CN103514593B - Image processing method and device - Google Patents
Image processing method and device Download PDFInfo
- Publication number
- CN103514593B CN103514593B CN201210206750.5A CN201210206750A CN103514593B CN 103514593 B CN103514593 B CN 103514593B CN 201210206750 A CN201210206750 A CN 201210206750A CN 103514593 B CN103514593 B CN 103514593B
- Authority
- CN
- China
- Prior art keywords
- image
- module
- depth
- template
- type
- 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
Landscapes
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
Abstract
The embodiment of the invention discloses a kind of image processing method and devices, can increase the media resource of stereoscopic effect, meet user demand.The present invention implementation include:The first image is obtained, wherein described first image is plane effect image;Described first image is analyzed, analysis result is obtained;When the analysis result shows that described first image is the first kind, described first image is handled using first method, obtains the second image, wherein second image is three-dimensional image;When the analysis result shows that described first image is Second Type, described first image is handled using second method, obtains third image, wherein the third image is three-dimensional image;Wherein, the first method and second method difference.During the embodiment of the present invention is mainly used for image procossing.
Description
Technical field
The present invention relates to multimedia technology field more particularly to a kind of image processing methods and device.
Background technology
With being in fashion for 3D films, stereoscopic effect display technology starts upsurge in the whole world.Although stereoscopic effect shows equipment
Numerous and confused listing, but existing numerous media resources are not all suitable for stereoscopic effect and show equipment, the media resource of stereoscopic effect
It is also very deficient, it cannot be satisfied user demand.
Invention content
A kind of image processing method of the embodiment of the present invention offer and device, can increase the media resource of stereoscopic effect,
Meet user demand.
In order to achieve the above objectives, the embodiment of the present invention adopts the following technical scheme that:
A kind of image processing method, including:
The first image is obtained, wherein described first image is plane effect image;
Described first image is analyzed, analysis result is obtained;
When the analysis result shows that described first image is the first kind, described first is handled using first method
Image obtains the second image, wherein second image is three-dimensional image;
When the analysis result shows that described first image is Second Type, described first is handled using second method
Image obtains third image, wherein the third image is three-dimensional image;
Wherein, the first method and second method difference.
A kind of image processing apparatus, including:
Acquiring unit, for obtaining the first image, wherein described first image is plane effect image;
Analytic unit, the described first image obtained for analyzing the acquiring unit, obtains analysis result;
First processing units, the analysis result for being obtained when analytic unit show that described first image is first
When type, described first image is handled using first method, obtains the second image, wherein second image is stereoscopic effect
Image;
Second processing unit, the analysis result for being obtained when analytic unit show that described first image is second
When type, described first image is handled using second method, obtains third image, wherein the third image is stereoscopic effect
Image;
Wherein, the first method and second method difference.
Image processing method and device provided in an embodiment of the present invention are determined by analyzing existing plane effect image
The type of the plane effect image handles different types of plane effect image in different ways, obtains corresponding vertical
Existing plane effect media resource is rapidly converted into the media resource of stereoscopic effect, has vitalized plane effect by body effect image
Fruit media resource increases stereoscopic effect media resource, and user is allowed conveniently to enjoy the media resource of stereoscopic effect.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of image processing method flow chart in the embodiment of the present invention one;
Fig. 2 is a kind of image processing method schematic diagram in the embodiment of the present invention one;
Fig. 3 is a kind of image processing method flow chart in the embodiment of the present invention two;
Fig. 4 is a kind of image processing method schematic diagram in the embodiment of the present invention two;
Fig. 5 is a kind of image processing method template schematic diagram in the embodiment of the present invention two;
Fig. 6 is a kind of image processing apparatus composition schematic diagram in the embodiment of the present invention three;
Fig. 7 is another image processing apparatus composition schematic diagram in the embodiment of the present invention three.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without creative efforts
Embodiment shall fall within the protection scope of the present invention.
Embodiment 1
The embodiment of the present invention provides a kind of image processing method, as shown in Figure 1, including:
101, the first image is obtained, wherein described first image is plane effect image.
Wherein, the first image of the acquisition can be a whole sheet of planar effect image, can also make from a whole sheet of planar
At least part image obtained in effect image, described first image are still plane effect image.
For example, as shown in Fig. 2, including eight parts in a sheet of planar effect image, described first image can be it
In a part or a multiple parts, such as the part marked as A, C and D in fig. 2 is all the first image.
102, described first image is analyzed, analysis result is obtained.
Wherein, described first image is analyzed, is that analysis passes through in multiple described first images that step 101 obtains respectively
Each first image can obtain the type information of image by analyzing image.First image can be the first kind and second
Type, for example, without the planar effect picture of manual amendment, i.e. natural scene type;The planar effect picture that manual amendment crosses, i.e.,
Artificial scene type.Certainly, the first image can also be third type, for example, natural scene and artificial scene mixed type.
103, when the analysis result shows that described first image is the first kind, handled using first method described in
First image obtains the second image, wherein second image is three-dimensional image.
For example, the first kind can be artificial field scape type, there are a large amount of manual amendments to cross content in artificial scene, make
At the object in the scape of workshop, polynary and pattern is complicated, and scene content is random, and the first method processing can be according to people
The feature of workshop scape selects to be suitble to people by analyzing color contrast, luminance contrast, the Texture complication etc. of artificial scene
The template of workshop scape, applies mechanically template and plane artificial field scape is converted to stereoscopic artificial scene, and obtained stereoscopic artificial scene is
Second image.
104, when the analysis result shows that described first image is Second Type, handled using second method described in
First image obtains third image, wherein the third image is three-dimensional image.
For example, the Second Type can be natural scene type, the object of natural scene is single, and style is simple, described
Second method processing can obtain depth prediction rule by concluding the level of natural scene, contrast, the feature of style, press
Depth prediction is carried out according to depth prediction rule to natural scene to be converted to plane natural scene according to the depth information of prediction
Stereo natural scene, obtained stereo natural scene are the third image.
Wherein, the first method and second method difference.The first method is adopted for first kind image
First processing mode, the second method are the second processing modes used for Second Type image.
Image processing method provided in an embodiment of the present invention is determined described flat by analyzing existing plane effect image
The type of face effect image handles different types of plane effect image, obtains corresponding stereoscopic effect in different ways
Image makes existing plane effect media resource be rapidly converted into the media resource of stereoscopic effect, increases stereoscopic effect media
Resource allows user conveniently to enjoy the media resource of stereoscopic effect.
Embodiment two
The embodiment of the present invention provides a kind of image processing method, as shown in figure 3, including:
201, initial pictures are obtained, wherein the initial pictures are plane effect images.
Wherein, the initial pictures can be provided by existing plane effect media resource, and picture material can be
Any kind, such as natural land, cartoon animation, propagating poster, personal portrait, background image, subtitle, recording cover etc., institute
It includes the plane effect graph type crossed with manual amendment without the plane effect graph type of manual amendment to state initial pictures.It obtains
Initial pictures can obtain plane effect image to be treated from existing plane effect media resource.
202, according to the initial pictures, determine the first image, wherein described first image be the initial pictures extremely
A few part.
Wherein, according to the initial pictures, determine the first image, can be the initial pictures that obtain step 201 according to
The complexity of image determines the divided part number of initial pictures, then initial pictures is divided into different parts, part
Quantity can be more than or equal to 1, image is more complicated, and the part number of division can be more, for example, division methods can be according to just
The length and width of beginning image, uniformly divides initial pictures.Initial pictures are completed after dividing, have obtained multiple described first
Image selects any of which part, is determined as the first image, can be carried out once selecting to each section, then divide
It analyses its type and carries out respective handling.
For example, as shown in figure 4, initial pictures are the propagating posters of a width cartoon animation, there is four positions in propagating poster
Cartoon figure, and the background of propagating poster is natural land, also has publicity literature in propagating poster.This width initial pictures is very multiple
It is miscellaneous, 12 parts can be divided into, then according to the length and width of initial pictures, initial pictures are uniformly drawn
Point, as shown in phantom in Figure 4.After having divided, each section is selected successively, is determined as the first image.
203, the types value of described first image is calculated.
Wherein, the types value includes following at least one factor:Color contrast, overall brightness contrast, part are bright
Spend contrast, character zone size and Texture complication etc..By step 202, it is determined that described first image, by first
Color contrast, overall brightness contrast, local luminance contrast, character zone and these features of Texture complication of image into
Row analysis, calculates the types value of image.Wherein, the types value can be a percentage.
For example, described first image can include multiple color, the contrast between color is judged, according to color contrast
Power, obtain color contrast angle value, the color contrast angle value is percentage.It can also be according to the overall brightness of the first image
The distribution situation of contrast, obtains overall brightness contrast value, or the local luminance contrast according to the first image distribution
Situation obtains local luminance contrast value, or according to the character distribution situation of the first image, obtains character Distribution Value, or
According to the grain distribution situation of the first image, grain distribution value is obtained.By the color contrast angle value of acquisition, overall brightness pair
Than angle value, local luminance contrast value, character Distribution Value, grain distribution value are added, and are then averaged again, are obtained described first
The types value of image.
204, the type of described first image is determined according to the types value and preset type threshold value.
Wherein, the preset type threshold value can be set by emulation, experience and actual needs.
In a kind of application scenarios of the embodiment of the present invention, two threshold values can be set, are first kind threshold value, Second Type threshold respectively
Value, wherein first kind threshold value are more than Second Type threshold value.When the types value being calculated in step 203 is more than the first kind
When type threshold value, determine that described first image is the first kind.When the types value is less than Second Type threshold value, described the is determined
One image is Second Type.When the types value is between first kind threshold value and Second Type threshold value, described first is determined
Image is third type.In another application scenarios of the embodiment of the present invention, a decision threshold can be set, when the class
When offset is greater than or equal to the decision threshold, determine that described first image is the first kind, when the types value is less than third
Type threshold value determines that described first image is Second Type.The type threshold value can be percentage.
For example, the types value that the first image is calculated in step 203 is 80%.To the first application scenarios, preset
First kind threshold value can be 95%, preset Second Type threshold value can be more than 5% and be less than due to 80% with 5%
95%, types value judges that the first image is third type between first kind threshold value and Second Type threshold value.To second
Kind applicable cases, preset third type threshold value can be 50%, and 80% is more than 50%, judge that the first image is the second class
Type.
It should be noted that by step 201-204, the type of described first image can be distinguished.According to the first figure
The concrete type of picture is respectively handled described first image with different modes.When described first image is the first kind
When, described first image is handled using the first processing mode, first processing mode is as described in step 205-208:
205, corresponding first template is selected according to the characteristics of image of described first image.
Wherein, first template is preset three-dimensional effect diagram template, can preset multiple and different types
Three-dimensional effect diagram template, have the parameter of image, such as image depth values in stereoscopic effect template.For example, as shown in figure 5, Fig. 5
(a)For plane template, Fig. 5(b)To tilt template.For other template types that the present invention does not enumerate, it is also included in this
In the first template in the bright embodiment of method.The feature according to described first image selectes corresponding first template, Ke Yishi
According to the color contrast of the first image, overall brightness contrast, local luminance contrast, character zone and Texture complication this
A little features select corresponding template.For example, the first image is a width subtitle, only there are two types of color in image, background color is black
Color, subtitle color are white, analyze that the first color of image contrast is strong, and overall brightness is bright, and character zone is more, and texture is simple,
It is possible thereby to judge that the first figure line is subtitling image, subtitling image need not distinguish front and back scape, level list in a sub-picture
One, so selecting plane template as the corresponding templates of the first image.
206, first template generation, at least two first depth image is applied mechanically.
Wherein, described to apply mechanically first template generation, at least two first depth image, be by described first image by
According to the form for the first template selected by step 205, the first depth image is generated.First depth image can be more
It is a, the visual pattern of different angle, such as front, rear, left and right etc. are corresponded to respectively.The templating species of selection are different, the depth of generation
The quantity of image also can be different.
207, it is the second image by described at least two first range image integrations.
Wherein, second image is three-dimensional image.It is described to be by described at least two first range image integrations
Second image can be that the depth image is read in existing stereoscopic effect after obtaining the first depth image by step 206
It shows in equipment, stereoscopic effect shows that equipment synthesizes the depth map of different angle, and plane effect image is made to have stereoscopic display
Effect obtains second image with stereoscopic effect.
Further, before step 206 applies mechanically first template generation, at least two first depth image, the side
Method further includes:
208, parameter adjustment is carried out to the first selected template according to the characteristics of image of described first image.
Wherein, first template is selected by step 205, includes image parameter in first template, such as scheme
As depth value.Image depth values can control image between vision at a distance from, make visually to experience image distance viewer close
Or it is remote.In a template, image parameter has been set a standard value, but can do appropriate tune to parameter according to the demand of user
It is whole.For example, in plane template, picture depth can be increased, be that image is in background, the small depth of figure can also be reduced, make figure
As being in foreground.
It is corresponding, parameter adjustment is carried out to the first selected masterplate according to step 208, then is applied mechanically described in step 206
First template can be the first template after applying mechanically adjusting parameter.
It should be noted that step 208 be optional step, select the first template after, can not also to first template into
Row parameter adjustment, does not execute step 208.
Further, when described first image is Second Type image, described first is handled using second processing mode
Types of image, the second processing mode is as described in step 209-210:
209, depth prediction is carried out to described first image according to preset depth prediction rule, generates at least two second
Depth image.
It wherein, can be to the level of the first image, contrast, formula since the image of Second Type has apparent rule
The characteristics such as sample are analyzed, and summarize the depth prediction rule, the depth prediction rule is applied to plane effect image
In, the foreground, medium shot and background depth of plane effect image can be obtained.It is described that depth prediction is carried out to described first image,
Can be by analyzing the level of described first image, contrast, style, select to be suitble to the foreground of described first image, medium shot,
Background depth does first figure translation of different depth then according to depth information, obtains at least two second depth
Image.
210, it is third image by described at least two second range image integrations.
Wherein, the third image is three-dimensional image.It is described to be by described at least two second range image integrations
Third image can be that the depth image is read in existing stereoscopic effect after obtaining the second depth image by step 209
It shows in equipment, stereoscopic effect shows that equipment synthesizes the depth map of different angle, and plane effect image is made to have stereoscopic display
Effect obtains the third image with stereoscopic effect.
Further, it is nor close to Second Type figure since described first image may both keep off first kind image
Described first image can be determined as by picture in order to make described first image obtain the better three-dimensional image of display effect
Third type handles described first image using the processing method as described in step 211-212:
211, when the analysis result shows that described first image is third type, then be respectively adopted first method and
Second method handles described first image, obtains the second image and third image.
Wherein, described that first method and second method processing described first image, first processing mode is respectively adopted
Referring to step 205-208, the second processing mode no longer repeats one by one herein such as referring to 209-210.
212, second image and third image are synthesized, obtains the 4th image, wherein the 4th image is three-dimensional
Effect image.
Wherein, the 4th image is that the second image that will be obtained by step 205-208 is obtained with by step 209-210
The third image synthesis arrived.For example, the synthetic method can be by the types value of described first image and preset centre
Boundary value(Intermediate boundary value is a percentage, and if desired the 4th image is more biased to the second image, could be provided as than 50%
Big number, if desired the 4th image deviation third image, can be arranged intermediate boundary value as the number smaller than 50%)Subtract each other to obtain difference
Value subtracts centre if the types value of described first image is more than preset intermediate boundary value with the types value of described first image
Boundary value, by quotient that obtained difference divided by intermediate boundary are worth to multiplied by be absolutely second image described
Shared ratio in 4th image, third image proportion in the 4th image are 1 to subtract second image the
Shared ratio in four images.If the types value of described first image is less than preset intermediate boundary value, subtracted with intermediate boundary value
The types value for going described first image, the quotient that obtained difference divided by intermediate boundary are worth to is multiplied by be absolutely institute
Third image ratio shared in the 4th image is stated, second image proportion in the 4th image subtracts for 1
Third image ratio shared in the 4th image.If the types value of described first image is equal to intermediate boundary value, institute
It is respectively 50% that the second image, which is stated, with third image proportion in the 4th image.
For example, the types value of the first image is 80%, if intermediate boundary value is 50%, 80% is more than 50%, and 80%, which subtracts 50%, obtains
To 30%, 30% divided by 50%, 60% is obtained, by the second image and third image according to 6:4 ratio synthesis, obtains the 4th image.
It should be noted that by step 203-212, the synthesis of the first image is completed, described first image can wrap
Containing multiple, the described first image determined by step 202 is handled according to the method described in step 203-212 successively,
Obtain multiple second images, third image and the 4th image.The multiple second image, third image and the 4th image be all from
It is obtained in one width initial pictures, by the multiple second image, third image and the 4th image according to described first image first
Position grouping in beginning image is at a complete three-dimensional image.
Image processing method provided in an embodiment of the present invention is determined described flat by analyzing existing plane effect image
The type of face effect image handles different types of plane effect image, obtains corresponding stereoscopic effect in different ways
Image makes existing plane effect media resource be rapidly converted into the media resource of stereoscopic effect, increases stereoscopic effect media
Resource allows user conveniently to enjoy the media resource of stereoscopic effect.
Also, it is handled by the way that existing planar effect picture is divided into multiple portions, determines that a wherein at least part is
Described first image determines the type of the first image by analysis, uses to different types of first image and is handled without mode
Three-dimensional image is obtained, the processing procedure to plane effect image is refined, improves the display of the three-dimensional image of acquisition
Effect promotes user experience.
Embodiment 3
The embodiment of the present invention provides a kind of image processing apparatus, as shown in fig. 6, including:Acquiring unit 31, analytic unit
32, first processing units 33, second processing unit 34.
Acquiring unit 31, for obtaining the first image, wherein described first image is plane effect image.
Analytic unit 32, the described first image for analyzing the acquisition of the acquiring unit 31 obtain analysis result.
First processing units 33, for showing that described first image is when the analysis result of the single 32 yuan of acquisitions of analysis
When the first kind, described first image is handled using first method, obtains the second image, wherein second image is three-dimensional
Effect image.
Second processing unit 34, the analysis result for obtaining 32 when analytic unit show that described first image is
When Second Type, described first image is handled using second method, obtains third image, wherein the third image is three-dimensional
Effect image.
Wherein, the first method and second method difference.
Further, as shown in fig. 7, the acquiring unit 31 may include:First acquisition module 311, second obtains mould
Block 312.
First acquisition module 311, for obtaining initial pictures, wherein the initial pictures are plane effect images.
Second acquisition module 312 determines for the initial pictures that are obtained according to first acquisition module 311
One image, wherein described first image is at least part of the initial pictures.
Further, the analytic unit 32 may include:Computing module 321, judgment module 322.
Computing module 321, the types value for calculating described first image.
Judgment module 322, the type for being calculated according to preset type threshold value and the computing module 321
Value determines the type of described first image.
Further, the first processing units 33 may include:Stencil-chosen module 331, the first depth map module
332, the first synthesis module 333.
Stencil-chosen module 331, for selecting corresponding first template according to the characteristics of image of described first image.
First depth map module 332, for applying mechanically selected first template generation of the stencil-chosen module 331 extremely
Few two the first depth images.
First synthesis module 333, described at least two first depth images for generating the first depth map module 332
Synthesize the second image.
Further, the first processing units 33 can also include:Parameter adjustment module 334.
Parameter adjustment module 334, for what is selected to stencil-chosen module 331 according to the characteristics of image of described first image
First template carries out parameter adjustment.
Corresponding, first depth map module 332 is additionally operable to:It applies mechanically and obtains after parameter adjustment module X adjusting parameters
First template generation, at least two first depth image.
Further, the second processing unit 34 may include:Second depth map module 341, the second synthesis module
342。
Second depth map module 341, it is pre- for carrying out depth to described first image according to preset depth prediction rule
It surveys, generates at least two second depth images.
Second synthesis module 342, described at least two second depth for generating second depth map module 341
Image synthesizes third image.
Further, which can also be to include:Third processing unit 35, third synthesis unit 36.
Third processing unit 35, the analysis result for being obtained when the analytic unit 32 show first figure
When seeming third type, first method and second method processing described first image is respectively adopted, obtains the second image and third
Image.
Synthesis unit 36, the second image for obtaining the third processing unit 35 and the synthesis of third image, obtain
4th image, wherein the 4th image is three-dimensional image.
Image processing apparatus provided in an embodiment of the present invention is determined described flat by analyzing existing plane effect image
The type of face effect image handles different types of plane effect image, obtains corresponding stereoscopic effect in different ways
Image makes existing plane effect media resource be rapidly converted into the media resource of stereoscopic effect, increases stereoscopic effect media
Resource allows user conveniently to enjoy the media resource of stereoscopic effect.
Also, it is handled by the way that existing planar effect picture is divided into multiple portions, determines that each section is institute respectively
The first image is stated, the type of the first image is determined by analysis, different types of first image is used and is handled without mode
To multiple second images, third image and the 4th image, the multiple second image, third image and the 4th image are combined into
One complete three-dimensional image refines the processing procedure to plane effect image, improves the three-dimensional image of acquisition
Display effect, promoted user experience.
Through the above description of the embodiments, it is apparent to those skilled in the art that the present invention can borrow
Help software that the mode of required common hardware is added to realize, naturally it is also possible to which by hardware, but the former is more preferably in many cases
Embodiment.Based on this understanding, the portion that technical scheme of the present invention substantially in other words contributes to the prior art
Dividing can be expressed in the form of software products, which is stored in the storage medium that can be read, and such as count
The floppy disk of calculation machine, hard disk or CD etc., including some instructions are used so that a computer equipment(Can be personal computer,
Server or the network equipment etc.)Execute the method described in each embodiment of the present invention.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (16)
1. a kind of image processing method, which is characterized in that including:
The first image is obtained, wherein described first image is plane effect image;
Described first image is analyzed, analysis result is obtained;
When the analysis result shows that described first image is the first kind, described first image is handled using first method,
Obtain the second image, wherein second image is three-dimensional image;
When the analysis result shows that described first image is Second Type, described first image is handled using second method,
Obtain third image, wherein the third image is three-dimensional image;
Wherein, the first method and second method difference.
2. image processing method according to claim 1, which is characterized in that the first image of the acquisition, including:
Initial pictures are obtained, wherein the initial pictures are plane effect images;
According to the initial pictures, the first image is determined, wherein described first image is at least one of the initial pictures
Point.
3. image processing method according to claim 1, which is characterized in that the analysis described first image is divided
Analysis is as a result, include:
Calculate the types value of described first image;
The type of described first image is determined according to the types value and preset type threshold value.
4. image processing method according to claim 3, which is characterized in that the types value include it is following it is at least one because
Element:Color contrast, overall brightness contrast, local luminance contrast, character zone size and Texture complication.
5. image processing method according to claim 1 or 2, which is characterized in that described using described in first method processing
First image obtains the second image, including:
Corresponding first template is selected according to the characteristics of image of described first image;
Apply mechanically first template generation, at least two first depth image;
It is the second image by described at least two first range image integrations.
6. image processing method according to claim 5, which is characterized in that deep applying mechanically first template generation first
It spends before image, further includes:
Parameter adjustment is carried out to the first selected template according to the characteristics of image of described first image;
It is corresponding, it is described to apply mechanically first template and be:Apply mechanically the first template after adjusting parameter.
7. image processing method according to claim 1 or 2, which is characterized in that described using described in second method processing
First image obtains third image, including:
Depth prediction is carried out to described first image according to preset depth prediction rule, generates at least two second depth maps
Picture;
It is third image by described at least two second range image integrations.
8. image processing method according to claim 1 or 2, which is characterized in that further include:
When the analysis result shows that described first image is third type, then first method and second method is respectively adopted
Described first image is handled, the second image and third image are obtained;
Second image and third image are synthesized, obtain the 4th image, wherein the 4th image is three-dimensional effect diagram
Picture.
9. a kind of image processing apparatus, which is characterized in that including:
Acquiring unit, for obtaining the first image, wherein described first image is plane effect image;
Analytic unit, the described first image obtained for analyzing the acquiring unit, obtains analysis result;
First processing units, the analysis result for being obtained when analytic unit show that described first image is the first kind
When, described first image is handled using first method, obtains the second image, wherein second image is three-dimensional image;
Second processing unit, the analysis result for being obtained when analytic unit show that described first image is Second Type
When, described first image is handled using second method, obtains third image, wherein the third image is three-dimensional image;
Wherein, the first method and second method difference.
10. image processing apparatus according to claim 9, which is characterized in that the acquiring unit includes:
First acquisition module, for obtaining initial pictures, wherein the initial pictures are plane effect images;
Second acquisition module, the initial pictures for being obtained according to first acquisition module, determines the first image,
In, described first image is at least part of the initial pictures.
11. image processing apparatus according to claim 9, which is characterized in that the analytic unit includes:
Computing module, the types value for calculating described first image;
Judgment module, described in being determined according to the types value of preset type threshold value and computing module calculating
The type of first image.
12. image processing apparatus according to claim 11, which is characterized in that the types value includes following at least one
Factor:Color contrast, overall brightness contrast, local luminance contrast, character zone size and Texture complication.
13. image processing apparatus according to claim 9 or 10, which is characterized in that the first processing units include:
Stencil-chosen module, for selecting corresponding first template according to the characteristics of image of described first image;
First depth map module, first template generation at least two first selected for applying mechanically the stencil-chosen module
Depth image;
First synthesis module, described at least two first range image integrations for generating the first depth map module are second
Image.
14. image processing apparatus according to claim 13, which is characterized in that the first processing units further include:
Parameter adjustment module, the first template for being selected to stencil-chosen module according to the characteristics of image of described first image into
Row parameter adjustment;
Corresponding, first depth map module is additionally operable to:Apply mechanically obtain after the parameter adjustment module adjusting parameter it is described
First template generation, at least two first depth image.
15. image processing apparatus according to claim 9 or 10, which is characterized in that the second processing unit includes;
Second depth map module is generated for carrying out depth prediction to described first image according to preset depth prediction rule
At least two second depth images;
Second synthesis module, described at least two second range image integrations for generating second depth map module are
Third image.
16. image processing apparatus according to claim 9 or 10, which is characterized in that further include:
Third processing unit, the analysis result for being obtained when the analytic unit show that described first image is third
When type, first method and second method processing described first image is respectively adopted, obtains the second image and third image;
Synthesis unit, second image for obtaining the third processing unit and third image synthesis, obtain
4th image, wherein the 4th image is three-dimensional image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210206750.5A CN103514593B (en) | 2012-06-18 | 2012-06-18 | Image processing method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210206750.5A CN103514593B (en) | 2012-06-18 | 2012-06-18 | Image processing method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103514593A CN103514593A (en) | 2014-01-15 |
CN103514593B true CN103514593B (en) | 2018-10-12 |
Family
ID=49897271
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210206750.5A Active CN103514593B (en) | 2012-06-18 | 2012-06-18 | Image processing method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103514593B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102327779B1 (en) | 2014-02-21 | 2021-11-18 | 삼성전자주식회사 | Method for processing image data and apparatus for the same |
CN108683826B (en) * | 2018-05-15 | 2021-12-14 | 腾讯科技(深圳)有限公司 | Video data processing method, video data processing device, computer equipment and storage medium |
CN111729314B (en) * | 2020-06-30 | 2024-06-21 | 网易(杭州)网络有限公司 | Virtual character face pinching processing method and device and readable storage medium |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011160306A (en) * | 2010-02-03 | 2011-08-18 | Casio Computer Co Ltd | Device, program, and method for processing image |
-
2012
- 2012-06-18 CN CN201210206750.5A patent/CN103514593B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN103514593A (en) | 2014-01-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wright | Digital compositing for film and vídeo: Production Workflows and Techniques | |
EP2306745B1 (en) | Method and system for creating depth and volume in a 2-D planar image | |
US8351689B2 (en) | Apparatus and method for removing ink lines and segmentation of color regions of a 2-D image for converting 2-D images into stereoscopic 3-D images | |
RU2692432C2 (en) | Method and apparatus for three-dimensional image forming | |
EP2323416A2 (en) | Stereoscopic editing for video production, post-production and display adaptation | |
WO2021135320A1 (en) | Video generation method and apparatus, and computer system | |
JP2005151534A (en) | Pseudo three-dimensional image creation device and method, and pseudo three-dimensional image display system | |
JP2007264722A (en) | Image processor | |
US10277877B2 (en) | 3D system including a neural network | |
CN102480626A (en) | Image processing apparatus, display apparatus and image processing program | |
US20090262125A1 (en) | Rendering A Multiple Viewpoint Image Into A Single Frame Buffer Using Off-Screen Rendering Surfaces | |
CN112446939A (en) | Three-dimensional model dynamic rendering method and device, electronic equipment and storage medium | |
CN103514593B (en) | Image processing method and device | |
Liu et al. | Arbitrary view generation based on DIBR | |
CN111951369B (en) | Detail texture processing method and device | |
WO2015186284A1 (en) | Image processing device, image processing method, and program | |
CN113546410A (en) | Terrain model rendering method and device, electronic equipment and storage medium | |
KR102091860B1 (en) | Method and apparatus for image encoding | |
JP2006185033A (en) | Pseudo three-dimensional image generating device, pseudo three-dimensional image generating program, and pseudo three-dimensional image display system | |
JP2013172214A (en) | Image processing device and image processing method and program | |
JP7387029B2 (en) | Single-image 3D photography technology using soft layering and depth-aware inpainting | |
CN113658064A (en) | Texture image generation method and device and electronic equipment | |
DE10250602A1 (en) | Synthetic scene generation method, involves generating direction dependent texture map based on data representing base images and generating scene in accordance to texture map | |
JP5254297B2 (en) | Image processing device | |
JP5515864B2 (en) | Image processing method, image processing apparatus, and image processing program |
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 |