CN109472763A - A kind of image synthetic method and device - Google Patents
A kind of image synthetic method and device Download PDFInfo
- Publication number
- CN109472763A CN109472763A CN201710801070.0A CN201710801070A CN109472763A CN 109472763 A CN109472763 A CN 109472763A CN 201710801070 A CN201710801070 A CN 201710801070A CN 109472763 A CN109472763 A CN 109472763A
- Authority
- CN
- China
- Prior art keywords
- pixel
- mixed
- neighborhood
- valid
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010189 synthetic method Methods 0.000 title claims abstract description 12
- 239000011159 matrix material Substances 0.000 claims abstract description 55
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 22
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 22
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 13
- 239000003086 colorant Substances 0.000 claims description 34
- 238000000034 method Methods 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 14
- 239000000203 mixture Substances 0.000 claims description 8
- 239000012141 concentrate Substances 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002845 discoloration Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
A kind of image synthetic method, comprising: the neighborhood for determining pixel to be mixed in image to be synthesized respectively determines neighborhood candidate pixel collection from the neighborhood；The valid pixel that the neighborhood candidate pixel is concentrated is analyzed, the valid pixel and the pixel to be mixed are determined as valid pixel collection；The corresponding coefficient of efficiency matrix of neighborhood territory pixel collection of the corresponding effective determining pixel to be mixed of mark of element is concentrated according to the valid pixel；Effective mixed number of the pixel to be mixed is obtained according to the valid pixel collection and the coefficient of efficiency matrix；Synthesis processing is carried out according to the image to be synthesized of effective mixed number of the pixel to be mixed of each image to be synthesized and mixed mode algorithm pair.A kind of device of image synthesis.This programme may be implemented to mix particular image, and flexibility ratio is high, using wide.
Description
Technical field
The present invention relates to technical field of image processing, and in particular to a kind of image synthetic method and device.
Background technique
Color between image and image can be combined together by mixed mode, to create multi-effect.Hybrid guided mode
Formula is very widely used in technical field of image processing, such as drawing tool, editor's adjustment tool, can apply mixed mode
Two width of aliasing or multiple image are carried out, then is effectively and flexibly using mixing, but image is dazzling colorful.
It is unfailing research heat based on image composition method with the deep development and application of image processing techniques
Point.Poisson described in the relevant technologies mixes under certain conditions, and the gradient of original image is maintained due to excessively imposing, causes to generate
Colour-change phenomena and the unsmooth phenomenon of mixed edge.The relevant technologies are also based on further expanding on the basis of Poisson mixing, to solve
Discoloration and the unsmooth phenomenon of mixed edge.But above-mentioned image blend is only that the rule followed based on most of image is mixed
It is folded, it is directed to special image and is mixed, lack flexibility ratio and extensive use property.
Summary of the invention
The embodiment of the present invention provides a kind of image synthetic method and device, is mixed with realizing to particular image.
A kind of image synthetic method, comprising:
The neighborhood for determining pixel to be mixed in image to be synthesized respectively determines neighborhood candidate pixel collection from the neighborhood；
The valid pixel that the neighborhood candidate pixel is concentrated is analyzed, the valid pixel and the pixel to be mixed are determined
For valid pixel collection；
The neighborhood territory pixel collection of the corresponding effective determining pixel to be mixed of mark of element is concentrated according to the valid pixel
Corresponding coefficient of efficiency matrix；
Effective mixed number of the pixel to be mixed is obtained according to the valid pixel collection and the coefficient of efficiency matrix；
According to effective mixed number of the pixel to be mixed of each image to be synthesized and mixed mode algorithm pair to
Composograph carries out synthesis processing.
Optionally, the neighborhood candidate pixel collection include in the neighborhood of the pixel to be mixed in addition to the pixel to be mixed
All pixels, the neighborhood territory pixel collection includes that the neighborhood candidate pixel concentrates all pixels and the pixel to be mixed.
Optionally, the valid pixel that the analysis neighborhood candidate pixel is concentrated, comprising:
Analyze whether each pixel that the neighborhood candidate pixel is concentrated has according to the coefficient matrix of the neighborhood territory pixel collection
Effect；
The valid pixel that the neighborhood candidate pixel is concentrated is determined according to each channel threshold value of three primary colours.
Optionally, the valid pixel for determining that the neighborhood candidate pixel is concentrated according to each channel threshold value of three primary colours,
Include:
Determine that three primary colours are each according to each channel value of the corresponding three primary colours of the pixel to be mixed and each channel threshold value of three primary colours
The valid interval of channel value；
If each channel value of the corresponding three primary colours of pixel that the neighborhood candidate pixel is concentrated in corresponding valid interval,
Determine that the pixel is valid pixel.
Optionally, described that having for the pixel to be mixed is obtained according to the valid pixel collection and the coefficient of efficiency matrix
Imitate mixed number, comprising:
The coefficient of all elements and its corresponding coefficient of efficiency matrix is concentrated to be weighted according to the valid pixel
Averagely obtain effective mixed number of the pixel to be mixed.
Optionally, the mixed mode algorithm are as follows:
Pout=P "1×α+P″2× (255- α), wherein
PoutTo be being exported after image blend as a result, P "1It is mixed for the effective of the pixel to be mixed of the first image to be synthesized
Conjunction value, P "2For effective mixed number of the pixel to be mixed of the second image to be synthesized, α is coefficient of transparency.
A kind of device of image synthesis, wherein include:
First determining module, for determining the neighborhood of pixel to be mixed in image to be synthesized respectively, from the neighborhood really
Determine neighborhood candidate pixel collection；
Analysis module, the valid pixel concentrated for analyzing the neighborhood candidate pixel, by the valid pixel and described
Pixel to be mixed is determined as valid pixel collection；
Second determining module, for concentrating the corresponding effective mark determination of element described to be mixed according to the valid pixel
The corresponding coefficient of efficiency matrix of the neighborhood territory pixel collection of pixel；
Module is obtained, for obtaining the pixel to be mixed according to the valid pixel collection and the coefficient of efficiency matrix
Effective mixed number；
Synthesis module, for being calculated according to the effective mixed number and mixed mode of the pixel to be mixed of each image to be synthesized
The image to be synthesized of method pair carries out synthesis processing.
Optionally, the neighborhood candidate pixel collection include in the neighborhood of the pixel to be mixed in addition to the pixel to be mixed
All pixels, the neighborhood territory pixel collection includes that the neighborhood candidate pixel concentrates all pixels and the pixel to be mixed.
Optionally, the analysis module analyzes the valid pixel that the neighborhood candidate pixel is concentrated, comprising: according to described
Whether the coefficient matrix of neighborhood territory pixel collection analyzes each pixel that the neighborhood candidate pixel is concentrated effective；It is each logical according to three primary colours
Road threshold value determines the valid pixel that the neighborhood candidate pixel is concentrated.
Optionally, the analysis module determines what the neighborhood candidate pixel was concentrated according to each channel threshold value of three primary colours
Valid pixel, comprising: determine three according to each channel value of the corresponding three primary colours of the pixel to be mixed and each channel threshold value of three primary colours
The valid interval of each channel value of primary colours；If each channel value of the corresponding three primary colours of pixel that the neighborhood candidate pixel is concentrated is in correspondence
Valid interval in, it is determined that the pixel be valid pixel.
Optionally, the acquisition module obtains described to mixed according to the valid pixel collection and the coefficient of efficiency matrix
Close effective mixed number of pixel, comprising: all elements and its corresponding coefficient of efficiency square are concentrated according to the valid pixel
The coefficient of battle array is weighted and averaged the effective mixed number for obtaining the pixel to be mixed.
Optionally, the synthesis module, according to mixed mode algorithm are as follows: Pout=P "1×α+P″2× (255- α),
In, PoutTo be being exported after image blend as a result, P "1For effective mixed number of the pixel to be mixed of the first image to be synthesized,
P″2For effective mixed number of the pixel to be mixed of the second image to be synthesized, α is coefficient of transparency.
The device of a kind of image synthesis, comprising: memory, processor and storage can transport on a memory and on a processor
Capable computer program, wherein the processor performs the steps of when executing described program
The neighborhood for determining pixel to be mixed in image to be synthesized respectively determines neighborhood candidate pixel collection from the neighborhood；
The valid pixel that the neighborhood candidate pixel is concentrated is analyzed, the valid pixel and the pixel to be mixed are determined
For valid pixel collection；
The neighborhood territory pixel collection of the corresponding effective determining pixel to be mixed of mark of element is concentrated according to the valid pixel
Corresponding coefficient of efficiency matrix；
Effective mixed number of the pixel to be mixed is obtained according to the valid pixel collection and the coefficient of efficiency matrix；
According to effective mixed number of the pixel to be mixed of each image to be synthesized and mixed mode algorithm pair to
Composograph carries out synthesis processing.
To sum up, the embodiment of the present invention provides a kind of image synthetic method and device, may be implemented to carry out particular image
Mixing, flexibility ratio is high, using wide.
Detailed description of the invention
Fig. 1 is a kind of flow chart of image synthetic method of the embodiment of the present invention one；
Fig. 2 is a kind of schematic diagram of image synthetic method of the embodiment of the present invention two；
Fig. 3 is the schematic diagram of the determination contiguous range of the embodiment of the present invention；
Fig. 4 is the schematic diagram for the device that a kind of image of the embodiment of the present invention two synthesizes.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention
Embodiment be described in detail.It should be noted that in the absence of conflict, in the embodiment and embodiment in the application
Feature can mutual any combination.
Embodiment one
Fig. 1 is a kind of flow chart of image synthetic method of the embodiment of the present invention, as shown in Figure 1, the side of the present embodiment
Method the following steps are included:
Step 11, the neighborhood for determining pixel to be mixed in image to be synthesized respectively determine that neighborhood is candidate from the neighborhood
Set of pixels；
The valid pixel that step 12, the analysis neighborhood candidate pixel are concentrated, by the valid pixel and described to be mixed
Pixel is determined as valid pixel collection；
Step 13, the neighborhood that the corresponding effective determining pixel to be mixed of mark of element is concentrated according to the valid pixel
The corresponding coefficient of efficiency matrix of set of pixels；
Step 14 obtains the effective mixed of the pixel to be mixed according to the valid pixel collection and the coefficient of efficiency matrix
Conjunction value；
Step 15, according to effective mixed number of the pixel to be mixed of each image to be synthesized and mixed mode algorithm pair
The image to be synthesized carries out synthesis processing.
The method of the present embodiment overcomes the limitation of the prior art, using pixel region mixing arbitrary sample image, together
When can also overcome the unsmooth phenomenon of metachromatism and edge.Threshold can also be chosen by customized threshold value or according to pixel value
The flexibility ratio of mixing rule can be improved in value, the neighborhood of mixed pixel, neighbour coefficient matrix.
Embodiment two
It is described in detail below with technical solution of the specific embodiment to this embodiment of the present invention.
As shown in Fig. 2, the method for the present embodiment comprises the steps of:
Step 101 determines neighborhood of pixels, based on the coordinate (x, y) of current mixed pixel point P, according to contiguous range parameter
The coordinate of h_l, h_r, v_u, v_d and point P determine N × M neighborhood ε of pixel P.
If current mixed pixel point is P, the coordinate of the pixel is (x, y), its N × M neighborhood ε range of mixed pixel point P
It is to be confirmed by this 4 contiguous range parameters of h_l, h_r, v_u and v_d.
Wherein, h_l indicates the distance of the coordinate x relative neighbo(u)rhood ε left margin of pixel P, and h_r indicates that the coordinate x of pixel P is opposite
The distance of neighborhood ε right margin, v_u indicate the distance of the coboundary coordinate y relative neighbo(u)rhood ε of pixel P, and v_d indicates the coordinate of pixel P
The distance of y relative neighbo(u)rhood ε lower boundary, then the horizontal direction field of mixed pixel point P is [x-h_l, x+h_r], vertical direction neck
Domain be [y-v_u, x+v_d], neighborhood ε, as shown in Figure 3.
Step 102 determines neighborhood candidate pixel collection；
Neighborhood candidate pixel collection be in N × M neighborhood ε of current mixed pixel point P non-P as candidate pixel collection.
The coordinate (x, y) and contiguous range parameter h_l, h_r, v_u of current mixed pixel point P as described in step 101
It can determine the set of pixels S in point P neighborhood ε with v_dε, as shown in table 1.
Table 1
Point P neighborhood ε candidate pixel collection is the set of all pixels of non-P pixel in mixed pixel point P neighborhood ε, and note is based on
Neighborhood candidate pixel integrates as Uε。
Step 103, analysis valid pixel；
By the set of pixels S of pixel P neighborhood εεCoefficient matrix Dp, calculate candidate pixel collection UεIn each pixel it is whether effective,
Then further confirm that whether each pixel is effective in previous step result based on each channel threshold value, then by candidate pixel collection
UεMiddle valid pixel and pixel P constitute the valid pixel collection Γ of P pointε。
If each channel threshold value of three primary colours is Rmin、Rmax、Gmin、Gmax、Bmin、Bmax, mixed pixel P neighborhood ε set of pixels SεSystem
Matrix number is Dp。Rmin、Rmax、Gmin、Gmax、Bmin、Bmax、DpParameter is as point P neighborhood ε candidate pixel collection UεIn each pixel
It whether is effective measurement standard.
Valid pixel analysis can be divided into following steps:
Step 103.1, by set of pixels SεCoefficient matrix is DpCalculate candidate pixel collection UεIn each pixel it is whether effective；
Set of pixels SεCoefficient matrix is DpBe it is known, be not just unfolded to illustrate here.
The width of P neighborhood ε of setting up an office is n, and a height of m can be obtained by step 101:
N=h_l+h_r+1,
M=v_u+v_d+1,
Then there is mixed pixel P neighborhood ε set of pixels SεCorresponding coefficient matrix DpAre as follows:
If using FUMatrix indicates set of pixels UεIn each pixel it is whether effective, FUAre as follows:
In FUIn matrix, current mixed pixel point P coordinate is (x, y) corresponding significant notation flagI, j, (wherein, i=x-
H_l+1, j=y-v_u+1) it is permanent be 1.And candidate pixel collection UεMiddle pixel PI, jCorresponding significant notation is flagI, j, wherein 1≤
I≤n and i ≠ x-h_l+1,1≤j≤m and j ≠ y-v_u+1.Based on candidate pixel collection UεMiddle pixel PI, jCoefficient of correspondence matrix is Dp
Middle dI, j, wherein 1≤i≤n and i ≠ x-h_l+1,1≤j≤m and j ≠ y-v_u+1, if dJ, jIt is 0, then corresponding flagI, j=0.
Step 103.2 is based on each channel threshold calculations candidate pixel collection UεIn each pixel it is whether effective；
If currently the corresponding each channel value of mixing point P is rp、gp、bp, candidate pixel collection UεMiddle pixel PI, jIt is corresponding each logical
Road value is rI, j、gI, j、bI, j, wherein 1≤i≤n and i ≠ x-h_l+1,1≤j≤m and j ≠ y-v_u+1.Then by calculating rp、
gp、bpWith threshold value Rmin, Rmax, Gmin, Gmax, Bmin, BmaxThe valid interval of the value in the channel r is obtained respectivelyThe value in the channel g has
Imitate sectionThe valid interval of the value in the channel b
The valid interval of the value in the channel rThe valid interval of the value in the channel gThe valid interval of the value in the channel b
Step 103.3 is based on the corresponding valid interval of r, g, bBy judging candidate pixel collection
UεMiddle pixel PI, jCorresponding each channel value is rI, j、gI, j、bI, jWhether valid interval is fallen in It further calculates
F in step 103.1UElement flag in matrixI, jWhether value is 0.If PI, jCorresponding flagI, jIt is 1, then PI, jFor effective candidate picture
Element.And current mixed pixel P perseverance is valid pixel, then by PI, jThe valid pixel collection Γ of P point is constituted with pixel Pε。
Step 104 determines mixed pixel P neighborhood ε set of pixels SεCorresponding coefficient of efficiency matrix D "P；
By valid pixel collection Γ in step 103εThe corresponding effective mark of middle element determines set of pixels SεCorresponding coefficient of efficiency
Matrix D "P.Obtained F is confirmed by step 103.2UFlag in matrixI, jValue (1≤i≤n, 1≤j≤m) determines DpWhether each element
Effectively.
If effective coefficient matrix D "PAre as follows:
Then have:
Wherein, 1≤i≤n, 1≤j≤m.
Step 105 determines effective mixed number；
Effective mixed number is valid pixel collection ΓεAll elements and coefficient of correspondence, which are weighted and averaged, obtains mixed pixel point
Effective mixed number of P.
If effective set of pixels ΓεIt is count_num that element, which corresponds to weight summation, and current mixed pixel P point is corresponding effectively
Mixed number is P ", then:
Step 106 carries out image blend, passes through the P of foreground image (src) "srcWith the P " of background image (dst)dstAnd thoroughly
Bright factor alpha carries out image aliasing, and formula is as follows:
Pout=P "src×α+P″dst×(255-α)
Foreground image Neighbourhood parameter hsrcAnd vsrcIt is mixed pixel point PsrcNeighborhood εsrcWidth and height, by currently mixing picture
Vegetarian refreshments PsrcCoordinate (xsrc, ysrc) and contiguous range parameter h_lsrc、h_rsrc、v_usrcAnd v_dsrcMixed pixel is calculated
Point PsrcNeighborhood εsrc.Then mixed pixel point PsrcHorizontal direction field be [xsrc-h_lsrc, xsrc+h_rsrc], vertical direction
Field is [ysrc-v_usrc, ysrc+v_dsrc]。
Background image Neighbourhood parameter hdstAnd vdstIt is mixed pixel point PdstNeighborhood εdstWidth and height, by currently mixing picture
Vegetarian refreshments PdstCoordinate (xdst, ydst) and contiguous range parameter h_ldst、h_rdst、v_udstAnd v_ddstMixed pixel is calculated
Point PdstNeighborhood εdst.Then mixed pixel point PdstHorizontal direction field be [xdst-h_ldst, xdst+h_rdst], vertical direction
Field is [ydst-v_udst, ydst+v_ddst]。
The neighborhood ε of foreground imagesrcIn candidate pixel collection beThe neighborhood ε of background imagedstIn candidate pixel collection
For
Foreground image neighborhood εsrcSet of pixelsCoefficient matrix be denoted asEach channel threshold value of three primary colours is respectivelyRmaxsrc,ByIt determines with each channel threshold value of three primary colours
Determine candidate pixel collectionValid pixel, candidate pixel collectionValid pixel and point PsrcConstitute the effective of foreground image
Set of pixelsSo as to obtain set of pixelsCorresponding coefficient of efficiency matrix
Background image neighborhood candidate pixel collectionCoefficient matrix be denoted asEach channel threshold value of three primary colours is respectivelyByWith each channel threshold of three primary colours
Value determines candidate pixel collectionValid pixel, candidate pixel collectionValid pixel and point PdstConstitute the effective of dst
Set of pixelsSo as to obtain set of pixelsCorresponding coefficient of efficiency matrix
By above-mentioned set of pixelsCorresponding coefficient of efficiency matrixAnd set of pixelsCorresponding coefficient of efficiency
MatrixValid pixel collection can be obtainedIt is sum that element, which corresponds to weight summation,srcWith valid pixel collectionElement is corresponding
Weight summation is sumdst。
Then there is foreground image mixed pixel point PsrcCorresponding effective mixed number is P "srcAre as follows:
Background image mixed pixel point PdstCorresponding effective mixed number is P "dstAre as follows:
Pass through the P of foreground image "srcWith the P of background image "dstAnd factor alpha carries out image aliasing and obtains Pout:
Pout=Psrc×α+P″dst×(255-α)
Using the method for the embodiment of the present invention, compared with prior art, chosen by customized threshold value or according to pixel value
Threshold value, the neighborhood of mixed pixel, neighbour coefficient matrix, it is smooth based on image border, avoid metachromatism from occurring, keep image
Texture while, improve image blend flexibility ratio and be widely applied property.
Fig. 3 is the schematic diagram for the device that a kind of image of the embodiment of the present invention synthesizes, as shown in figure 3, the dress of the present embodiment
It sets and includes:
First determining module, for determining the neighborhood of pixel to be mixed in image to be synthesized respectively, from the neighborhood really
Determine neighborhood candidate pixel collection；
Analysis module, the valid pixel concentrated for analyzing the neighborhood candidate pixel, by the valid pixel and described
Pixel to be mixed is determined as valid pixel collection；
Second determining module, for concentrating the corresponding effective mark determination of element described to be mixed according to the valid pixel
The corresponding coefficient of efficiency matrix of the neighborhood territory pixel collection of pixel；
Module is obtained, for obtaining the pixel to be mixed according to the valid pixel collection and the coefficient of efficiency matrix
Effective mixed number；
Synthesis module, for being calculated according to the effective mixed number and mixed mode of the pixel to be mixed of each image to be synthesized
The image to be synthesized of method pair carries out synthesis processing.
The device of the present embodiment overcomes the limitation of the prior art, using pixel region mixing arbitrary sample image, together
When can also overcome the unsmooth phenomenon of metachromatism and edge.Threshold can also be chosen by customized threshold value or according to pixel value
The flexibility ratio of mixing rule can be improved in value, the neighborhood of mixed pixel, neighbour coefficient matrix.
In one embodiment, the neighborhood candidate pixel collection includes in the neighborhood of the pixel to be mixed except described to be mixed
All pixels outside pixel, the neighborhood territory pixel collection include that the neighborhood candidate pixel concentrates all pixels and the picture to be mixed
Element.
In one embodiment, the analysis module analyzes the valid pixel that the neighborhood candidate pixel is concentrated, comprising: root
It is whether effective that each pixel that the neighborhood candidate pixel is concentrated is analyzed according to the coefficient matrix of the neighborhood territory pixel collection；According to three bases
Each channel threshold value of color determines the valid pixel that the neighborhood candidate pixel is concentrated.
In one embodiment, the analysis module determines the neighborhood candidate pixel according to each channel threshold value of three primary colours
The valid pixel of concentration, comprising: according to each channel value of the corresponding three primary colours of the pixel to be mixed and each channel threshold value of three primary colours
Determine the valid interval of each channel value of three primary colours；If each channel value of the corresponding three primary colours of pixel that the neighborhood candidate pixel is concentrated
In corresponding valid interval, it is determined that the pixel is valid pixel.
In one embodiment, the acquisition module obtains institute according to the valid pixel collection and the coefficient of efficiency matrix
State effective mixed number of pixel to be mixed, comprising: according to the valid pixel concentrate all elements and its it is corresponding it is described effectively
The coefficient of coefficient matrix is weighted and averaged the effective mixed number for obtaining the pixel to be mixed.
In one embodiment, the synthesis module, according to mixed mode algorithm are as follows:
Pout=P "1×α+P″2× (255- α), wherein
PoutTo be being exported after image blend as a result, P "1It is mixed for the effective of the pixel to be mixed of the first image to be synthesized
Conjunction value, P "2For effective mixed number of the pixel to be mixed of the second image to be synthesized, α is coefficient of transparency.
The embodiment of the present invention also provides a kind of device of image synthesis, comprising: memory, processor and is stored in memory
Computer program that is upper and can running on a processor, which is characterized in that the processor is realized following when executing described program
Step:
The neighborhood for determining pixel to be mixed in image to be synthesized respectively determines neighborhood candidate pixel collection from the neighborhood；
The valid pixel that the neighborhood candidate pixel is concentrated is analyzed, the valid pixel and the pixel to be mixed are determined
For valid pixel collection；
The neighborhood territory pixel collection of the corresponding effective determining pixel to be mixed of mark of element is concentrated according to the valid pixel
Corresponding coefficient of efficiency matrix；
Effective mixed number of the pixel to be mixed is obtained according to the valid pixel collection and the coefficient of efficiency matrix；
According to effective mixed number of the pixel to be mixed of each image to be synthesized and mixed mode algorithm pair to
Composograph carries out synthesis processing.
The embodiment of the invention also provides a kind of computer readable storage mediums, are stored with computer executable instructions,
The computer executable instructions, which are performed, realizes described image synthetic method.
Those of ordinary skill in the art will appreciate that all or part of the steps in the above method can be instructed by program
Related hardware is completed, and described program can store in computer readable storage medium, such as read-only memory, disk or CD
Deng.Optionally, one or more integrated circuits can be used also to realize in all or part of the steps of above-described embodiment.Accordingly
Ground, each module/unit in above-described embodiment can take the form of hardware realization, can also use the shape of software function module
Formula is realized.The present invention is not limited to the combinations of the hardware and software of any particular form.
The above is only a preferred embodiment of the present invention, and certainly, the invention may also have other embodiments, without departing substantially from this
In the case where spirit and its essence, those skilled in the art make various corresponding changes in accordance with the present invention
And deformation, but these corresponding changes and modifications all should fall within the scope of protection of the appended claims of the present invention.
Claims (13)
1. a kind of image synthetic method, comprising:
The neighborhood for determining pixel to be mixed in image to be synthesized respectively determines neighborhood candidate pixel collection from the neighborhood；
The valid pixel that the neighborhood candidate pixel is concentrated is analyzed, the valid pixel and the pixel to be mixed are determined as having
Imitate set of pixels；
The corresponding effective mark of element is concentrated to determine that the neighborhood territory pixel collection of the pixel to be mixed is corresponding according to the valid pixel
Coefficient of efficiency matrix；
Effective mixed number of the pixel to be mixed is obtained according to the valid pixel collection and the coefficient of efficiency matrix；
According to the described to be synthesized of effective mixed number of the pixel to be mixed of each image to be synthesized and mixed mode algorithm pair
Image carries out synthesis processing.
2. the method as described in claim 1, it is characterised in that:
The neighborhood candidate pixel collection includes all pixels in the neighborhood of the pixel to be mixed in addition to the pixel to be mixed,
The neighborhood territory pixel collection includes that the neighborhood candidate pixel concentrates all pixels and the pixel to be mixed.
3. the method as described in claim 1, it is characterised in that: effective picture that the analysis neighborhood candidate pixel is concentrated
Element, comprising:
It is whether effective that each pixel that the neighborhood candidate pixel is concentrated is analyzed according to the coefficient matrix of the neighborhood territory pixel collection；
The valid pixel that the neighborhood candidate pixel is concentrated is determined according to each channel threshold value of three primary colours.
4. method as claimed in claim 3, it is characterised in that: described to determine the neighborhood according to each channel threshold value of three primary colours
The valid pixel that candidate pixel is concentrated, comprising:
Each channel of three primary colours is determined according to each channel value of the corresponding three primary colours of the pixel to be mixed and each channel threshold value of three primary colours
The valid interval of value；
If each channel value of the corresponding three primary colours of pixel that the neighborhood candidate pixel is concentrated is in corresponding valid interval, it is determined that
The pixel is valid pixel.
5. the method as described in claim 1, it is characterised in that: described according to the valid pixel collection and the coefficient of efficiency square
Battle array obtains effective mixed number of the pixel to be mixed, comprising:
The coefficient of all elements and its corresponding coefficient of efficiency matrix is concentrated to be weighted and averaged according to the valid pixel
Obtain effective mixed number of the pixel to be mixed.
6. the method as described in claim 1, it is characterised in that: the mixed mode algorithm are as follows:
Pout=P "1×α+P″2× (255- α), wherein
PoutTo be being exported after image blend as a result, P "1For effective mixed number of the pixel to be mixed of the first image to be synthesized,
P″2For effective mixed number of the pixel to be mixed of the second image to be synthesized, α is coefficient of transparency.
7. a kind of device of image synthesis characterized by comprising
First determining module determines adjacent for determining the neighborhood of pixel to be mixed in image to be synthesized respectively from the neighborhood
Domain candidate pixel collection；
Analysis module, the valid pixel concentrated for analyzing the neighborhood candidate pixel, by the valid pixel and described to mixed
It closes pixel and is determined as valid pixel collection；
Second determining module, for concentrating the corresponding effective mark of element to determine the pixel to be mixed according to the valid pixel
The corresponding coefficient of efficiency matrix of neighborhood territory pixel collection；
Module is obtained, for obtaining the effective of the pixel to be mixed according to the valid pixel collection and the coefficient of efficiency matrix
Mixed number；
Synthesis module, for the effective mixed number and mixed mode algorithm pair according to the pixel to be mixed of each image to be synthesized
The image to be synthesized carry out synthesis processing.
8. device as claimed in claim 7, it is characterised in that:
The neighborhood candidate pixel collection includes all pixels in the neighborhood of the pixel to be mixed in addition to the pixel to be mixed,
The neighborhood territory pixel collection includes that the neighborhood candidate pixel concentrates all pixels and the pixel to be mixed.
9. device as claimed in claim 7, it is characterised in that:
The analysis module analyzes the valid pixel that the neighborhood candidate pixel is concentrated, comprising: according to the neighborhood territory pixel collection
Whether coefficient matrix analyzes each pixel that the neighborhood candidate pixel is concentrated effective；It is determined according to each channel threshold value of three primary colours
The valid pixel that the neighborhood candidate pixel is concentrated.
10. device as claimed in claim 9, it is characterised in that:
The analysis module determines the valid pixel that the neighborhood candidate pixel is concentrated, packet according to each channel threshold value of three primary colours
It includes: each channel value of three primary colours is determined according to each channel value of the corresponding three primary colours of the pixel to be mixed and each channel threshold value of three primary colours
Valid interval；If each channel value of the corresponding three primary colours of pixel that the neighborhood candidate pixel is concentrated is in corresponding valid interval
It is interior, it is determined that the pixel is valid pixel.
11. device as claimed in claim 7, it is characterised in that:
The acquisition module obtains the effective of the pixel to be mixed according to the valid pixel collection and the coefficient of efficiency matrix
Mixed number, comprising: concentrate the coefficient of all elements and its corresponding coefficient of efficiency matrix to carry out according to the valid pixel
Weighted average obtains effective mixed number of the pixel to be mixed.
12. such as the described in any item devices of claim 7-11, it is characterised in that:
The synthesis module, according to mixed mode algorithm are as follows: Pout=P "1×α+P″2× (255- α), wherein PoutFor image
It is being exported after mixing as a result, P "1For effective mixed number of the pixel to be mixed of the first image to be synthesized, P "2For second wait close
At effective mixed number of the pixel to be mixed of image, α is coefficient of transparency.
13. a kind of device of image synthesis, comprising: memory, processor and storage can transport on a memory and on a processor
Capable computer program, which is characterized in that the processor performs the steps of when executing described program
The neighborhood for determining pixel to be mixed in image to be synthesized respectively determines neighborhood candidate pixel collection from the neighborhood；
The valid pixel that the neighborhood candidate pixel is concentrated is analyzed, the valid pixel and the pixel to be mixed are determined as having
Imitate set of pixels；
The corresponding effective mark of element is concentrated to determine that the neighborhood territory pixel collection of the pixel to be mixed is corresponding according to the valid pixel
Coefficient of efficiency matrix；
Effective mixed number of the pixel to be mixed is obtained according to the valid pixel collection and the coefficient of efficiency matrix；
According to the described to be synthesized of effective mixed number of the pixel to be mixed of each image to be synthesized and mixed mode algorithm pair
Image carries out synthesis processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710801070.0A CN109472763B (en) | 2017-09-07 | 2017-09-07 | Image synthesis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710801070.0A CN109472763B (en) | 2017-09-07 | 2017-09-07 | Image synthesis method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109472763A true CN109472763A (en) | 2019-03-15 |
| CN109472763B CN109472763B (en) | 2020-12-08 |
Family
ID=65657592
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710801070.0A Active CN109472763B (en) | 2017-09-07 | 2017-09-07 | Image synthesis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109472763B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5630037A (en) * | 1994-05-18 | 1997-05-13 | Schindler Imaging, Inc. | Method and apparatus for extracting and treating digital images for seamless compositing |
| CN1217126A (en) * | 1996-04-30 | 1999-05-19 | Cfb(新图象设计中心)有限公司 | Device and process for producing composite picture |
| CN1510656A (en) * | 2002-11-27 | 2004-07-07 | 松下电器产业株式会社 | Displaying device, method and programm |
| CN105578094A (en) * | 2015-12-18 | 2016-05-11 | 深圳市帅映科技有限公司 | Image edge fusion processing system |
-
2017
- 2017-09-07 CN CN201710801070.0A patent/CN109472763B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5630037A (en) * | 1994-05-18 | 1997-05-13 | Schindler Imaging, Inc. | Method and apparatus for extracting and treating digital images for seamless compositing |
| CN1217126A (en) * | 1996-04-30 | 1999-05-19 | Cfb(新图象设计中心)有限公司 | Device and process for producing composite picture |
| CN1510656A (en) * | 2002-11-27 | 2004-07-07 | 松下电器产业株式会社 | Displaying device, method and programm |
| CN105578094A (en) * | 2015-12-18 | 2016-05-11 | 深圳市帅映科技有限公司 | Image edge fusion processing system |
Non-Patent Citations (2)
| Title |
|---|
| FENG DONG等: "Multiscaled Texture Synthesis Using Multisized Pixel Neighborhoods", 《 IEEE COMPUTER GRAPHICS AND APPLICATIONS》 * |
| 吴昊: "高效图像合成技术研究", 《中国博士学位论文全文数据库信息科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109472763B (en) | 2020-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106504220B (en) | A kind of image processing method and device | |
| CN103971126B (en) | A kind of traffic sign recognition method and device | |
| CN103136766B (en) | A kind of object conspicuousness detection method based on color contrast and color distribution | |
| CN104134200B (en) | Mobile scene image splicing method based on improved weighted fusion | |
| CN103208115B (en) | Based on the saliency method for detecting area of geodesic line distance | |
| CN101588438A (en) | Mobile phone animation creation method for converting digitalized coloured picture into pictures of different styles | |
| CN106530266B (en) | A kind of infrared and visible light image fusion method based on region rarefaction representation | |
| CN106022205B (en) | Image processing apparatus and image processing method | |
| RU2014154403A (en) | SEGMENTATION MEANS | |
| CN107527054A (en) | Prospect extraction method based on various visual angles fusion | |
| CN104933679B (en) | A kind of method and its correspondence system of enlarged drawing | |
| CN101826209A (en) | Canny model-based method for segmenting three-dimensional medical image | |
| CN110188730A (en) | Face datection and alignment schemes based on MTCNN | |
| Yang et al. | Exploring Prior Knowledge for Pedestrian Detection. | |
| CN106297492A (en) | A kind of Educational toy external member and utilize color and the method for outline identification programming module | |
| CN103700078A (en) | Defogging method for image with few backgrounds containing fog | |
| CN105303536A (en) | Median filtering algorithm based on weighted mean filtering | |
| CN103020959A (en) | Gravity model-based oceanic front information extraction method | |
| CN106650811A (en) | Hyperspectral mixed pixel classification method based on neighbor cooperation enhancement | |
| CN109472763A (en) | A kind of image synthetic method and device | |
| CN103295238A (en) | ROI (region of interest) motion detection based real-time video positioning method for Android platform | |
| CN106469432A (en) | Object extraction method and object extraction equipment | |
| CN107085859B (en) | A kind of color lead painting style lattice method for drafting based on image | |
| Liu et al. | Depth-aware layered edge for object proposal | |
| Savant et al. | Color Image Edge Detection using Gradient Operator |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |