CN107977927A - Stature method of adjustment and device, computing device based on view data - Google Patents
Stature method of adjustment and device, computing device based on view data Download PDFInfo
- Publication number
- CN107977927A CN107977927A CN201711339119.1A CN201711339119A CN107977927A CN 107977927 A CN107977927 A CN 107977927A CN 201711339119 A CN201711339119 A CN 201711339119A CN 107977927 A CN107977927 A CN 107977927A
- Authority
- CN
- China
- Prior art keywords
- special object
- image
- ratio
- adjustment
- adjusted
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000012545 processing Methods 0.000 claims abstract description 38
- 230000004927 fusion Effects 0.000 claims abstract description 20
- 210000000746 body region Anatomy 0.000 claims description 63
- 239000002279 physical standard Substances 0.000 claims description 52
- 238000004891 communication Methods 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 abstract description 21
- 238000013135 deep learning Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 241000220324 Pyrus Species 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 208000001491 myopia Diseases 0.000 description 2
- 235000021017 pears Nutrition 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241000406668 Loxodonta cyclotis Species 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Classifications
-
- G06T3/04—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Abstract
The invention discloses a kind of stature method of adjustment and device, computing device based on view data, its method includes：Obtain the pending image for including special object；Scene cut processing is carried out to pending image, obtains including the foreground image and background image of special object body；The key message of special object body is extracted from foreground image, special object Body proportion is adjusted according to key message；Foreground image after adjustment and background image are subjected to fusion treatment, the image after being handled.The present invention is adjusted according to the body key message of special object in itself so that the Body proportion of the special object in the image obtained after adjustment is more natural, and display effect is truer.And whole process is not required user to carry out extra process to image, user time is saved.
Description
Technical field
The present invention relates to image processing field, and in particular to a kind of stature method of adjustment and device based on view data,
Computing device.
Background technology
With the development of science and technology, self-timer, live, making video image become a kind of fashion.User can according to oneself
Mood is clapped, claps everywhere, arbitrarily clapped at any time.Take pictures also increasingly simpler for a user, it is more and more convenient.The figure that user obtains
Image sharpness, resolution ratio, display effect also greatly improve.But the image that the prior art obtains does not beautify user's stature
Processing, or be only that stature is integrally simply subjected to elongation processing, the effect of processing is coarse, untrue, can not meet user
Demand.And user is after image is obtained, if handled by user is further again to image manually, and need user have compared with
High image processing techniques, and the cost user more time is needed in processing, handle cumbersome, technical sophistication.
Therefore, it is necessary to a kind of stature method of adjustment based on view data, while user demand is met, and saves and uses
The family time, it is not necessary to which user exclusively carries out processing.
The content of the invention
In view of the above problems, it is proposed that the present invention overcomes the above problem in order to provide one kind or solves at least in part
State the stature method of adjustment and device, computing device based on view data of problem.
According to an aspect of the invention, there is provided a kind of stature method of adjustment based on view data, it includes：
Obtain the pending image for including special object；
Scene cut processing is carried out to pending image, obtains including the foreground image and Background of special object body
Picture；
The key message of special object body is extracted from foreground image, according to key message to special object body ratio
Example is adjusted；
Foreground image after adjustment and background image are subjected to fusion treatment, the image after being handled.
Alternatively, key message is key point information；
The key message of special object body is extracted from foreground image, according to key message to special object body ratio
Example, which is adjusted, to be further comprised：
The key point information of special object body is extracted from foreground image；
According to key point information, special object body region is determined, and special object body region ratio is calculated；
According to default physical standard ratio, special object body region ratio is adjusted.
Alternatively, according to default physical standard ratio, special object body region ratio is adjusted and is further comprised：
According to default physical standard ratio, special object body region ratio is analyzed, determines special object body region ratio
The adjustment target proportion of example；
According to adjustment target proportion, special object body region ratio is adjusted.
Alternatively, key message is key point information；
The key message of special object body is extracted from foreground image, according to key message to special object body ratio
Example, which is adjusted, to be further comprised：
The key point information of special object body is extracted from foreground image；
According to key point information, special object upper part of the body region and/or special object lower part of the body region are determined, and calculate
To special object upper part of the body ratio and/or special object lower part of the body ratio；
According to default physical standard ratio, special object upper part of the body ratio and/or special object lower part of the body ratio are carried out
Adjustment.
Alternatively, according to default physical standard ratio, to special object upper part of the body ratio and/or special object lower part of the body ratio
Example, which is adjusted, to be further comprised：
According to default physical standard ratio, special object upper part of the body ratio and/or special object lower part of the body ratio are analyzed, really
Determine the adjustment target proportion of special object upper part of the body ratio and/or the adjustment target proportion of special object lower part of the body ratio；
According to the adjustment target proportion of special object upper part of the body ratio, special object upper part of the body ratio is adjusted；With/
Or, the adjustment target proportion according to special object lower part of the body ratio, special object lower part of the body ratio is adjusted.
Alternatively, the pending image comprising special object is obtained to further comprise：
The image comprising special object that real-time image acquisition collecting device is caught is as pending image.
Alternatively, the pending image comprising special object is obtained to further comprise：
Real-time image acquisition collecting device is captured and/or the video recorded in include special object current frame image
As pending image；Treated alternatively, obtaining the current frame image comprising special object in currently played video in real time and being used as
Handle image.
Alternatively, the pending image comprising special object is obtained to further comprise：
Obtain video data；
Video data is screened, obtains the two field picture comprising special object as pending image.
Alternatively, method further includes：
Image after display processing.
According to another aspect of the present invention, there is provided a kind of stature adjusting apparatus based on view data, it includes：
Acquisition module, suitable for obtaining the pending image for including special object；
Split module, suitable for carrying out scene cut processing to pending image, obtain including the prospect of special object body
Image and background image；
Module is adjusted, suitable for extracting the key message of special object body from foreground image, according to key message pair
Special object Body proportion is adjusted；
Fusion Module, suitable for the foreground image after adjustment and background image are carried out fusion treatment, the figure after being handled
Picture.
Alternatively, key message is key point information；
Adjustment module is further adapted for：
The key point information of special object body is extracted from foreground image；According to key point information, it is specific right to determine
As body region, and special object body region ratio is calculated；According to default physical standard ratio, to special object body
Regional percentage is adjusted.
Alternatively, adjustment module is further adapted for：
According to default physical standard ratio, special object body region ratio is analyzed, determines special object body region ratio
The adjustment target proportion of example；According to adjustment target proportion, special object body region ratio is adjusted.
Alternatively, key message is key point information；
Adjustment module is further adapted for：
The key point information of special object body is extracted from foreground image；According to key point information, it is specific right to determine
As upper part of the body region and/or special object lower part of the body region, and special object upper part of the body ratio and/or special object is calculated
Lower part of the body ratio；According to default physical standard ratio, to special object upper part of the body ratio and/or special object lower part of the body ratio into
Row adjustment.
Alternatively, adjustment module is further adapted for：
According to default physical standard ratio, special object upper part of the body ratio and/or special object lower part of the body ratio are analyzed, really
Determine the adjustment target proportion of special object upper part of the body ratio and/or the adjustment target proportion of special object lower part of the body ratio；According to
The adjustment target proportion of special object upper part of the body ratio, is adjusted special object upper part of the body ratio；And/or according to specific
The adjustment target proportion of object lower part of the body ratio, is adjusted special object lower part of the body ratio.
Alternatively, acquisition module is further adapted for：
The image comprising special object that real-time image acquisition collecting device is caught is as pending image.
Alternatively, acquisition module is further adapted for：
Real-time image acquisition collecting device is captured and/or the video recorded in include special object current frame image
As pending image；Treated alternatively, obtaining the current frame image comprising special object in currently played video in real time and being used as
Handle image.
Alternatively, acquisition module is further adapted for：
Obtain video data；
Video data is screened, obtains the two field picture comprising special object as pending image.
Alternatively, device further includes：
Display module, suitable for the image after display processing.
According to another aspect of the invention, there is provided a kind of computing device, including：Processor, memory, communication interface and
Communication bus, processor, memory and communication interface complete mutual communication by communication bus；
Memory is used to store an at least executable instruction, and executable instruction makes processor execution is above-mentioned to be based on view data
The corresponding operation of stature method of adjustment.
In accordance with a further aspect of the present invention, there is provided a kind of computer-readable storage medium, is stored with least one in storage medium
Executable instruction, executable instruction make processor perform such as the above-mentioned corresponding operation of stature method of adjustment based on view data.
The stature method of adjustment and device, computing device based on view data provided according to the present invention, obtains comprising spy
Determine the pending image of object；Scene cut processing is carried out to pending image, obtains including the foreground picture of special object body
Picture and background image；The key message of special object body is extracted from foreground image, according to key message to special object
Body proportion is adjusted；Foreground image after adjustment and background image are subjected to fusion treatment, the image after being handled.This
Invention is adjusted according to the body key message of special object in itself so that special object in the image obtained after adjustment
Body proportion is more natural, and display effect is truer.And whole process is not required user to carry out extra process to image, user is saved
Time.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, and in order to allow above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by the embodiment of the present invention.
Brief description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this area
Technical staff will be clear understanding.Attached drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And in whole attached drawing, identical component is denoted by the same reference numerals.In the accompanying drawings：
Fig. 1 shows the flow chart of the stature method of adjustment according to an embodiment of the invention based on view data；
Fig. 2 shows the flow chart of the stature method of adjustment in accordance with another embodiment of the present invention based on view data；
Fig. 3 shows the functional block diagram of the stature adjusting apparatus according to an embodiment of the invention based on view data；
Fig. 4 shows a kind of structure diagram of computing device according to an embodiment of the invention.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
Fig. 1 shows the flow chart of the stature method of adjustment according to an embodiment of the invention based on view data.Such as
Shown in Fig. 1, the stature method of adjustment based on view data specifically comprises the following steps：
Step S101, obtains the pending image for including special object.
Special object is illustrated by taking human body as an example in the present invention, but is not limited only to human body.
Obtaining the mode of the pending image comprising special object can be obtained by following several ways：
The image comprising special object that real-time image acquisition collecting device is caught such as obtains in real time as pending image
Self-timer, the image for including special object shot using the camera of mobile equipment；Alternatively, real-time image acquisition collecting device institute
The current frame image comprising special object such as obtains live in real time as pending image in shooting and/or the video recorded
During shoot the current frame image comprising special object, obtain in real time record short-sighted frequency, in fast video comprising specific right
The current frame image of elephant；Treated alternatively, obtaining the current frame image comprising special object in currently played video in real time and being used as
Image is handled, the current frame image for including special object in the video played as obtained present terminal equipment in real time.Alternatively,
One section of video data can also be first obtained, video data is screened, the wherein two field picture comprising special object is only obtained and makees
For pending image.
The pending image got can obtain the image of shooting, recording or broadcasting in real time using any of the above mode,
Can also be to directly acquire the image for having been taken or recording.
Step S102, carries out scene cut processing to pending image, obtains including the foreground image of special object body
And background image.
Scene cut processing is carried out to the pending image got, since the present embodiment is mainly to the stature of special object
It is adjusted, it is necessary to be to split the body of special object from pending image, obtains comprising special object body
Foreground image and background image.
When carrying out scene cut processing to pending image, such as deep learning method can be utilized.Deep learning is
It is a kind of based on the method that data are carried out with representative learning in machine learning.Observation (such as piece image) can use a variety of sides
Formula represents, such as vector of each pixel intensity value, or is more abstractively expressed as a series of sides, the region etc. of given shape.
And some specific method for expressing are used to be easier from example learning task (for example, recognition of face).
Step S103, extracts the key message of special object body, according to key message to specific from foreground image
Subject's body ratio is adjusted.
The key message can be specially key point information, key area information, and/or key lines information etc..This implementation
Example is illustrated by taking key point information as an example, but the key message of the present invention is not limited to key point information.Believed using key point
Breath can improve the processing speed and efficiency adjusted according to key point information to Body proportion, can be directly according to key point information
Body proportion is adjusted, it is not necessary to carry out the complex operations such as subsequently calculating, analysis to key message again.Meanwhile key point
Information is extracted accurately easy to extraction, and obtained Body proportion information is more accurate.Key point information is being extracted from foreground image
When, extract the key point information positioned at special object body edge.Key point information, body such as positioned at body trunk edge
The key point information at four limbs edge etc..
The key point information on special object body is extracted from foreground image., can be true according to key point information
Determine special object body region.Also, special object body region ratio can also be calculated according to key point information.Such as
Body height and the width ratio, head body height ratio, estimation height etc..According to default physical standard ratio, to special object body
Body region ratio is adjusted.Default physical standard ratio can be as healthy human body standard proportional (masculinity and femininity it is pre-
If physical standard ratio is also different according to gender difference, corresponding default body is set after special object gender can be identified
Body standard proportional)；Alternatively, according to the preassigned famous person of user, the physical standard ratio of famous person is obtained as default body mark
Quasi- ratio etc..When being adjusted to special object body region ratio, according to default physical standard ratio, it is corresponding will be specific
Subject's body regional percentage is adjusted to default physical standard ratio.Specifically, such as the body of special object is highly stretched,
Width reduces etc. so that special object body region ratio is adjusted to default physical standard ratio.
Further, to make the effect after adjustment truer, more natural, can be analyzed special according to default physical standard ratio
Determine the body region ratio of object in itself, determine the adjustment target proportion of special object body region ratio.According to adjustment target
Ratio, is adjusted special object body region ratio, and special object body region ratio is adjusted to adjustment target proportion.
It so outside being adjusted to special object body, can also retain the personality of special object body itself, avoid
All human bodies are adjusted so as to machine-made adjustment effect.
Step S104, fusion treatment, the image after being handled are carried out by the foreground image after adjustment and background image.
The background image that foreground image after adjustment and dividing processing are obtained carries out fusion treatment, the figure after being handled
Picture.Alternatively it is also possible to the foreground image after adjustment and other background images are subjected to fusion treatment, the figure after being handled
Picture.Other background images can be preassigned dynamic or static background image, or the background set according to user preference
Image.
Step S105, the image after display processing.
Image after processing can be shown to user in real time, facilitate user can directly be seen that specific right after adjusting
As body, the perfect stature ratio display effect of user is presented directly to.
This step is optional step, is obtaining pending image in real time, is being adjusted, and after the image after being handled, is stood
Carve to replace using the image after processing and treat that image is shown, be generally replaced within 1/24 second, for a user, by
In replacing, the time is relatively short, and human eye is not discovered significantly, equivalent to the image after real-time display processing.
The stature method of adjustment based on view data provided according to the present invention, obtains the pending figure for including special object
Picture；Scene cut processing is carried out to pending image, obtains including the foreground image and background image of special object body；In the past
The key message of special object body is extracted in scape image, special object Body proportion is adjusted according to key message；
Foreground image after adjustment and background image are subjected to fusion treatment, the image after being handled.The present invention is according to special object
The body key message of itself is adjusted so that and the Body proportion of the special object in the image obtained after adjustment is more natural,
Display effect is truer.And whole process is not required user to carry out extra process to image, user time is saved.Further, also
The body region ratio of special object in itself in each image can be analyzed, to each image according to default physical standard ratio
Middle special object sets it to adjust target proportion in itself, so that the personalization that adjustment can retain special object body itself is special
Color so that the effect after adjustment is more natural true, avoids that machine-made adjustment effect is presented.
Fig. 2 shows the flow chart of the stature method of adjustment in accordance with another embodiment of the present invention based on view data.
As shown in Fig. 2, the stature method of adjustment based on view data specifically comprises the following steps：
Step S201, obtains the pending image for including special object.
Step S202, carries out scene cut processing to pending image, obtains including the foreground image of special object body
And background image.
Above step is with reference to Fig. 1 embodiment step S101-S102, and details are not described herein.
Step S203, extracts the key point information of special object body from foreground image.
Step S204, according to key point information, determines special object upper part of the body region and/or special object lower part of the body area
Domain, and special object upper part of the body ratio and/or special object lower part of the body ratio is calculated.
It is thinner above the waist such as pears type stature in view of the situation of actual human body, but the lower part of the body is more fat；Or only on
The more fat needs of half body are adjusted.So when stature adjusts, according to key point information, the upper half of special object is marked off
Body region and lower part of the body region, respectively targetedly adjust upper part of the body region and/or lower part of the body region so that after adjustment
Stature it is more perfect.
Behind definite special object upper part of the body region and/or special object lower part of the body region, according to key point information, calculate
Obtain special object upper part of the body ratio and/or special object lower part of the body ratio.
Step S205, according to default physical standard ratio, to special object upper part of the body ratio and/or the special object lower part of the body
Ratio is adjusted.
Default physical standard ratio can be standard proportional (the default physical standard ratio of masculinity and femininity such as healthy human body
Example is also different according to gender difference, and corresponding default physical standard ratio is set after special object gender can be identified)；
Alternatively, according to the preassigned famous person of user, the physical standard ratio of famous person is obtained as default physical standard ratio etc..It is default
Include upper part of the body ratio, lower part of the body ratio etc. in physical standard ratio.
When being adjusted to special object upper part of the body ratio and/or special object lower part of the body ratio, according to default body
Standard proportional, the corresponding upper part of the body ratio being adjusted to special object upper part of the body ratio in default physical standard ratio, and/or
Special object lower part of the body ratio is adjusted to preset the lower part of the body ratio in physical standard ratio.
Further, to make the effect after adjustment truer, more natural, can be analyzed special according to default physical standard ratio
Determine object upper part of the body ratio and/or special object lower part of the body ratio, determine the adjustment target proportion of special object upper part of the body ratio
And/or the adjustment target proportion of special object lower part of the body ratio.It is right according to the adjustment target proportion of special object upper part of the body ratio
Special object upper part of the body ratio is adjusted；And/or the adjustment target proportion according to special object lower part of the body ratio, to specific
Object lower part of the body ratio is adjusted.So it can also retain special object sheet outside being adjusted to special object body
The personality of body body, avoids all human bodies from being adjusted so as to machine-made adjustment effect.
Step S206, fusion treatment, the image after being handled are carried out by the foreground image after adjustment and background image.
Step S207, the image after display processing.
Above step is with reference to Fig. 1 embodiment step S104-S105, and details are not described herein.
The stature method of adjustment based on view data provided according to the present invention, according to key point information, it is specific right to determine
As upper part of the body region and/or special object lower part of the body region, and special object upper part of the body ratio and/or special object is calculated
Lower part of the body ratio.Targetedly upper part of the body region and/or lower part of the body region are adjusted respectively, more meet actual human body feelings
Condition.Further, special object upper part of the body ratio and/or spy in each image can also be analyzed according to default physical standard ratio
Object lower part of the body ratio is determined, to setting the adjustment target proportion of special object upper part of the body ratio and/or specific right in each image
As the adjustment target proportion of lower part of the body ratio, so that adjustment can retain the personality of special object body itself so that
Effect after adjustment is more natural true, avoids that machine-made adjustment effect is presented.
Fig. 3 shows the functional block diagram of the stature adjusting apparatus according to an embodiment of the invention based on view data.
As shown in figure 3, the stature adjusting apparatus based on view data includes following module：
Acquisition module 310, suitable for obtaining the pending image for including special object.
The mode that acquisition module 310 obtains the pending image comprising special object can be carried out by following several ways
Obtain：
The image comprising special object that 310 real-time image acquisition collecting device of acquisition module is caught is as pending figure
Picture, as acquisition module 310 obtains self-timer, the image for including special object shot using the camera of mobile equipment in real time；Or
Person, 310 real-time image acquisition collecting device of acquisition module is captured and/or the video recorded in it is current comprising special object
Two field picture as pending image, as acquisition module 310 obtain in real time it is live during shoot it is current comprising special object
Two field picture, obtain the current frame image for including special object in the short-sighted frequency recorded, fast video in real time；Alternatively, acquisition module 310
Obtain in real time and the current frame image of special object is included in currently played video as pending image, such as acquisition module
310 obtain the current frame image for including special object in the video that present terminal equipment is playing in real time.Alternatively, acquisition module
310 can also first obtain one section of video data, and video data is screened, and only obtain the two field picture for wherein including special object
As pending image.
The pending image that acquisition module 310 is got can be obtained in real time using any of the above mode shooting, record or
The image of broadcasting, or directly acquire the image for having been taken or recording.
Split module 320, suitable for carrying out scene cut processing to pending image, obtain before including special object body
Scape image and background image.
The pending image that segmentation module 320 gets acquisition module 310 carries out scene cut processing, due to this implementation
Example is mainly adjusted the stature of special object, and segmentation module 320 needs to be from pending image by the body of special object
In split, obtain including the foreground image and background image of special object body.
Split module 320 when carrying out scene cut processing to pending image, such as deep learning method can be utilized.
Deep learning is a kind of based on the method that data are carried out with representative learning in machine learning.Observation (such as piece image) can be with
Use a plurality of ways to represent, a series of such as vector of each pixel intensity value, or be more abstractively expressed as sides, given shape
Region etc..And some specific method for expressing are used to be easier from example learning task (for example, recognition of face).
Module 330 is adjusted, suitable for extracting the key message of special object body from foreground image, according to key message
Special object Body proportion is adjusted.
The key message can be specially key point information, key area information, and/or key lines information etc..This implementation
Example is illustrated by taking key point information as an example, but the key message of the present invention is not limited to key point information.Believed using key point
Breath can improve the processing speed and efficiency adjusted according to key point information to Body proportion, can be directly according to key point information
Body proportion is adjusted, it is not necessary to carry out the complex operations such as subsequently calculating, analysis to key message again.Meanwhile key point
Information is extracted accurately easy to extraction, and obtained Body proportion information is more accurate.Adjustment module 330 is being carried from foreground image
When taking key point information, the key point information positioned at special object body edge is extracted.Such as it is located at the pass at body trunk edge
Key point information, the key point information at body limbs edge etc..
Adjustment module 330 extracts the key point information on special object body from foreground image.According to key point
Information, adjustment module 330 can determine special object body region.Also, adjustment module 330 can also be believed according to key point
Breath, is calculated special object body region ratio.Such as body height and the width ratio, head body height ratio, estimation height.
Module 330 is adjusted according to default physical standard ratio, special object body region ratio is adjusted.Default physical standard ratio
Example can be as healthy human body standard proportional (the default physical standard ratio of masculinity and femininity is also different according to gender difference,
Corresponding default physical standard ratio is set after special object gender can be identified)；Alternatively, preassigned according to user
Famous person, obtain the physical standard ratio of famous person as default physical standard ratio etc..Module 330 is adjusted to special object body
It is corresponding to be adjusted to special object body region ratio according to default physical standard ratio when body region ratio is adjusted
Default physical standard ratio.Specifically, highly being stretched to the body of special object as adjusted module 330, width contracts
It is small etc. so that special object body region ratio is adjusted to default physical standard ratio.
Further, to make the effect after adjustment truer, more natural, adjustment module 330 can be according to default physical standard
Ratio, analyzes the body region ratio of special object in itself, determines the adjustment target proportion of special object body region ratio.Adjust
Mould preparation block 330 is adjusted special object body region ratio, by special object body region ratio according to adjustment target proportion
Example is adjusted to adjustment target proportion.So also it can retain special object in itself outside being adjusted to special object body
The personality of body, avoids all human bodies from being adjusted so as to machine-made adjustment effect.
It is thinner above the waist such as pears type stature in view of the situation of actual human body, but the lower part of the body is more fat；Or only on
The more fat needs of half body are adjusted.So when stature adjusts, adjustment module 330 is needed according to key point information, division
Go out the upper part of the body region and lower part of the body region of special object, specific aim is carried out to upper part of the body region and/or lower part of the body region respectively
Adjustment so that the stature after adjustment is more perfect.
Module 330 is adjusted behind definite special object upper part of the body region and/or special object lower part of the body region, according to key
Point information, is calculated special object upper part of the body ratio and/or special object lower part of the body ratio.Wrapped in default physical standard ratio
Upper part of the body ratio, lower part of the body ratio etc. are included.Module 330 is adjusted under to special object upper part of the body ratio and/or special object
It is corresponding that special object upper part of the body ratio is adjusted to default according to default physical standard ratio when half body ratio is adjusted
Upper part of the body ratio in physical standard ratio, and/or special object lower part of the body ratio are adjusted to preset physical standard ratio
In lower part of the body ratio.
Further, special object upper part of the body ratio can also be analyzed according to default physical standard ratio by adjusting module 330
And/or special object lower part of the body ratio, determine the adjustment target proportion and/or special object lower half of special object upper part of the body ratio
The adjustment target proportion of body ratio.Adjustment target proportion of the module 330 according to special object upper part of the body ratio is adjusted, to specific right
As upper part of the body ratio is adjusted；And/or the adjustment target proportion according to special object lower part of the body ratio, under special object
Half body ratio is adjusted.So it can also retain special object body itself outside being adjusted to special object body
Personality, avoid all human bodies from being adjusted so as to machine-made adjustment effect.
Fusion Module 340, suitable for the foreground image after adjustment and background image are carried out fusion treatment, after being handled
Image.
The background image that Fusion Module 340 obtains the foreground image after adjustment and dividing processing carries out fusion treatment, obtains
Image after to processing.Alternatively, Fusion Module 340 can also be melted the foreground image after adjustment and other background images
Conjunction is handled, the image after being handled.Other background images can be the background image of preassigned dynamic or static state, or root
The background image set according to user preference.
Display module 350, suitable for the image after display processing.
Image after processing can be shown to user in real time by display module 350, facilitate user to can directly be seen that tune
Special object body after whole, is presented directly to the perfect stature ratio display effect of user.
Acquisition module 310 is obtaining pending image in real time, adjusts module 330 and is adjusted, Fusion Module 340 obtains everywhere
After image after reason, display module 350 at once using after processing image replace treat that image is shown, generally 1/24 second it
Inside it is replaced, for a user, relatively short due to replacing the time, human eye is not discovered significantly, and display module 350 is suitable
Image after real-time display processing.
The stature adjusting apparatus based on view data provided according to the present invention, obtains the pending figure for including special object
Picture；Scene cut processing is carried out to pending image, obtains including the foreground image and background image of special object body；In the past
The key message of special object body is extracted in scape image, special object Body proportion is adjusted according to key message；
Foreground image after adjustment and background image are subjected to fusion treatment, the image after being handled.The present invention is according to special object
The body key message of itself is adjusted so that and the Body proportion of the special object in the image obtained after adjustment is more natural,
Display effect is truer.And whole process is not required user to carry out extra process to image, user time is saved.Further, also
The body region ratio of special object in itself in each image can be analyzed, to each image according to default physical standard ratio
Middle special object sets it to adjust target proportion in itself, so that the personalization that adjustment can retain special object body itself is special
Color so that the effect after adjustment is more natural true, avoids that machine-made adjustment effect is presented.
Present invention also provides a kind of nonvolatile computer storage media, the computer-readable storage medium is stored with least
One executable instruction, the computer executable instructions can perform the stature based on view data in above-mentioned any means embodiment
Method of adjustment.
Fig. 4 shows a kind of structure diagram of computing device according to an embodiment of the invention, and the present invention is specific real
Specific implementation of the example not to computing device is applied to limit.
As shown in figure 4, the computing device can include：Processor (processor) 402, communication interface
(Communications Interface) 404, memory (memory) 406 and communication bus 408.
Wherein：
Processor 402, communication interface 404 and memory 406 complete mutual communication by communication bus 408.
Communication interface 404, for communicating with the network element of miscellaneous equipment such as client or other servers etc..
Processor 402, for executive program 410, can specifically perform the above-mentioned stature method of adjustment based on view data
Correlation step in embodiment.
Specifically, program 410 can include program code, which includes computer-managed instruction.
Processor 402 is probably central processor CPU, or specific integrated circuit ASIC (Application
Specific Integrated Circuit), or be arranged to implement the embodiment of the present invention one or more integrate electricity
Road.The one or more processors that computing device includes, can be same type of processors, such as one or more CPU；Also may be used
To be different types of processor, such as one or more CPU and one or more ASIC.
Memory 406, for storing program 410.Memory 406 may include high-speed RAM memory, it is also possible to further include
Nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.
Program 410 specifically can be used for so that processor 402 perform in above-mentioned any means embodiment based on picture number
According to stature method of adjustment.The specific implementation of each step may refer to the above-mentioned stature adjustment based on view data in program 410
Corresponding description in corresponding steps and unit in embodiment, this will not be repeated here.Those skilled in the art can be clearly
Recognize, for convenience and simplicity of description, the equipment of foregoing description and the specific work process of module, may be referred to preceding method
Corresponding process description in embodiment, details are not described herein.
Algorithm and display be not inherently related to any certain computer, virtual system or miscellaneous equipment provided herein.
Various general-purpose systems can also be used together with teaching based on this.As described above, required by constructing this kind of system
Structure be obvious.In addition, the present invention is not also directed to any certain programmed language.It should be understood that it can utilize various
Programming language realizes the content of invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the specification that this place provides, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice in the case of these no details.In some instances, known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it will be appreciated that in order to simplify the disclosure and help to understand one or more of each inventive aspect,
Above in the description to the exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention：I.e. required guarantor
The application claims of shield features more more than the feature being expressly recited in each claim.It is more precisely, such as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following embodiment are expressly incorporated in the embodiment, wherein each claim is in itself
Separate embodiments all as the present invention.
Those skilled in the art, which are appreciated that, to carry out adaptively the module in the equipment in embodiment
Change and they are arranged in one or more equipment different from the embodiment.Can be the module or list in embodiment
Member or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement or
Sub-component.In addition at least some in such feature and/or process or unit exclude each other, it can use any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, summary and attached drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (including adjoint power
Profit requires, summary and attached drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
Replace.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included some features rather than further feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
One of meaning mode can use in any combination.
The all parts embodiment of the present invention can be with hardware realization, or to be run on one or more processor
Software module realize, or realized with combinations thereof.It will be understood by those of skill in the art that it can use in practice
Microprocessor or digital signal processor (DSP) realize the stature adjustment according to embodiments of the present invention based on view data
Device in some or all components some or all functions.The present invention is also implemented as being used to perform institute here
The some or all equipment or program of device of the method for description are (for example, computer program and computer program production
Product).Such program for realizing the present invention can store on a computer-readable medium, or can have one or more
The form of signal.Such signal can be downloaded from internet website and obtained, and either be provided or on carrier signal to appoint
What other forms provides.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between bracket 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" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of some different elements and being come by means of properly programmed computer real
It is existing.In if the unit claim of equipment for drying is listed, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and run after fame
Claim.
Claims (10)
1. a kind of stature method of adjustment based on view data, it includes：
Obtain the pending image for including special object；
Scene cut processing is carried out to the pending image, obtains including the foreground image and background of the special object body
Image；
The key message of the special object body is extracted from the foreground image, according to the key message to the spy
Determine subject's body ratio to be adjusted；
Foreground image after adjustment and background image are subjected to fusion treatment, the image after being handled.
2. according to the method described in claim 1, wherein, the key message is key point information；
The key message that the special object body is extracted from the foreground image, according to the key message to institute
State special object Body proportion and be adjusted and further comprise：
The key point information of the special object body is extracted from the foreground image；
According to the key point information, the special object body region is determined, and the special object body region is calculated
Domain ratio；
According to default physical standard ratio, the special object body region ratio is adjusted.
3. according to the method described in claim 2, wherein, the basis presets physical standard ratio, to the special object body
Body region ratio, which is adjusted, to be further comprised：
According to default physical standard ratio, the special object body region ratio is analyzed, determines the special object body region
The adjustment target proportion of domain ratio；
According to the adjustment target proportion, the special object body region ratio is adjusted.
4. according to the method described in claim 1, wherein, the key message is key point information；
The key message that the special object body is extracted from the foreground image, according to the key message to institute
State special object Body proportion and be adjusted and further comprise：
The key point information of the special object body is extracted from the foreground image；
According to the key point information, the special object upper part of the body region and/or the special object lower part of the body region are determined,
And the special object upper part of the body ratio and/or the special object lower part of the body ratio is calculated；
According to default physical standard ratio, to the special object upper part of the body ratio and/or the special object lower part of the body ratio
It is adjusted.
5. according to the method described in claim 4, wherein, the basis presets physical standard ratio, on the special object
Half body ratio and/or the special object lower part of the body ratio are adjusted and further comprise：
According to default physical standard ratio, the special object upper part of the body ratio and/or the special object lower part of the body ratio are analyzed
Example, determines the adjustment of the adjustment target proportion and/or the special object lower part of the body ratio of the special object upper part of the body ratio
Target proportion；
According to the adjustment target proportion of the special object upper part of the body ratio, the special object upper part of the body ratio is adjusted
It is whole；And/or the adjustment target proportion according to the special object lower part of the body ratio, to the special object lower part of the body ratio into
Row adjustment.
6. according to the method any one of claim 1-5, wherein, it is described to obtain the pending image for including special object
Further comprise：
The image comprising special object that real-time image acquisition collecting device is caught is as pending image.
7. according to the method any one of claim 1-5, wherein, it is described to obtain the pending image for including special object
Further comprise：
Real-time image acquisition collecting device is captured and/or the video recorded in include special object current frame image conduct
Pending image；The current frame image of special object is included in currently played video as pending alternatively, obtaining in real time
Image.
8. a kind of stature adjusting apparatus based on view data, it includes：
Acquisition module, suitable for obtaining the pending image for including special object；
Split module, suitable for carrying out scene cut processing to the pending image, obtain comprising the special object body
Foreground image and background image；
Module is adjusted, suitable for extracting the key message of the special object body from the foreground image, according to the pass
Key information is adjusted the special object Body proportion；
Fusion Module, suitable for the foreground image after adjustment and background image are carried out fusion treatment, the image after being handled.
9. a kind of computing device, including：Processor, memory, communication interface and communication bus, the processor, the storage
Device and the communication interface complete mutual communication by the communication bus；
The memory is used to store an at least executable instruction, and the executable instruction makes the processor perform right such as will
Ask the corresponding operation of stature method of adjustment based on view data any one of 1-7.
10. a kind of computer-readable storage medium, an at least executable instruction, the executable instruction are stored with the storage medium
Processor is set to perform the corresponding operation of stature method of adjustment based on view data as any one of claim 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711339119.1A CN107977927A (en) | 2017-12-14 | 2017-12-14 | Stature method of adjustment and device, computing device based on view data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711339119.1A CN107977927A (en) | 2017-12-14 | 2017-12-14 | Stature method of adjustment and device, computing device based on view data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107977927A true CN107977927A (en) | 2018-05-01 |
Family
ID=62006455
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711339119.1A Pending CN107977927A (en) | 2017-12-14 | 2017-12-14 | Stature method of adjustment and device, computing device based on view data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107977927A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108830782A (en) * | 2018-05-29 | 2018-11-16 | 北京字节跳动网络技术有限公司 | Image processing method, device, computer equipment and storage medium |
| CN108830783A (en) * | 2018-05-31 | 2018-11-16 | 北京市商汤科技开发有限公司 | A kind of image processing method, device and computer storage medium |
| CN109191414A (en) * | 2018-08-21 | 2019-01-11 | 北京旷视科技有限公司 | A kind of image processing method, device, electronic equipment and storage medium |
| CN109191552A (en) * | 2018-08-16 | 2019-01-11 | Oppo广东移动通信有限公司 | Threedimensional model processing method, device, electronic equipment and storage medium |
| CN109658355A (en) * | 2018-12-19 | 2019-04-19 | 维沃移动通信有限公司 | A kind of image processing method and device |
| CN110852933A (en) * | 2018-08-21 | 2020-02-28 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, image processing device, and storage medium |
| CN110852943A (en) * | 2018-08-21 | 2020-02-28 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, image processing device, and storage medium |
| CN111091507A (en) * | 2019-12-09 | 2020-05-01 | Oppo广东移动通信有限公司 | Image processing method, image processing apparatus, electronic device, and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101478629A (en) * | 2008-01-04 | 2009-07-08 | 华晶科技股份有限公司 | Image processing process for regulating human face ratio |
| CN103795931A (en) * | 2014-02-20 | 2014-05-14 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN105869116A (en) * | 2016-03-25 | 2016-08-17 | 捷开通讯(深圳)有限公司 | Mobile terminal and photo processing method |
| CN106169172A (en) * | 2016-07-08 | 2016-11-30 | 深圳天珑无线科技有限公司 | A kind of method and system of image procossing |
| CN107392844A (en) * | 2017-07-27 | 2017-11-24 | 三星电子（中国）研发中心 | A kind of method and apparatus for correcting portrait sight |
-
2017
- 2017-12-14 CN CN201711339119.1A patent/CN107977927A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101478629A (en) * | 2008-01-04 | 2009-07-08 | 华晶科技股份有限公司 | Image processing process for regulating human face ratio |
| CN103795931A (en) * | 2014-02-20 | 2014-05-14 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN105869116A (en) * | 2016-03-25 | 2016-08-17 | 捷开通讯(深圳)有限公司 | Mobile terminal and photo processing method |
| CN106169172A (en) * | 2016-07-08 | 2016-11-30 | 深圳天珑无线科技有限公司 | A kind of method and system of image procossing |
| CN107392844A (en) * | 2017-07-27 | 2017-11-24 | 三星电子（中国）研发中心 | A kind of method and apparatus for correcting portrait sight |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108830782A (en) * | 2018-05-29 | 2018-11-16 | 北京字节跳动网络技术有限公司 | Image processing method, device, computer equipment and storage medium |
| CN108830782B (en) * | 2018-05-29 | 2022-08-05 | 北京字节跳动网络技术有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN108830783A (en) * | 2018-05-31 | 2018-11-16 | 北京市商汤科技开发有限公司 | A kind of image processing method, device and computer storage medium |
| CN108830783B (en) * | 2018-05-31 | 2021-07-02 | 北京市商汤科技开发有限公司 | Image processing method and device and computer storage medium |
| US11288796B2 (en) | 2018-05-31 | 2022-03-29 | Beijing Sensetime Technology Development Co., Ltd. | Image processing method, terminal device, and computer storage medium |
| CN109191552A (en) * | 2018-08-16 | 2019-01-11 | Oppo广东移动通信有限公司 | Threedimensional model processing method, device, electronic equipment and storage medium |
| CN109191414A (en) * | 2018-08-21 | 2019-01-11 | 北京旷视科技有限公司 | A kind of image processing method, device, electronic equipment and storage medium |
| CN110852933A (en) * | 2018-08-21 | 2020-02-28 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, image processing device, and storage medium |
| CN110852943A (en) * | 2018-08-21 | 2020-02-28 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, image processing device, and storage medium |
| CN109658355A (en) * | 2018-12-19 | 2019-04-19 | 维沃移动通信有限公司 | A kind of image processing method and device |
| CN111091507A (en) * | 2019-12-09 | 2020-05-01 | Oppo广东移动通信有限公司 | Image processing method, image processing apparatus, electronic device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107977927A (en) | Stature method of adjustment and device, computing device based on view data | |
| CN110008817B (en) | Model training method, image processing method, device, electronic equipment and computer readable storage medium | |
| CN108604369B (en) | Method, device and equipment for removing image noise and convolutional neural network | |
| CN107507155B (en) | Video segmentation result edge optimization real-time processing method and device and computing equipment | |
| CN107277615B (en) | Live broadcast stylization processing method and device, computing device and storage medium | |
| CN107862277A (en) | Live dress ornament, which is dressed up, recommends method, apparatus, computing device and storage medium | |
| CN107665482A (en) | Realize the video data real-time processing method and device, computing device of double exposure | |
| CN107820027A (en) | Video personage dresss up method, apparatus, computing device and computer-readable storage medium | |
| CN108111911B (en) | Video data real-time processing method and device based on self-adaptive tracking frame segmentation | |
| CN107613360A (en) | Video data real-time processing method and device, computing device | |
| CN114187624B (en) | Image generation method, device, electronic equipment and storage medium | |
| CN107945188A (en) | Personage based on scene cut dresss up method and device, computing device | |
| CN108109161A (en) | Video data real-time processing method and device based on adaptive threshold fuzziness | |
| CN107610149A (en) | Image segmentation result edge optimization processing method, device and computing device | |
| CN112541867A (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| CN107959798A (en) | Video data real-time processing method and device, computing device | |
| CN107563357A (en) | Live dress ornament based on scene cut, which is dressed up, recommends method, apparatus and computing device | |
| CN107547803A (en) | Video segmentation result edge optimization processing method, device and computing device | |
| CN107766803B (en) | Video character decorating method and device based on scene segmentation and computing equipment | |
| CN107705279A (en) | Realize the view data real-time processing method and device, computing device of double exposure | |
| Puthussery et al. | Wdrn: A wavelet decomposed relightnet for image relighting | |
| CN108171716A (en) | Video personage based on the segmentation of adaptive tracing frame dresss up method and device | |
| CN107743263A (en) | Video data real-time processing method and device, computing device | |
| CN107563962A (en) | Video data real-time processing method and device, computing device | |
| Peng et al. | Mpib: An mpi-based bokeh rendering framework for realistic partial occlusion effects |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180501 |