CN104978712A - Image processing method and device - Google Patents
Image processing method and device Download PDFInfo
- Publication number
- CN104978712A CN104978712A CN201410138449.4A CN201410138449A CN104978712A CN 104978712 A CN104978712 A CN 104978712A CN 201410138449 A CN201410138449 A CN 201410138449A CN 104978712 A CN104978712 A CN 104978712A
- Authority
- CN
- China
- Prior art keywords
- little
- former
- pixel
- resolution
- preview graph
- 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
Landscapes
- Image Processing (AREA)
Abstract
The embodiment of the invention discloses an image processing method and device, and relates to the field of the information technology. Image processing complexity can not be increased while processing effect differences between an original drawing and a preview are lowered. The method comprises the following steps: firstly, dividing the original drawing into a plurality of small drawings, wherein a resolution corresponding to each small drawing is the same with the resolution corresponding to the preview; then, according to an art filter algorithm corresponding to the preview, carrying out image processing on each small drawing; and finally, according to the position of each small drawing in the original drawing, combining all processed small drawings into an image corresponding to the original drawing.
Description
Technical field
The present invention relates to areas of information technology, particularly a kind of image processing method and device.
Background technology
Along with the development of terminal device, the function of terminal device also from strength to strength.Wherein, user can be taken pictures by terminal device, browsing pictures, and is processed the image got by artistic filter.But the result that terminal device art filter leading portion presents to the former figure that the result of the preview graph of user and backstage are preserved is completely different.
At present, usually by increasing spatial filtering convolution kernel, the difference between the result of preview graph and the result of former figure is reduced.But differ larger with the resolution sizes of former figure due to the resolution sizes of preview graph, adopt the difference on effect of mode to preview graph and former figure process increasing spatial filtering convolution kernel still larger, and because spatial filtering convolution kernel is larger, required calculated amount is larger, because this increasing image procossing complexity.
Summary of the invention
The embodiment of the present invention provides a kind of image processing method and device, while not increasing image procossing complexity, can reduce the treatment effect difference between preview graph and former figure.
The technical scheme that the embodiment of the present invention adopts is:
A kind of image processing method, comprising:
Be multiple little figure by former diagram root, the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical;
The artistic filter algorithm corresponding according to described preview graph, carries out image procossing to each little figure described;
According to the described position of each little figure in described former figure, each the little figure after process is merged into image corresponding to described former figure.
A kind of image processing apparatus, comprising:
Division unit, for being multiple little figure by former diagram root, the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical;
Processing unit, for the artistic filter algorithm corresponding according to described preview graph, carries out image procossing to each little figure that described division unit divides;
Merge cells, for according to the described position of each little figure in described former figure, merges into image corresponding to described former figure by little for each after described processing unit processes figure.
The image processing method that the embodiment of the present invention provides and device, first be multiple little figure by former diagram root, the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical, then corresponding according to described preview graph artistic filter algorithm, image procossing is carried out to each little figure described, last according to the described position of each little figure in described former figure, each the little figure after process is merged into image corresponding to described former figure.With prior art by increasing spatial filtering convolution kernel, reduce compared with the difference between the result of preview graph and the result of former figure, the mode of the embodiment of the present invention by adopting discrete sampling to split former figure, make each the little figure after splitting identical with the resolution sizes of preview graph, thus the artistic filter algorithm identical with preview graph can be adopted to carry out image procossing to former figure, while reducing the treatment effect difference between former figure and preview graph, image procossing complexity can not be increased.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
A kind of image processing method process flow diagram that Fig. 1 provides for the embodiment of the present invention;
The another kind of image processing method process flow diagram that Fig. 2 provides for the embodiment of the present invention;
A kind of image processing apparatus structural representation that Fig. 3 provides for the embodiment of the present invention;
The another kind of image processing apparatus structural representation that Fig. 4 provides for the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making other embodiments all obtained under creative work prerequisite, belong to the scope of protection of the invention.
For making the advantage of technical solution of the present invention clearly, below in conjunction with drawings and Examples, the present invention is elaborated.
The embodiment of the present invention provides a kind of image processing method, and as shown in Figure 1, described method comprises:
101, by former diagram root be multiple little figure.
Wherein, the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical.Such as, if resolution corresponding to preview graph is 400*200, then the resolution of each the little figure after dividing also be 400*200, thus can ensure that each the little figure after division is identical with the size of preview graph.
102, corresponding according to described preview graph artistic filter algorithm, carries out image procossing to each little figure described.
Wherein, artistic filter algorithm can be the multistage edge detection algorithm of canny(), structure tensor(is based on the region growing image segmentation algorithm in region), sobel(edge detection algorithm) etc., the embodiment of the present invention does not limit.For the embodiment of the present invention, by by former diagram root being the multiple little figure that the resolution corresponding with preview graph is identical, and adopt the algorithm identical with preview graph to carry out image procossing to each little figure, thus can ensure that the result of each little figure is identical with the result of preview graph or close, thus make the processing result image of the former figure be made up of each little figure identical with the result of preview graph or close further.
103, according to the described position of each little figure in described former figure, each the little figure after process is merged into image corresponding to described former figure.
Wherein, specifically according to the coordinate position of each little figure in the two-dimensional space coordinate system that former figure is corresponding, each the little figure after process can be merged into image corresponding to described former figure.
A kind of image processing method that the embodiment of the present invention provides, first be multiple little figure by former diagram root, the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical, then corresponding according to described preview graph artistic filter algorithm, image procossing is carried out to each little figure described, last according to the described position of each little figure in described former figure, each the little figure after process is merged into image corresponding to described former figure.With prior art by increasing spatial filtering convolution kernel, reduce compared with the difference between the result of preview graph and the result of former figure, the mode of the embodiment of the present invention by adopting discrete sampling to split former figure, make each the little figure after splitting identical with the resolution sizes of preview graph, thus the artistic filter algorithm identical with preview graph can be adopted to carry out image procossing to former figure, while reducing the treatment effect difference between former figure and preview graph, image procossing complexity can not be increased.
Further, the embodiment of the present invention provides another kind of image processing method, and as shown in Figure 2, described method comprises:
201, the one-to-one relationship between each pixel and each coordinate points that described former figure comprises is set up.
Such as, the function f (x, y) of can be the image configurations of N*M by resolution be two-dimensional space, the corresponding coordinate (x, y) of each pixel in image, thus ensure that the one-to-one relationship between each pixel that former figure comprises and each coordinate points.
202, by former diagram root be multiple little figure.
Wherein, the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical.Such as, if the resolution that really preview graph is corresponding is 200*100, then the resolution of each the little figure after dividing also is 200*100, thus can ensure that each the little figure after dividing is identical with the size of preview graph.
Particularly, first resolution, N * M corresponding to described former figure and resolution n*m corresponding to described preview graph is obtained, then according to the sampling interval in formula t=N/n calculated level direction, and calculating the sampling interval of vertical direction according to formula k=M/m is finally t*k little figure by described former diagram root, the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical.Wherein, N, M, n, m are positive integer, and t is the sampling interval of horizontal direction, and k is the sampling interval of vertical direction, and t, k are positive integer.
Such as, the resolution that former figure is corresponding is 800*400, and resolution corresponding to preview graph is 200*100, now the sampling interval of horizontal direction is 800/400=4, the sampling interval of vertical direction is 400/100=4, now, and the little figure of to be 16 resolution by former diagram root be 200*100.
203, pixel set a(i, j that each little figure is corresponding is obtained).
Wherein, i is the remainder of x divided by t, and j is the remainder of y divided by k, and x is the horizontal coordinate that each pixel that each little figure described comprises is corresponding respectively, and y is the vertical coordinate that each pixel that each little figure described comprises is corresponding respectively.Such as, the coordinate of some pixels is (6,6), and the sampling interval of horizontal direction is 5, and the sampling interval of vertical direction is 5, then now this pixel is (1,1).
For the embodiment of the present invention, because each little figure is combined into by the set of pixels of former figure being carried out to discrete sampling, therefore the pixel one_to_one corresponding in each pixel comprised in each little figure and former figure, thus ensure that the image be made up of each the little figure after processing can not lose former figure resolution.
204, corresponding according to described preview graph artistic filter algorithm, each pixel in the pixel set corresponding to each little figure carries out image procossing.
Wherein, artistic filter algorithm can be the multistage edge detection algorithm of canny(), structure tensor(is based on the region growing image segmentation algorithm in region), sobel(edge detection algorithm) etc., the embodiment of the present invention does not limit.For the embodiment of the present invention, by by former diagram root being the multiple little figure that the resolution corresponding with preview graph is identical, and adopt the algorithm identical with preview graph to carry out image procossing to each little figure, thus can ensure that the result of each little figure is identical with the result of preview graph or close, thus make the processing result image of the former figure be made up of each little figure identical with the result of preview graph or close further.
205, according to the coordinate position of each pixel in described former figure in pixel set corresponding to each little figure described, each pixel after process is merged into image corresponding to described former figure.
The another kind of image processing method that the embodiment of the present invention provides, first be multiple little figure by former diagram root, the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical, then corresponding according to described preview graph artistic filter algorithm, image procossing is carried out to each little figure described, last according to the described position of each little figure in described former figure, each the little figure after process is merged into image corresponding to described former figure.With prior art by increasing spatial filtering convolution kernel, reduce compared with the difference between the result of preview graph and the result of former figure, the mode of the embodiment of the present invention by adopting discrete sampling to split former figure, make each the little figure after splitting identical with the resolution sizes of preview graph, thus the artistic filter algorithm identical with preview graph can be adopted to carry out image procossing to former figure, while reducing the treatment effect difference between former figure and preview graph, image procossing complexity can not be increased.
Again further, as the specific implementation of method shown in Fig. 1, the embodiment of the present invention provides a kind of image processing apparatus, and the entity of described device can be the terminal device such as mobile phone, computer, as shown in Figure 3, described device comprises: division unit 31, processing unit 32, merge cells 33.
Division unit 31, may be used for being multiple little figure by former diagram root, and the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical.
Processing unit 32, may be used for the artistic filter algorithm corresponding according to described preview graph, carries out image procossing to each little figure that described division unit 31 divides.
Merge cells 33, may be used for according to the described position of each little figure in described former figure, each the little figure after being processed by described processing unit 32 merges into image corresponding to described former figure.
It should be noted that, other the corresponding descriptions of each functional unit involved by the device that the embodiment of the present invention provides can the correspondence in reference diagram 1 describe, and do not repeat them here.
A kind of image processing apparatus that the embodiment of the present invention provides, first be multiple little figure by former diagram root, the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical, then corresponding according to described preview graph artistic filter algorithm, image procossing is carried out to each little figure described, last according to the described position of each little figure in described former figure, each the little figure after process is merged into image corresponding to described former figure.With prior art by increasing spatial filtering convolution kernel, reduce compared with the difference between the result of preview graph and the result of former figure, the mode of the embodiment of the present invention by adopting discrete sampling to split former figure, make each the little figure after splitting identical with the resolution sizes of preview graph, thus the artistic filter algorithm identical with preview graph can be adopted to carry out image procossing to former figure, while reducing the treatment effect difference between former figure and preview graph, image procossing complexity can not be increased.
Again further, as the specific implementation of method shown in Fig. 2, the embodiment of the present invention provides another kind of image processing apparatus, the entity of described device can be the terminal device such as mobile phone, computer, as shown in Figure 4, described device comprises: division unit 41, processing unit 42, merge cells 43, set up unit 44, acquiring unit 45.
Division unit 41, may be used for being multiple little figure by former diagram root, and the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical.
Processing unit 42, may be used for the artistic filter algorithm corresponding according to described preview graph, carries out image procossing to each little figure that described division unit 41 divides.
Merge cells 43, may be used for according to the described position of each little figure in described former figure, each the little figure after being processed by described processing unit 42 merges into image corresponding to described former figure.
Division unit 41 can comprise: acquisition module 4101, computing module 4102, division module 4103.
Acquisition module 4101, may be used for obtaining resolution, N * M corresponding to described former figure and resolution n*m corresponding to described preview graph, wherein, N, M, n, m are positive integer.
Computing module 4102, may be used for the sampling interval according to formula t=N/n calculated level direction, and calculates the sampling interval of vertical direction according to formula k=M/m, wherein, t is the sampling interval of horizontal direction, and k is the sampling interval of vertical direction, and t, k are positive integer.
Divide module 4103, may be used for is t*k little figure by described former diagram root, and the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical.
Set up unit 44, may be used for setting up the one-to-one relationship between each pixel and each coordinate points that described former figure comprises.
Acquiring unit 45, may be used for obtaining pixel set a(i corresponding to each little figure, j), wherein, i is the remainder of x divided by t, j is the remainder of y divided by k, and x is the horizontal coordinate that each pixel that each little figure described comprises is corresponding respectively, and y is the vertical coordinate that each pixel that each little figure described comprises is corresponding respectively.
Processing unit 42, may be used for the artistic filter algorithm corresponding according to described preview graph, and each pixel in the pixel set corresponding to each little figure of described acquiring unit 45 acquisition carries out image procossing.
Merge cells 43, may be used for according to corresponding pixel set a(i, the j of each little figure described) in the coordinate position of each pixel in described former figure, by process after each pixel merge into image corresponding to described former figure.
It should be noted that, other the corresponding descriptions of each functional unit involved by the device that the embodiment of the present invention provides can the correspondence in reference diagram 2 describe, and do not repeat them here.
The another kind of image processing apparatus that the embodiment of the present invention provides, first be multiple little figure by former diagram root, the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical, then corresponding according to described preview graph artistic filter algorithm, image procossing is carried out to each little figure described, last according to the described position of each little figure in described former figure, each the little figure after process is merged into image corresponding to described former figure.With prior art by increasing spatial filtering convolution kernel, reduce compared with the difference between the result of preview graph and the result of former figure, the mode of the embodiment of the present invention by adopting discrete sampling to split former figure, make each the little figure after splitting identical with the resolution sizes of preview graph, thus the artistic filter algorithm identical with preview graph can be adopted to carry out image procossing to former figure, while reducing the treatment effect difference between former figure and preview graph, image procossing complexity can not be increased.
The image processing apparatus that the embodiment of the present invention provides can realize the above-mentioned embodiment of the method provided, and concrete function realizes the explanation referred in embodiment of the method, does not repeat them here.The image processing method that the embodiment of the present invention provides and device go for areas of information technology, but are not limited only to this.
One of ordinary skill in the art will appreciate that all or part of flow process realized in above-described embodiment method, that the hardware that can carry out instruction relevant by computer program has come, described program can be stored in a computer read/write memory medium, this program, when performing, can comprise the flow process of the embodiment as above-mentioned each side method.Wherein, described storage medium can be magnetic disc, CD, read-only store-memory body (Read-Only Memory, ROM) or random store-memory body (Random Access Memory, RAM) etc.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; the change that can expect easily or replacement, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of claim.
Claims (10)
1. an image processing method, is characterized in that, comprising:
Be multiple little figure by former diagram root, the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical;
The artistic filter algorithm corresponding according to described preview graph, carries out image procossing to each little figure described;
According to the described position of each little figure in described former figure, each the little figure after process is merged into image corresponding to described former figure.
2. image processing method according to claim 1, is characterized in that, described is that the step of multiple little figure comprises by former diagram root:
Obtain resolution, N * M corresponding to described former figure and resolution n*m corresponding to described preview graph, wherein, N, M, n, m are positive integer;
According to the sampling interval in formula t=N/n calculated level direction, and calculate the sampling interval of vertical direction according to formula k=M/m, wherein, t is the sampling interval of horizontal direction, and k is the sampling interval of vertical direction, and t, k are positive integer;
Be t*k little figure by described former diagram root, the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical.
3. image processing method according to claim 2, is characterized in that, described by former diagram root be the step of multiple little figure before, also comprise:
Set up the one-to-one relationship between each pixel and each coordinate points that described former figure comprises.
4. image processing method according to claim 3, is characterized in that, the described artistic filter algorithm corresponding according to described preview graph, before carrying out the step of image procossing, also comprises each little figure described:
Obtain pixel set a(i, j that each little figure is corresponding), wherein, i is the remainder of x divided by t, j is the remainder of y divided by k, and x is the horizontal coordinate that each pixel that each little figure described comprises is corresponding respectively, and y is the vertical coordinate that each pixel that each little figure described comprises is corresponding respectively;
The described artistic filter algorithm corresponding according to described preview graph, comprises the step that each little figure described carries out image procossing:
The artistic filter algorithm corresponding according to described preview graph, each pixel in the pixel set corresponding to each little figure carries out image procossing.
5. image processing method according to claim 4, is characterized in that, described according to the described position of each little figure in described former figure, the step that each the little figure after process merges into image corresponding to described former figure is comprised:
According to the coordinate position of each pixel in described former figure in the pixel set that each little figure described is corresponding, each pixel after process is merged into image corresponding to described former figure.
6. an image processing apparatus, is characterized in that, comprising:
Division unit, for being multiple little figure by former diagram root, the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical;
Processing unit, for the artistic filter algorithm corresponding according to described preview graph, carries out image procossing to each little figure that described division unit divides;
Merge cells, for according to the described position of each little figure in described former figure, merges into image corresponding to described former figure by little for each after described processing unit processes figure.
7. image processing apparatus according to claim 6, is characterized in that, described division unit comprises:
Acquisition module, for obtaining resolution, N * M corresponding to described former figure and resolution n*m corresponding to described preview graph, wherein, N, M, n, m are positive integer;
Computing module, for the sampling interval according to formula t=N/n calculated level direction, and calculate the sampling interval of vertical direction according to formula k=M/m, wherein, t is the sampling interval of horizontal direction, and k is the sampling interval of vertical direction, and t, k are positive integer;
Divide module, for by described former diagram root being t*k little figure, the resolution that each little figure described the is corresponding resolution corresponding with preview graph is identical.
8. image processing apparatus according to claim 7, is characterized in that, described device also comprises:
Set up unit, for setting up the one-to-one relationship between each pixel and each coordinate points that described former figure comprises.
9. image processing apparatus according to claim 8, is characterized in that, described device also comprises: acquiring unit;
Described acquiring unit, for obtaining pixel set a(i corresponding to each little figure, j), wherein, i is the remainder of x divided by t, j is the remainder of y divided by k, and x is the horizontal coordinate that each pixel that each little figure described comprises is corresponding respectively, and y is the vertical coordinate that each pixel that each little figure described comprises is corresponding respectively;
Described processing unit, for the artistic filter algorithm corresponding according to described preview graph, each pixel in the pixel set that each the little figure obtained described acquiring unit is corresponding carries out image procossing.
10. image processing apparatus according to claim 9, is characterized in that,
Described merge cells, for according to corresponding pixel set a(i, the j of each little figure described) in the coordinate position of each pixel in described former figure, each pixel after process is merged into image corresponding to described former figure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410138449.4A CN104978712B (en) | 2014-04-08 | 2014-04-08 | Image processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410138449.4A CN104978712B (en) | 2014-04-08 | 2014-04-08 | Image processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104978712A true CN104978712A (en) | 2015-10-14 |
| CN104978712B CN104978712B (en) | 2019-08-16 |
Family
ID=54275192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410138449.4A Active CN104978712B (en) | 2014-04-08 | 2014-04-08 | Image processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104978712B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780295A (en) * | 2016-11-28 | 2017-05-31 | 努比亚技术有限公司 | Image processing method and device |
| CN111784698A (en) * | 2020-07-02 | 2020-10-16 | 广州信瑞医疗技术有限公司 | Image self-adaptive segmentation method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6895127B1 (en) * | 1999-09-10 | 2005-05-17 | Arcsoft, Inc. | Photomontage using multiple layer placement and color variation |
| CN101655978A (en) * | 2008-08-21 | 2010-02-24 | 英华达(上海)电子有限公司 | Method and device for image analysis |
| CN103366352A (en) * | 2012-03-30 | 2013-10-23 | 北京三星通信技术研究有限公司 | Device and method for producing image with background being blurred |
-
2014
- 2014-04-08 CN CN201410138449.4A patent/CN104978712B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6895127B1 (en) * | 1999-09-10 | 2005-05-17 | Arcsoft, Inc. | Photomontage using multiple layer placement and color variation |
| CN101655978A (en) * | 2008-08-21 | 2010-02-24 | 英华达(上海)电子有限公司 | Method and device for image analysis |
| CN103366352A (en) * | 2012-03-30 | 2013-10-23 | 北京三星通信技术研究有限公司 | Device and method for producing image with background being blurred |
Non-Patent Citations (1)
| Title |
|---|
| 王平江等: "激光焊接对接拼缝测量的微景深方法", 《中国图象图形学报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780295A (en) * | 2016-11-28 | 2017-05-31 | 努比亚技术有限公司 | Image processing method and device |
| CN106780295B (en) * | 2016-11-28 | 2020-12-18 | 努比亚技术有限公司 | Picture processing method and device |
| CN111784698A (en) * | 2020-07-02 | 2020-10-16 | 广州信瑞医疗技术有限公司 | Image self-adaptive segmentation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104978712B (en) | 2019-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9053540B2 (en) | Stereo matching by census transform and support weight cost aggregation | |
| CN103235949B (en) | Image point of interest detection method and device | |
| US9519996B2 (en) | Virtual view generating method and apparatus | |
| CN104794685B (en) | A kind of method and device for realizing image denoising | |
| CN107749987B (en) | Digital video image stabilization method based on block motion estimation | |
| CN110458772B (en) | Point cloud filtering method and device based on image processing and storage medium | |
| US20230252664A1 (en) | Image Registration Method and Apparatus, Electronic Apparatus, and Storage Medium | |
| CN107563974B (en) | Image denoising method and device, electronic equipment and storage medium | |
| WO2010050911A1 (en) | Method and system for image resizing based on interpolation enhanced seam operations | |
| CN105389165A (en) | Document picture display method and apparatus, and terminal | |
| CN109636730B (en) | Method for filtering pseudo pixels in a depth map | |
| CN104794756A (en) | Mapping system and method of point clouds model | |
| CN111402170A (en) | Image enhancement method, device, terminal and computer readable storage medium | |
| CN111127303A (en) | Background blurring method and device, terminal equipment and computer readable storage medium | |
| US11368661B2 (en) | Image synthesis method, apparatus and device for free-viewpoint | |
| CN114049499A (en) | Target object detection method, apparatus and storage medium for continuous contour | |
| US8295647B2 (en) | Compressibility-aware media retargeting with structure preserving | |
| CN110827301B (en) | Method and apparatus for processing image | |
| CN106384071A (en) | Two-dimensional code scanning recognition processing method and device | |
| CN113506305B (en) | Image enhancement method, semantic segmentation method and device for three-dimensional point cloud data | |
| KR20160130455A (en) | Animation data generating method, apparatus, and electronic device | |
| CN104952089A (en) | Image processing method and image processing system | |
| CN104978712A (en) | Image processing method and device | |
| CN106204455A (en) | A kind of image processing method with multiple filtering effects and system thereof | |
| CN116468632A (en) | Grid denoising method and device based on self-adaptive feature preservation |
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 |