CN102542544A - Color matching method and system - Google Patents
Color matching method and system Download PDFInfo
- Publication number
- CN102542544A CN102542544A CN2010106165989A CN201010616598A CN102542544A CN 102542544 A CN102542544 A CN 102542544A CN 2010106165989 A CN2010106165989 A CN 2010106165989A CN 201010616598 A CN201010616598 A CN 201010616598A CN 102542544 A CN102542544 A CN 102542544A
- Authority
- CN
- China
- Prior art keywords
- image
- region
- matched
- color
- neighborhood
- 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
Images
Abstract
The invention discloses a color matching method and a color matching system so as to solve the problem that a color matching effect of a whole image is bad in the prior art. The color matching method comprises the following steps of: segmenting an image to be matched into a plurality of image areas according to image characteristic information of the image to be matched; establishing a color mapping relationship between a reference image and various corresponding image areas of the image to be matched so as to obtain an image subjected to color matching in various image areas of the image to be matched; and performing color blending on edge areas of the various image areas of the image subjected to color matching according to neighborhood information so as to obtain a final result image subjected to color matching of the image to be matched. Due to the technical scheme, local accurate color matching can be realized.
Description
Technical field
The present invention relates to a kind of method and system of match colors.
Background technology
Personnel often can obtain the original electron original text that the client provides and the scanning copy of corresponding printed matter simultaneously before the seal; In order to make the effect of drawing a design of electronics original text consistent with the effect of drawing a design of the scanning copy of corresponding printed matter, before the seal personnel just need the scanning copy of original electron original text and corresponding printed matter to be carried out match colors consistent to guarantee their final effects of drawing a design.This moment, the original electron original text provided image to be matched, and scanning copy is a reference picture, and the two content is identical.
At present; Main " match " function that adopts Adobe Photoshop to provide realizes the match colors between two width of cloth images in the production practices; There is following problem in this function: there is the colour cast of globality in coupling back image, and the problem that descends of the sharpness that exists picture contrast to reduce to cause; In addition, regional area, particularly the matching error in texture-rich zone is often bigger; Therefore, the match colors effect of this function can not satisfy the production needs.
The problem that has the match colors poor effect in the prior art for this problem, does not propose effective solution at present as yet.
Summary of the invention
Fundamental purpose of the present invention provides a kind of method and system of match colors, in order to solve the problem of match colors poor effect in the prior art.
For addressing the above problem, according to an aspect of the present invention, a kind of method of match colors is provided.
The method of match colors of the present invention is used for the color of image to be matched is adjusted into the color of the reference picture identical with picture material to be matched, comprising: according to the image feature information of image to be matched, be a plurality of image-regions with said image segmentation to be matched; Set up the interregional color map of reference picture and each correspondence image of image to be matched relation, obtain the image after each image-region match colors of image to be matched; According to neighborhood information to match colors after the fringe region of each image-region of image carry out color and merge, obtain the result images after the final match colors of image to be matched.
Further, be a plurality of image-regions with said image segmentation to be matched, comprising: with the said image to be matched of the color identification of preset number; Gradient and neighborhood information according to the image to be matched after the sign are selected seed region, carry out the region growing of said seed region then based on neighborhood; To each zone that obtains behind the said region growing, merge according to adjacent area in the position of adjacent area relation and the color degree of approximation image after to region growing, finally obtaining image segmentation to be matched is the segmentation result figure of a plurality of image-regions.
Further, carry out region growing, comprising: adopt 8 connected domain criterions that said seed region is carried out region growing based on said seed region.
Further, adjacent area in the image to be matched after identifying is merged, comprising: steps A: calculate said each regional centroid position and color average according to the position of adjacent area relation and color degree of approximation; Step B: judge that each if the two product is adjacent less than predetermined threshold value and two zones, then merges this two zone to the color difference of adjacent area and the distance of centroid position in the image to be matched after the zone merges; Carry out said steps A and said step B repeatedly, identical up to carrying out the back with the regional amalgamation result that last time, execution obtained.
Further, said reference picture and each correspondence image regional color mapping relations of image to be matched set up are meant based on histogram and set up said color map relation.
Further; Carry out match colors based on histogram and comprise said: the image-region interior zone of treating matching image carries out multiple dimensioned mean filter; Filtered is carried out dictionary ordering obtain the strict ordering that singly increases, said interior zone is the image-region that does not comprise fringe region; Interior zone to said image-region distributes according to the said interior zone accumulative histogram that singly increases the image-region of ordering and reference picture correspondence, sets up the color map relation in image to be matched and reference picture correspondence image zone; According to said color map relation, obtain the image after the match colors of each image-region of image to be matched.
Further; Said fringe region according to each image-region of neighborhood information after to match colors carries out color and merges; Be meant according to the color and the distance of neighborhood scope interior pixel point and carry out the neighborhood weighted sum; The color that carries out each image-region fringe region merges, and obtains the result images after the final match colors of image to be matched.
Further; The color fusion that each image-region fringe region is carried out in said neighborhood weighted sum is meant: the match value p ' that calculates pixel p in said each image-region fringe region according to formula
; Wherein, K representes the adjacent area number of p.In this formula, p
kThe color map relation and function of k the adjacent area of expression point p is in the color value of this point;
Wherein N representes the port number of said image to be matched, { M
i=k|i ∈ Ω } expression belongs to the neighborhood Ω of a p and the some i that its corresponding stencil value is k, | I
p-I
i| the color difference of expression point p and some i, function f represent one with | I
p-I
i| value be a function of negative correlation, G
PiExpression point p and the Gaussian distance of putting i.
For addressing the above problem, according to a further aspect in the invention, a kind of system of match colors is provided.
The system of match colors of the present invention is used for the color of image to be matched is adjusted into the color of the reference picture identical with picture material to be matched; Comprise: cut apart module; Being used for the image feature information according to image to be matched, is a plurality of image-regions with said image segmentation to be matched; Matching module is used to set up the interregional color map relation of reference picture and each correspondence image of image to be matched, obtains the image after each image-region match colors of image to be matched; Fusion Module, be used for according to neighborhood information to match colors after the fringe region of each image-region of image carry out color and merge, obtain the result images after the final match colors of image to be matched.
Further, the said module of cutting apart also is used for: with the said image to be matched of the color identification of preset number; Gradient and neighborhood information according to the image to be matched after the sign are selected seed region, carry out the region growing of said seed region then based on neighborhood; To each zone that obtains behind the said region growing, merge according to adjacent area in the position of adjacent area relation and the color degree of approximation image after to region growing, finally obtaining image segmentation to be matched is the segmentation result figure of a plurality of image-regions.
Further, the said module of cutting apart also is used to adopt 8 connected domain criterions that said seed region is carried out region growing.
Further, the said module of cutting apart also is used for carrying out: steps A: calculate said each regional centroid position and color average; Step B: judge that each if the two product is adjacent less than predetermined threshold value and two zones, then merges this two zone to the color difference of adjacent area and the distance of centroid position in the image to be matched after the zone merges; And carry out said steps A and said step B repeatedly, identical up to carrying out the back with the regional amalgamation result that last time, execution obtained.
Further, said matching module also is used for setting up said color map relation based on histogram.
Further, said matching module also is used for: the image-region interior zone of treating matching image carries out multiple dimensioned mean filter, filtered is carried out dictionary ordering obtain the strict ordering that singly increases, and said interior zone is the image-region that does not comprise fringe region; Interior zone to said image-region distributes according to the said interior zone accumulative histogram that singly increases the image-region of ordering and reference picture correspondence, sets up the color map relation in image to be matched and reference picture correspondence image zone; According to said color map relation, obtain the image after the match colors of each image-region of image to be matched.
Further, said Fusion Module also is used for: carry out the neighborhood weighted sum according to the color of neighborhood scope interior pixel point and distance, the color that carries out each image-region fringe region merges, and obtains the result images after the final match colors of image to be matched.
Further, said Fusion Module also is used for according to formula
Calculate the match value p ' of pixel p in said each image-region fringe region, wherein, K representes the adjacent area number of p, in this formula, and p
kThe color map relation and function of k the adjacent area of expression point p is in the color value of this point;
Wherein N representes the port number of said image to be matched, { M
i=k|i ∈ Ω } expression belongs to the neighborhood Ω of a p and the some i that its corresponding stencil value is k, | I
p-I
i| the color difference of expression point p and some i, function f represent one with | I
p-I
i| value be a function of negative correlation, G
PiExpression point p and the Gaussian distance of putting i.
According to scheme of the present invention; Set up the color map relation between each image-region according to segmentation result; And carry out color through fringe region and merge image-region; Revised the color error of fringe region, thereby realized accurate match colors, thereby helped to improve the effect of match colors based on the part.
Description of drawings
Accompanying drawing described herein is used to provide further understanding of the present invention, constitutes the application's a part, and illustrative examples of the present invention and explanation thereof are used to explain the present invention, do not constitute improper qualification of the present invention.In the accompanying drawings:
Fig. 1 is the main schematic flow sheet according to the method for the match colors of the embodiment of the invention;
Fig. 2 is the process flow diagram according to the key step of the image segmentation of the embodiment of the invention;
Fig. 3 carries out the synoptic diagram of the key step of match colors according to the embodiment of the invention based on histogram; And
Fig. 4 is the synoptic diagram according to system's main modular of the match colors of the embodiment of the invention.
Embodiment
Below with reference to accompanying drawing and combine embodiment, specify the present invention.
Fig. 1 is the main schematic flow sheet according to the method for the match colors of the embodiment of the invention, and is as shown in Figure 1, and this method mainly may further comprise the steps:
Step S11:, be a plurality of image-regions with image segmentation to be matched according to the image feature information of image to be matched;
Step S13: set up the interregional color map of reference picture and each correspondence image of image to be matched relation, obtain the image after each image-region match colors of image to be matched;
Step S15: according to neighborhood information to match colors after the fringe region of each image-region of image carry out color and merge, obtain the result images after the final match colors of image to be matched.
From top step, can find out; The scheme of present embodiment mainly is to mate and the fringe region of cutting apart the image-region that obtains is carried out color to the image of cutting apart to merge; Can revise the color error of this fringe region like this; Realization is based on the accurate match colors of part, thereby helps to improve the effect of match colors.
In above-mentioned step S11, can adopt the scheme of carrying out image segmentation based on color and texture.Concrete steps are as shown in Figure 2, and Fig. 2 is the process flow diagram according to the key step of the image segmentation of the embodiment of the invention.
Step S21: with the color identification of preset number image to be matched;
Step S23: gradient and neighborhood information according to the image to be matched after the sign are selected seed region, carry out the region growing of seed region then based on neighborhood;
Step S25: to each zone that obtains behind the region growing; Merge according to adjacent area in the position of adjacent area relation and the color degree of approximation image after to region growing, finally obtaining image segmentation to be matched is the segmentation result figure of a plurality of image-regions.
In above-mentioned step S23, can adopt 8 connected domain criterions that seed region is carried out region growing.In step S25, specifically can adopt following steps to carry out the zone and merge:
Steps A: calculate each regional centroid position and color average;
Step B: judge that each if the two product is adjacent less than predetermined threshold value and two zones, then merges this two zone to the color difference of adjacent area and the distance of centroid position in the image to be matched after the zone merges;
Execution in step A and step B are identical with the regional amalgamation result that last time, execution obtained up to carrying out the back repeatedly.Can obtain the least possible number of regions like this, thereby thereby reducing the zone boundary number reduces the calculated amount among the step S15, improve the speed of Flame Image Process.
The image that uses when setting up mapping relations among the above-mentioned steps S13 is the image-region interior zone, but when carrying out match colors is whole this image-region of coupling.The mapping relations here specifically can be set up based on histogram, and concrete steps are as shown in Figure 3, and Fig. 3 carries out the synoptic diagram of the key step of match colors according to the embodiment of the invention based on histogram.
Step S31: the image-region interior zone of treating matching image carries out multiple dimensioned mean filter, filtered is carried out dictionary ordering obtain the strict ordering that singly increases, and this interior zone is the image-region that does not comprise fringe region;
Step S33: the interior zone to image-region distributes according to the interior zone accumulative histogram that singly increases the corresponding image-region of ordering and reference picture, sets up the color map relation in image to be matched and reference picture correspondence image zone;
Step S35:, obtain the image after the match colors of each image-region of image to be matched according to color map relation.
In above-mentioned steps S15; Carrying out color according to the fringe region of each image-region of neighborhood information after to match colors merges; Can be to carry out the neighborhood weighted sum according to the color and the distance of neighborhood scope interior pixel point; The color that carries out each image-region fringe region merges, and obtains the result images after the final match colors of image to be matched.The color fusion that each image-region fringe region is carried out in the neighborhood weighted sum here can be the match value p ' that calculates pixel p in each image-region fringe region according to formula
; Wherein, K representes the adjacent area number of p.In this formula, p
kThe color map relation and function of k the adjacent area of expression point p is in the color value of this point;
Wherein N representes the port number of image to be matched, { M
i=k|i ∈ Ω } expression belongs to the neighborhood Ω of a p and the some i that its corresponding stencil value is k, | I
p-I
i| the color difference of expression point p and some i, function f represent one with | I
p-I
i| value be a function of negative correlation, G
PiExpression point p and the Gaussian distance of putting i.
Fig. 4 is the synoptic diagram according to system's main modular of the match colors of the embodiment of the invention.As shown in Figure 4, the system 40 of match colors mainly comprises like lower module:
Cutting apart module, be used for the image feature information according to image to be matched, is a plurality of image-regions with image segmentation to be matched; Matching module is used to set up the interregional color map relation of reference picture and each correspondence image of image to be matched, obtains the image after each image-region match colors of image to be matched; Fusion Module, be used for according to neighborhood information to match colors after the fringe region of each image-region of image carry out color and merge, obtain the result images after the final match colors of image to be matched.
Cutting apart module also can be used for: with the color identification of preset number image to be matched; Gradient and neighborhood information according to the image to be matched after the sign are selected seed region, carry out the region growing of seed region then based on neighborhood; To each zone that obtains behind the region growing, merge according to adjacent area in the position of adjacent area relation and the color degree of approximation image after to region growing, finally obtaining image segmentation to be matched is the segmentation result figure of a plurality of image-regions.When carrying out the region growing processing, cut apart module and can adopt 8 connected domain criterions that said seed region is carried out region growing.
Cutting apart module also can be used for carrying out the zone merging by following mode: steps A: calculate each regional centroid position and color average; Step B: judge that each if the two product is adjacent less than predetermined threshold value and two zones, then merges this two zone to the color difference of adjacent area and the distance of centroid position in the image to be matched after the zone merges; And execution in step A and said step B repeatedly, identical up to carrying out the back with the regional amalgamation result that last time, execution obtained.
Matching module also can be used for setting up the color map relation based on histogram; Specifically can be that the image-region interior zone of treating matching image carries out multiple dimensioned mean filter; Filtered is carried out dictionary ordering obtain the strict ordering that singly increases, this interior zone is the image-region that does not comprise fringe region; Interior zone to image-region distributes according to the interior zone accumulative histogram that singly increases the corresponding image-region of ordering and reference picture, sets up the color map relation in image to be matched and reference picture correspondence image zone; According to color map relation, obtain the image after the match colors of each image-region of image to be matched.
Fusion Module can also be used for carrying out the neighborhood weighted sum according to the color of neighborhood scope interior pixel point and distance, and the color that carries out each image-region fringe region merges, and obtains the result images after the final match colors of image to be matched.Specifically can calculate the match value p ' of pixel p in each image-region fringe region according to formula
; Wherein, K representes the adjacent area number of p.In this formula, p
kThe color map relation and function of k the adjacent area of expression point p is in the color value of this point;
Wherein N representes the port number of image to be matched, { M
i=k|i ∈ Ω } expression belongs to the neighborhood Ω of a p and the some i that its corresponding stencil value is k, | I
p-I
i| the color difference of expression point p and some i, function f represent one with | I
p-I
i| value be a function of negative correlation, G
PiExpression point p and the Gaussian distance of putting i.
Obviously, it is apparent to those skilled in the art that above-mentioned each module of the present invention or each step can realize with the general calculation device; They can concentrate on the single calculation element; Perhaps be distributed on the network that a plurality of calculation element forms, alternatively, they can be realized with the executable program code of calculation element; Thereby; Can they be stored in the memory storage and carry out, perhaps they are made into each integrated circuit modules respectively, perhaps a plurality of modules in them or step are made into the single integrated circuit module and realize by calculation element.Like this, the present invention is not restricted to any specific hardware and software combination.
The above is merely the preferred embodiments of the present invention, is not limited to the present invention, and for a person skilled in the art, the present invention can have various changes and variation.All within spirit of the present invention and principle, any modification of being done, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (16)
1. the method for a match colors is used for the color of image to be matched is adjusted into the color of the reference picture identical with picture material to be matched, it is characterized in that said method comprises:
According to the image feature information of image to be matched, be a plurality of image-regions with said image segmentation to be matched;
Set up the interregional color map of reference picture and each correspondence image of image to be matched relation, obtain the image after each image-region match colors of image to be matched;
According to neighborhood information to match colors after the fringe region of each image-region of image carry out color and merge, obtain the result images after the final match colors of image to be matched.
2. method according to claim 1 is characterized in that, is a plurality of image-regions with said image segmentation to be matched, comprising:
With the said image to be matched of the color identification of preset number;
Gradient and neighborhood information according to the image to be matched after the sign are selected seed region, carry out the region growing of said seed region then based on neighborhood;
To each zone that obtains behind the said region growing, merge according to adjacent area in the position of adjacent area relation and the color degree of approximation image after to region growing, finally obtaining image segmentation to be matched is the segmentation result figure of a plurality of image-regions.
3. method according to claim 2 is characterized in that, carries out region growing based on said seed region, comprising: adopt 8 connected domain criterions that said seed region is carried out region growing.
4. according to claim 2 or 3 described methods, it is characterized in that, merge according to adjacent area in the position of adjacent area relation and the color degree of approximation image to be matched after to region growing and comprise:
Steps A: calculate said each regional centroid position and color average;
Step B: judge that each if the two product is adjacent less than predetermined threshold value and two zones, then merges this two zone to the color difference of adjacent area and the distance of centroid position in the image to be matched after the zone merges;
Carry out said steps A and said step B repeatedly, identical up to carrying out the back with the regional amalgamation result that last time, execution obtained.
5. method according to claim 1 is characterized in that, said reference picture and each correspondence image regional color mapping relations of image to be matched set up are meant based on histogram and set up said color map relation.
6. method according to claim 5 is characterized in that, carries out match colors based on histogram and comprises said:
The image-region interior zone of treating matching image carries out multiple dimensioned mean filter, filtered is carried out dictionary ordering obtain the strict ordering that singly increases, and said interior zone is the image-region that does not comprise fringe region;
Interior zone to said image-region distributes according to the said interior zone accumulative histogram that singly increases the image-region of ordering and reference picture correspondence, sets up the color map relation in image to be matched and reference picture correspondence image zone;
According to said color map relation, obtain the image after the match colors of each image-region of image to be matched.
7. method according to claim 1; It is characterized in that; Said fringe region according to each image-region of neighborhood information after to match colors carries out color and merges; Be meant according to the color of neighborhood scope interior pixel point and distance and carry out the neighborhood weighted sum, the color that carries out each image-region fringe region merges, and obtains the result images after the final match colors of image to be matched.
8. method according to claim 7 is characterized in that, the color fusion that each image-region fringe region is carried out in said neighborhood weighted sum is meant:
Calculate the match value p ' of pixel p in said each image-region fringe region according to formula
; Wherein, K representes the adjacent area number of p.In this formula, p
kThe color map relation and function of k the adjacent area of expression point p is in the color value of this point;
Wherein N representes the port number of said image to be matched, { M
i=k|i ∈ Ω } expression belongs to the neighborhood Ω of a p and the some i that its corresponding stencil value is k, | I
p-I
i| the color difference of expression point p and some i, function f represent one with | I
p-I
i| value be a function of negative correlation, G
PiExpression point p and the Gaussian distance of putting i.
9. the system of a match colors is used for the color of image to be matched is adjusted into the color of the reference picture identical with picture material to be matched, it is characterized in that said system comprises:
Cutting apart module, be used for the image feature information according to image to be matched, is a plurality of image-regions with said image segmentation to be matched;
Matching module is used to set up the interregional color map relation of reference picture and each correspondence image of image to be matched, obtains the image after each image-region match colors of image to be matched;
Fusion Module, be used for according to neighborhood information to match colors after the fringe region of each image-region of image carry out color and merge, obtain the result images after the final match colors of image to be matched.
10. system according to claim 9 is characterized in that, the said module of cutting apart also is used for:
With the said image to be matched of the color identification of preset number;
Gradient and neighborhood information according to the image to be matched after the sign are selected seed region, carry out the region growing of said seed region then based on neighborhood;
To each zone that obtains behind the said region growing, merge according to adjacent area in the position of adjacent area relation and the color degree of approximation image after to region growing, finally obtaining image segmentation to be matched is the segmentation result figure of a plurality of image-regions.
11. system according to claim 10 is characterized in that, the said module of cutting apart also is used to adopt 8 connected domain criterions that said seed region is carried out region growing.
12., it is characterized in that the said module of cutting apart also is used for carrying out according to claim 10 or 11 described systems:
Steps A: calculate said each regional centroid position and color average;
Step B: judge that each if the two product is adjacent less than predetermined threshold value and two zones, then merges this two zone to the color difference of adjacent area and the distance of centroid position in the image to be matched after the zone merges; And
Carry out said steps A and said step B repeatedly, identical up to carrying out the back with the regional amalgamation result that last time, execution obtained.
13. system according to claim 9 is characterized in that, said matching module also is used for setting up said color map relation based on histogram.
14. system according to claim 13 is characterized in that, said matching module also is used for:
The image-region interior zone of treating matching image carries out multiple dimensioned mean filter, filtered is carried out dictionary ordering obtain the strict ordering that singly increases, and said interior zone is the image-region that does not comprise fringe region;
Interior zone to said image-region distributes according to the said interior zone accumulative histogram that singly increases the image-region of ordering and reference picture correspondence, sets up the color map relation in image to be matched and reference picture correspondence image zone;
According to said color map relation, obtain the image after the match colors of each image-region of image to be matched.
15. system according to claim 9; It is characterized in that; Said Fusion Module also is used for: color and distance according to neighborhood scope interior pixel point are carried out the neighborhood weighted sum; The color that carries out each image-region fringe region merges, and obtains the result images after the final match colors of image to be matched.
16. system according to claim 15 is characterized in that, said Fusion Module also is used for according to formula
Calculate the match value p ' of pixel p in said each image-region fringe region, wherein, K representes the adjacent area number of p, in this formula, and p
kThe color map relation and function of k the adjacent area of expression point p is in the color value of this point;
Wherein N representes the port number of said image to be matched, { M
i=k|i ∈ Ω } expression belongs to the neighborhood Ω of a p and the some i that its corresponding stencil value is k, | I
p-I
i| the color difference of expression point p and some i, function f represent one with | I
p-I
i| value be a function of negative correlation, G
PiExpression point p and the Gaussian distance of putting i.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010106165989A CN102542544A (en) | 2010-12-30 | 2010-12-30 | Color matching method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010106165989A CN102542544A (en) | 2010-12-30 | 2010-12-30 | Color matching method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102542544A true CN102542544A (en) | 2012-07-04 |
Family
ID=46349369
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010106165989A Pending CN102542544A (en) | 2010-12-30 | 2010-12-30 | Color matching method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102542544A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020998A (en) * | 2012-11-19 | 2013-04-03 | 中山大学 | Tone mapping method based on edge-preserving total variation model |
| CN103325107A (en) * | 2013-05-22 | 2013-09-25 | 北京小米科技有限责任公司 | Method, device and terminal device for processing image |
| CN103929629A (en) * | 2014-04-24 | 2014-07-16 | 厦门美图网科技有限公司 | Image processing method based on image major colors |
| CN104580883A (en) * | 2013-10-09 | 2015-04-29 | 卡西欧计算机株式会社 | Image processing device and image processing method |
| CN104899909A (en) * | 2015-05-12 | 2015-09-09 | 福建天晴数码有限公司 | Color mapping method and device thereof |
| CN109087311A (en) * | 2018-07-24 | 2018-12-25 | 中国航发沈阳发动机研究所 | Temperature indicating paint temperature interpretation method |
| CN109840912A (en) * | 2019-01-02 | 2019-06-04 | 厦门美图之家科技有限公司 | The modification method of abnormal pixel and equipment is calculated in a kind of image |
| CN110189329A (en) * | 2019-04-03 | 2019-08-30 | 阿里巴巴集团控股有限公司 | System and method for positioning the color block areas of colour atla |
| WO2022042754A1 (en) * | 2020-08-31 | 2022-03-03 | 维沃移动通信有限公司 | Image processing method and apparatus, and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1595434A (en) * | 2004-06-21 | 2005-03-16 | 南开大学 | Color image matching analytical method based on color content and distribution |
| CN1851731A (en) * | 2006-05-25 | 2006-10-25 | 电子科技大学 | Registration number character dividing method |
| CN101299277A (en) * | 2008-06-25 | 2008-11-05 | 北京中星微电子有限公司 | Method and system for colorizing black and white picture |
| CN101441763A (en) * | 2008-11-11 | 2009-05-27 | 浙江大学 | Multiple-colour tone image unity regulating method based on color transfer |
| CN101706965A (en) * | 2009-11-03 | 2010-05-12 | 上海大学 | Method for colorizing regional image on basis of Gaussian mixture model |
| CN101872473A (en) * | 2010-06-25 | 2010-10-27 | 清华大学 | Multiscale image natural color fusion method and device based on over-segmentation and optimization |
-
2010
- 2010-12-30 CN CN2010106165989A patent/CN102542544A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1595434A (en) * | 2004-06-21 | 2005-03-16 | 南开大学 | Color image matching analytical method based on color content and distribution |
| CN1851731A (en) * | 2006-05-25 | 2006-10-25 | 电子科技大学 | Registration number character dividing method |
| CN101299277A (en) * | 2008-06-25 | 2008-11-05 | 北京中星微电子有限公司 | Method and system for colorizing black and white picture |
| CN101441763A (en) * | 2008-11-11 | 2009-05-27 | 浙江大学 | Multiple-colour tone image unity regulating method based on color transfer |
| CN101706965A (en) * | 2009-11-03 | 2010-05-12 | 上海大学 | Method for colorizing regional image on basis of Gaussian mixture model |
| CN101872473A (en) * | 2010-06-25 | 2010-10-27 | 清华大学 | Multiscale image natural color fusion method and device based on over-segmentation and optimization |
Non-Patent Citations (1)
| Title |
|---|
| 杨筱平 等: "基于GrabCut分割和自动采样的敦煌壁画色彩修复", 《兰州理工大学学报》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020998A (en) * | 2012-11-19 | 2013-04-03 | 中山大学 | Tone mapping method based on edge-preserving total variation model |
| CN103325107A (en) * | 2013-05-22 | 2013-09-25 | 北京小米科技有限责任公司 | Method, device and terminal device for processing image |
| CN104580883B (en) * | 2013-10-09 | 2018-05-29 | 卡西欧计算机株式会社 | Image processing apparatus, image processing method and recording medium |
| CN104580883A (en) * | 2013-10-09 | 2015-04-29 | 卡西欧计算机株式会社 | Image processing device and image processing method |
| US9679386B2 (en) | 2013-10-09 | 2017-06-13 | Casio Computer Co., Ltd. | Image processing device capable of segmenting an image into plural areas |
| CN103929629A (en) * | 2014-04-24 | 2014-07-16 | 厦门美图网科技有限公司 | Image processing method based on image major colors |
| CN104899909A (en) * | 2015-05-12 | 2015-09-09 | 福建天晴数码有限公司 | Color mapping method and device thereof |
| CN109087311A (en) * | 2018-07-24 | 2018-12-25 | 中国航发沈阳发动机研究所 | Temperature indicating paint temperature interpretation method |
| CN109087311B (en) * | 2018-07-24 | 2021-05-28 | 中国航发沈阳发动机研究所 | Temperature judging and reading method for temperature indicating paint |
| CN109840912A (en) * | 2019-01-02 | 2019-06-04 | 厦门美图之家科技有限公司 | The modification method of abnormal pixel and equipment is calculated in a kind of image |
| CN109840912B (en) * | 2019-01-02 | 2021-05-04 | 厦门美图之家科技有限公司 | Method for correcting abnormal pixels in image and computing equipment |
| CN110189329A (en) * | 2019-04-03 | 2019-08-30 | 阿里巴巴集团控股有限公司 | System and method for positioning the color block areas of colour atla |
| CN110189329B (en) * | 2019-04-03 | 2022-12-13 | 创新先进技术有限公司 | System and method for locating patch regions of a color chip |
| WO2022042754A1 (en) * | 2020-08-31 | 2022-03-03 | 维沃移动通信有限公司 | Image processing method and apparatus, and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102542544A (en) | Color matching method and system | |
| CN104050682B (en) | Image segmentation method fusing color and depth information | |
| CN103034856B (en) | The method of character area and device in positioning image | |
| CN105608456A (en) | Multi-directional text detection method based on full convolution network | |
| CN102411774A (en) | Processing method, device and system based on single-image defogging | |
| CN105608722B (en) | It is a kind of that pouch method and system are gone based on face key point automatically | |
| CN103077500B (en) | The defogging method capable of view data and device | |
| CN100481966C (en) | Video camera marking method based on plane homographic matrix characteristic line | |
| CN103208115B (en) | Based on the saliency method for detecting area of geodesic line distance | |
| CN103578085B (en) | Image cavity region based on variable-block method for repairing and mending | |
| DE602005026862D1 (en) | SEGMENTATION OF A DIGITAL IMAGE AND MANUFACTURE OF A COMPACT REPRESENTATION | |
| CN101510304B (en) | Method, device and pick-up head for dividing and obtaining foreground image | |
| CN104680482A (en) | Method and device for image processing | |
| CN104598905A (en) | License plate positioning method and device | |
| CN107909079A (en) | One kind collaboration conspicuousness detection method | |
| CN107169973A (en) | The background removal and synthetic method and device of a kind of image | |
| CN107038707B (en) | Image segmentation method and device | |
| CN105809673A (en) | SURF (Speeded-Up Robust Features) algorithm and maximal similarity region merging based video foreground segmentation method | |
| CN111462164A (en) | Foreground segmentation method and data enhancement method based on image synthesis | |
| CN102768758B (en) | Improved color image unsharp masking (USM) method | |
| CN111145305A (en) | Document image processing method | |
| CN104134192A (en) | Image defogging method and system | |
| CN103778428B (en) | Disease area-of-interest exacting method and system based on block labelling | |
| Peng et al. | A region-based color image segmentation method based on P systems | |
| CN105046696A (en) | Image matching method based on deep planar constraint graph cut optimization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120704 |