shot image
The left vertex of point, left ear where the crown, the right vertex of auris dextra are located on the face outer profile.
In image processing method provided by the invention, by keeping the face outer profile of image constant, and will be in outer profile
Pixel gather to the pixel of image center, the portrait being amplified in outer profile is effectively reduced, so as to
The distortion and distortion of imaging descendant's picture caused by face and taking lens are closer when reducing due to actual photographed, after making imaging
The ratio of portrait more connect the ratio of practical face, improve the appreciation effect of close-range imaging descendant picture.
It should be noted that the outer profile of face may be generally understood to the crown, two ears and chin on the practical number of people
The outer profile of composition, than profile L ' as shown in Figure 3.However when shooting, due to compared to two ears and the crown, chin
The vertical range of position and camera is closer, and the image after planar imaging at chin portion can be also amplified.Therefore, in order to right
The image at chin portion is also reduced when image is gathered, the face outer profile in close shot image in the present invention is not
It should be the profile comprising the profile at chin on ordinary meaning, and should be face outer profile L as shown in Figure 3.In reality
In, upper vertex (point where the crown), left vertex (the left vertex of left ear) and right vertex (the right top of auris dextra of profile L
Point) and these three vertex between profile it is identical as the vertical range of camera and farthest with the vertical range of camera, this
Sample is just not necessarily to be adjusted the pixel at this partial contour.And as described above, the pixel at chin, it is to need to adjust
's.Part of the outer profile L of face below chin can be redefined in this way, so that the pixel at chin falls into the outer profile
Within L, so that the pixel at chin is also gathered to central point in adjustment.In order to determine the outer profile of face under
The part of side, can be used the shape (ellipse generally circular in cross section or with default length-width ratio) of preset facial contour with
Profile between three above-mentioned vertex is matched, so that it is determined that bottom profiled.
For ease of understanding, the implementation procedure of above-mentioned steps is described in detail below.It specifically may refer to Fig. 3.Assuming that
Descendant's image position region to the right in picture centre is imaged.Firstly, obtaining the outer profile L of face in image shown in Fig. 3 and whole
The central point O of a image.Then, keep the position of the outer profile L of face in Fig. 3 constant, by the image pixel edge in outer profile L
Arrow direction shown in Fig. 3 is to gathering at image center O point.It is understood that as shown in Figure 1, in actual photographed, only
There is the point positioned at camera lens S coverage center that positional shift will not occur after imaging.It therefore, can be with image in Fig. 3
On the basis of central point O, the image in outer profile L is gathered to image center O, so that be amplified inside outer profile L
Portrait can effectively be reduced, and the ratio for causing the portrait ratio of distortion to be adjusted to practical face due to shooting is finally made
Example, to promote the imaging effect of close shot portrait.
It should be noted that above-mentioned acquisition outer profile and image center and the implementation procedure gathered can be in practical bats
It is carried out before for terminal display imaging after taking the photograph.Since this implementation procedure processing speed is very fast, this was adjusted
Journey is that milli is insensible for a user, so that user can check after taking pictures soon after having already passed through adjustment
Meet the portrait of face actual ratio, to not influence taking pictures for user.
It is understood that the method for the distortion of adjustment portrait described in above-mentioned steps S2 can be real in several ways
It is existing, several embodiments therein are specifically described below.
(1) portrait distortion is adjusted according to face actual conditions
Method provided in an embodiment of the present invention can determine imaging at a distance from taking lens when shooting according to face
Afterwards close to image center region and the ratio compressed far from image center region to image center, tool in close shot image
Body is as shown in figure 4, step S2 can specifically include:
First ratio of the point to be adjusted in S2a, acquisition close shot image in face outer profile；Wherein, the first ratio be to
First distance and the second distance the ratio between of first outer profile point to image center of the adjustment point to image center；First foreign steamer
Exterior feature point is the line of point to be adjusted and image center and the intersection point of face outer profile；
S2b, keep the face outer profile in close shot image constant, by the pixel in outer profile to the picture of image center
Element is gathered, so that the first ratio is adjusted to original N times；Wherein, when N is actual photographed, point to be adjusted in actual persons on the face
Corresponding points between camera lens the first object distance and the first outer profile point in actual persons corresponding points on the face to second between camera lens
The ratio between object distance.
For convenience of understanding, below the execution step to the adjustment of the portrait of step S2a and step S2b and adjustment principle into
Row is described in detail.
The ratio pair of the portrait method of adjustment of the offer of step S2a and step S2b practical face when mainly foundation is shot
The portrait being amplified after imaging carries out compression adjustment.As shown in figure 5, S point is camera lens in Fig. 5, dotted fill part is camera lens S's
Coverage, the top half of S are imaging region, and lower half portion is actual photographed region.In lower half portion, O ' point is camera lens
The central point of S coverage, the corresponding image center O in the imaging region of top half；A ' is in practical face
A certain characteristic point, the corresponding A point in imaging.By being described above it is found that the A point on image is not that A ' point meets people
The imaging point of the ornamental habit of eye, therefore A point is the point to be adjusted for needing to adjust.In addition, in practical face, E ' point and F ' point are
Point on the outer profile of practical face respectively corresponds E point and F point in imaging.And E point is straight line AO and image
The intersection point of middle face outer profile, therefore E point is the first outer profile point described in step S2a.In turn, the first ratio in step S2a
Example is first distance and the second distance the ratio between of E point to O point of the A point to O point.
As shown in Figure 5, it is to be understood that since face is three-dimensional, and close shot image is only able to display the image of plane.Cause
And for point A point to be adjusted, the corresponding imaging B point of B ' point is only the A point for meeting the ornamental habit of people in practical face
Position.That is, portrait in close-range imaging and true could be made by only adjusting point A to be adjusted to the position of B point
Human face ratio is close.So present problem is how to adjust point A point to be adjusted to B point.It is understandable to be, due to
The outer profile of face remains stationary in close shot image, therefore the first outer profile point E point will not change.In addition, picture centre
Point O point will not change, thus the above problem can be converted into how by AO/EO (namely in step S2a first ratio
Example) it is adjusted to BO/EO.
If the first ratio needs just obtain BO/EO multiplied by N times, namely:
It is available by formula (1):
According to similar triangle theory, can learn:
As shown in Figure 5, B ' D '=A ' G ', therefore:
Wherein, L1For first object distance of the point A to be adjusted between actual persons corresponding points A ' and camera lens S on the face；L2It is first
Second object distance of the outer profile point E between actual persons corresponding points E ' and camera lens S on the face.Therefore, N is the first object distance and the second object
Away from ratio L1/L2。
After obtaining N, so that it may step S2b is executed, namely keeps the face outer profile in close shot image constant, it will be outer
Pixel in profile is gathered to the pixel of image center, so that the first ratio is adjusted to original N times, so that adjustment
The ratio of image afterwards is to meet the ratio of people's appreciation habit, improves the appreciation effect of imaging.
In the specific implementation, the first object distance in step S2 and the second object distance can obtain in several ways, below
One of acquisition modes are illustrated, are specifically included:
Step a, focus of the camera lens in actual persons on the face when determining shooting；
Step b, the first object distance and the second object distance are determined to the object distance of focus according to preset model and camera lens；Wherein
Preset model is sphere model or head dummy model.
Specifically, as shown in Figure 5, it is first determined focus H ' point of the camera lens in actual persons on the face when shooting.Further according to pre-
If model, establish any reference point of actual persons on the face to two ears line distance.For example, in the position for determining A ' point
Later, so that it may which the distance A ' B ' that A ' point arrives E ' F ' line is obtained according to preset model；Likewise it is possible to according to preset mould
Type obtains the distance that focus H ' point arrives E ' F ' line.Finally according between camera lens S and focus H ' object distance namely Fig. 5 in show
L0, the first object distance that A ' arrives camera lens is obtained by following formula:
L1=L0+H’I’-A’B’ (5)
Similarly, the second object distance of the first outer profile point E ' to camera lens S can be obtained by following formula:
L2=L0+H’I’ (6)
Wherein, preset model here can be sphere model.That is, can be close by the shape on the head of actual persons
Like be sphere, according to the attribute of sphere to obtain any reference point of actual persons on the face to two ears line distance, thus
According to the object distance of camera and the focus of practical face, the actual persons object distance between any point and camera on the face is obtained.
In addition, preset model here can also be head dummy model.It establishes head model and mainly passes through acquisition different people
(such as Asian, European) greater number of header data of kind, and the method based on big data obtains the upper any two points of face
Distance on actual persons head erect centerline direction (direction H ' I ' as shown in Figure 5).To know camera and reality
, can be according to the head dummy model after the object distance of the focus of face, acquisition actual persons are on the face between any point and camera
Object distance.
(2) portrait distortion is adjusted according to distant view image
Method provided in an embodiment of the present invention can be adjusted closely by the ratio of face in stored distant view image
The distortion of human face ratio in scape image, as shown in fig. 6, step S2 can also include:
First ratio of the point to be adjusted in S21, acquisition close shot image in face outer profile；Wherein, the first ratio be to
First distance and the second distance the ratio between of first outer profile point to image center of the adjustment point to image center；First foreign steamer
Exterior feature point is the line of point to be adjusted and image center and the intersection point of face outer profile；
S22, keep the face outer profile in close shot image constant, by the pixel in outer profile to the picture of image center
Element is gathered, so that the first ratio is adjusted to the second ratio；Wherein, the second ratio is corresponding points of the point to be adjusted in distant view image
To the third distance of corresponding points of the image center in distant view image, with corresponding points of the first outer profile point in distant view image
To the 4th ratio of distances constant of corresponding points of the image center in distant view image.
The principle of Image Adjusting in above-mentioned steps is illustrated below.It is understood that in vista shot, due to
Farther out, therefore the ratio of the face in distant view image may be considered and meets people's appreciation habit distance of the people apart from camera
Ratio.That is, corresponding points of the point to be adjusted in distant view image in close shot image are to image center in distant view image
In corresponding points third distance, with corresponding points of the first outer profile point in distant view image to image center in distant view image
In the 4th ratio of distances constant of corresponding points be the ratio for meeting people's appreciation habit, wherein third distance and the 4th ratio of distances constant
For the second ratio.Therefore, it is necessary to adjust the first ratio in close shot image to reference point to the second ratio, can realize pair
The distortion of face restores, so that the ratio of image adjusted is to meet the ratio of people's appreciation habit, to improve imaging
Appreciation effect.
(3) adjustment portrait distortion is indicated according to user
Image processing method provided in an embodiment of the present invention can also make close shot portrait by oneself according to the instruction of user
Justice adjustment, it that case, the third embodiment of step S2 includes:
When receiving the beginning adjustment instruction of user's input, the position of the outer profile pixel of the face in close shot image is kept
Set it is constant, keep close shot image in face outer profile it is constant, the pixel in outer profile is gathered to the pixel of image center；
Stop gathering when receiving the end adjustment instruction of user's input.
The advantage of doing so is that enable method provided in an embodiment of the present invention support user manually to close shot portrait into
The customized adjustment of row promotes user experience to extend application range of the invention.
It should be noted that the point A to be adjusted in above-described embodiment be in face outer profile first image center gather
One of point.The point that other needs are gathered gather mode and point A to be adjusted to gather mode identical, no longer go to live in the household of one's in-laws on getting married herein
It states.
Understandable to be, the illustration in above-described embodiment is only to facilitate more fully understand the embodiment of the present invention
The image processing method distorted for eliminating portrait provided, can not be constituted to specific restriction of the invention.And it is above-mentioned each
It will not influence each other between a preferred embodiment, the obtained scheme of any combination between each preferred embodiment should all
This falls into protection scope of the present invention.
Second aspect, the present invention also provides a kind of image processing apparatus embodiments, as shown in fig. 7, comprises:
Portrait determination unit 701, for obtaining face outer profile and image center in close shot image；
Image processing unit 702, for keeping the face outer profile in close shot image constant, by the pixel in outer profile to
The pixel of image center is gathered.
Wherein, the shape of face outer profile here is the shape of preset facial contour model；And in close shot image
The left vertex of point, left ear where the crown, the right vertex of auris dextra are located on the face outer profile.
In the specific implementation, the face outer profile is the round or ellipse with default length-width ratio.
In the specific implementation, described device further include: distance acquiring unit 703.The distance acquiring unit 703, is used for
Obtain the first ratio of the point to be adjusted in close shot image in face outer profile；Wherein, first ratio is that point to be adjusted arrives
The ratio between the second distance of the first distance of image center and the first outer profile point to image center；The first outer profile point
For the intersection point of the line of point to be adjusted and image center and face outer profile；
Described image processing unit 702 is further used for keeping the face outer profile in the close shot image constant, will be outer
Pixel in profile is gathered to the pixel of image center, so that first ratio is adjusted to original N times；Wherein, N is
When actual photographed, point to be adjusted actual persons corresponding points on the face between camera lens the first object distance and the first outer profile point in reality
Corresponding points on the face of border are to the ratio between the second object distance between camera lens.
In the specific implementation, the distance acquiring unit 703 is also used to obtain first object distance and second object
Away from specifically including:
Focus of the camera lens in actual persons on the face when for determining shooting；
For, to the object distance of the focus, determining the first object distance and the second object distance according to preset model and camera lens；Its
Described in preset model be sphere model or head dummy model.
In the specific implementation, the distance acquiring unit 703, for obtain in close shot image in face outer profile wait adjust
First ratio of integral point；Wherein, first ratio is first distance and first outer profile of the point to be adjusted to image center
Point arrives the ratio between the second distance of image center；The first outer profile point is line and the people of point to be adjusted and image center
The intersection point of face outer profile；
Described image processing single 702, is further used for keeping the face outer profile in the close shot image constant, by foreign steamer
Pixel in exterior feature is gathered to the pixel of image center, so that first ratio is adjusted to the second ratio；Wherein, described
Two ratios are corresponding points corresponding points to described image central point in distant view image of the point to be adjusted in distant view image
Third distance, with corresponding points of the first outer profile point in distant view image to described image central point in distant view image
Corresponding points the 4th ratio of distances constant.
In the specific implementation, described image processing unit 702 is also used in the beginning adjustment instruction for receiving user's input
When, it keeps the position of the outer profile pixel of the face in close shot image constant, keeps the face outer profile in close shot image constant,
Pixel in outer profile is gathered to the pixel of image center；Stop when receiving the end adjustment instruction of user's input poly-
Hold together.
Since the image processing apparatus that the present embodiment is introduced is the image processing method that can be executed in the embodiment of the present invention
The device of method, so based on image processing method described in the embodiment of the present invention, those skilled in the art can be much of that
Solve the present embodiment image processing apparatus specific embodiment and its various change form, so herein for the image at
How reason device realizes that the image processing method in the embodiment of the present invention is no longer discussed in detail.As long as those skilled in the art
Implement device used by image processing method in the embodiment of the present invention, belongs to the range to be protected of the application.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch
To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame
Claim.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (6)
1. a kind of image processing method characterized by comprising
Obtain the face outer profile and image center in close shot image；
It keeps the face outer profile in close shot image constant, the pixel in outer profile is gathered to the pixel of image center；Institute
The shape for stating face outer profile is the shape of preset facial contour model；And point, left ear where the crown in close shot image
Left vertex, auris dextra right vertex be located on the face outer profile；
It is described to keep the face outer profile in close shot image constant, the pixel in outer profile is gathered to the pixel of image center
Hold together, comprising:
Obtain the first ratio of the point to be adjusted in close shot image in face outer profile；Wherein, first ratio is to be adjusted
First distance and the second distance the ratio between of first outer profile point to image center of the point to image center；First foreign steamer
Exterior feature point is the line of point to be adjusted and image center and the intersection point of face outer profile；
It keeps the face outer profile in the close shot image constant, the pixel in outer profile is gathered to the pixel of image center
Hold together, so that first ratio adjusts to original N times or adjusts first ratio to the second ratio；Wherein, N is practical
When shooting, point to be adjusted actual persons corresponding points on the face between camera lens the first object distance and the first outer profile point in actual persons
Corresponding points on the face are to the ratio between the second object distance between camera lens；Second ratio is the point to be adjusted in distant view image
The third distance of corresponding points of the corresponding points to described image central point in distant view image is with the first outer profile point in distant view
4th ratio of distances constant of corresponding points of the corresponding points to described image central point in distant view image in image.
2. the method according to claim 1, wherein the face outer profile is round or with default length and width
The ellipse of ratio.
3. the method according to claim 1, wherein the method also includes: obtain first object distance and institute
The second object distance is stated, is specifically included:
Focus of the camera lens in actual persons on the face when determining shooting；
According to preset model and camera lens to the object distance of the focus, the first object distance and the second object distance are determined；It is wherein described pre-
If model be sphere model or head dummy model.
4. a kind of image processing apparatus characterized by comprising
Portrait determination unit, for obtaining face outer profile and image center in close shot image；
Image processing unit, for keeping the face outer profile in close shot image constant, by the pixel in outer profile into image
The pixel of heart point is gathered；Wherein, the shape of the face outer profile is the shape of preset facial contour model；And close shot image
In the crown where point, the left vertex of left ear, the right vertex of auris dextra be located on the face outer profile；
Distance acquiring unit, for obtaining the first ratio of the point to be adjusted in close shot image in face outer profile；Wherein, described
First ratio is first distance and the second distance of first outer profile point to image center of the point to be adjusted to image center
The ratio between；The first outer profile point is the line of point to be adjusted and image center and the intersection point of face outer profile；
Described image processing unit is further used for keeping the face outer profile in the close shot image constant, will be in outer profile
Pixel gather to the pixel of image center so that first ratio adjust to original N times or make it is described first ratio
Example is adjusted to the second ratio；Wherein, when N is actual photographed, point to be adjusted is in actual persons corresponding points on the face between camera lens
First object distance and the first outer profile point are in actual persons corresponding points on the face to the ratio between the second object distance between camera lens；Second ratio
Example is the of corresponding points corresponding points to described image central point in distant view image of the point to be adjusted in distant view image
Corresponding points pair to described image central point in distant view image of three distances with the first outer profile point in distant view image
The 4th ratio of distances constant that should be put.
5. device according to claim 4, which is characterized in that the face outer profile is round or with default length and width
The ellipse of ratio.
6. device according to claim 4, which is characterized in that the distance acquiring unit is also used to obtain first object
Away from second object distance, specifically include:
Focus of the camera lens in actual persons on the face when for determining shooting；
For, to the object distance of the focus, determining the first object distance and the second object distance according to preset model and camera lens；Wherein institute
Stating preset model is sphere model or head dummy model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610547712.4A CN106131409B (en) | 2016-07-12 | 2016-07-12 | Image processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610547712.4A CN106131409B (en) | 2016-07-12 | 2016-07-12 | Image processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106131409A CN106131409A (en) | 2016-11-16 |
| CN106131409B true CN106131409B (en) | 2019-01-25 |
Family
ID=57282945
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610547712.4A Active CN106131409B (en) | 2016-07-12 | 2016-07-12 | Image processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106131409B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108513668B (en) * | 2016-12-29 | 2020-09-08 | 华为技术有限公司 | Picture processing method and device |
| CN110232667B (en) * | 2019-06-17 | 2021-06-04 | 厦门美图之家科技有限公司 | Image distortion correction method, device, electronic equipment and readable storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002175538A (en) * | 2000-12-08 | 2002-06-21 | Mitsubishi Electric Corp | Device and method for portrait generation, recording medium with portrait generating program recorded thereon, terminal for communication, and communication method by terminal for communication |
| JP4973393B2 (en) * | 2007-08-30 | 2012-07-11 | セイコーエプソン株式会社 | Image processing apparatus, image processing method, image processing program, and image processing system |
| US9202138B2 (en) * | 2012-10-04 | 2015-12-01 | Adobe Systems Incorporated | Adjusting a contour by a shape model |
| CN104751404B (en) * | 2013-12-30 | 2019-04-12 | 腾讯科技（深圳）有限公司 | A kind of method and device of image transformation |
| CN105678251B (en) * | 2015-12-31 | 2019-10-01 | Tcl海外电子（惠州）有限公司 | Face image processing process and device |
-
2016
- 2016-07-12 CN CN201610547712.4A patent/CN106131409B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106131409A (en) | 2016-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105580051B (en) | Picture catching feedback | |
| US10171792B2 (en) | Device and method for three-dimensional video communication | |
| WO2022160701A1 (en) | Special effect generation method and apparatus, device, and storage medium | |
| WO2020192458A1 (en) | Image processing method and head-mounted display device | |
| US10110868B2 (en) | Image processing to determine center of balance in a digital image | |
| DE112018007721T5 (en) | Acquire and modify 3D faces using neural imaging and time tracking networks | |
| CN106797459A (en) | The transmission of 3 D video | |
| CN106462956A (en) | Local adaptive histogram equalization | |
| CN107578395B (en) | Image quality evaluation method based on visual perception | |
| CN103369238B (en) | Image creating device and image creating method | |
| TWI691937B (en) | Method and device for filtering light spot, computer readable storage medium, processor, gaze tracking equipment | |
| CN105825499A (en) | Reference plane determination method and determination system | |
| CN105761243A (en) | Three-dimensional full face photographing system based on structured light projection and photographing method thereof | |
| CN107908278A (en) | A kind of method and apparatus of Virtual Reality interface generation | |
| CN102761768A (en) | Method and device for realizing three-dimensional imaging | |
| CN108377355A (en) | A kind of video data handling procedure, device and equipment | |
| CN110324532A (en) | A kind of image weakening method, device, storage medium and electronic equipment | |
| CN113192132B (en) | Eye catch method and device, storage medium and terminal | |
| WO2015149611A1 (en) | Image presentation control methods and image presentation control apparatuses | |
| CN106131409B (en) | Image processing method and device | |
| CN108470149A (en) | A kind of 3D 4 D datas acquisition method and device based on light-field camera | |
| CN112598628A (en) | Image occlusion detection method and device, shooting equipment and medium | |
| CN107786808B (en) | Method and apparatus for generating data representative of a shot associated with light field data | |
| CN107065164B (en) | Image presentation method and device | |
| Hauser et al. | Image quality benchmark of computational bokeh |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210707 Address after: 100015 No. 10, Jiuxianqiao Road, Beijing, Chaoyang District Patentee after: BOE TECHNOLOGY GROUP Co.,Ltd. Patentee after: Beijing Oriental Wisdom Material Union Technology Co.,Ltd. Address before: 100015 No. 10, Jiuxianqiao Road, Beijing, Chaoyang District Patentee before: BOE TECHNOLOGY GROUP Co.,Ltd. Patentee before: BEIJING BOE MULTIMEDIA TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |