CN105787995B - A kind of graphical image plane processing method - Google Patents
A kind of graphical image plane processing method Download PDFInfo
- Publication number
- CN105787995B CN105787995B CN201610052897.1A CN201610052897A CN105787995B CN 105787995 B CN105787995 B CN 105787995B CN 201610052897 A CN201610052897 A CN 201610052897A CN 105787995 B CN105787995 B CN 105787995B
- Authority
- CN
- China
- Prior art keywords
- image
- music
- picture
- snatch
- threedimensional model
- 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.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/44—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of graphical image plane processing methods, include the following steps：The extraction of picture edge characteristic point will be carried out after the pretreatment of image, accurate surface model is then rebuild according to the characteristic point of edge extracting；The surface model of gained and a series of taken photochromes in kind are subjected to accuracy registration, obtain threedimensional model；According to the RGB data of the threedimensional model of acquisition and alpha channel datas, the PNG format data of gained threedimensional model are generated, and extract the RGB data and alpha channel datas of gained threedimensional model, generate the BMP formats being inserted into video；PNG format data based on gained threedimensional model generate the animation with background music and background picture according to determining switching instant.Picture can be converted into dynamic threedimensional model by the present invention, then perfectly be combined together background music, background picture, 3-D effect, provide feeling of immersion true to nature to the user.
Description
Technical field
The present invention relates to graph processing technique fields, and in particular to a kind of graphical image plane processing method.
Background technology
With the maturation of electronic technology, more digital products generate, the number such as digital camera, tablet computer, smart mobile phone
Code product prevalence with it is universal, be the numerous common people bring great convenience.In daily life, people are recorded using digital product
The drop of life, a wedding, primary travelling or certain party, digital product is used by people to take pictures, recorded video, with note
Course of life is recorded, but people but have no way of arranging for photo at random；For needing to record the people recorded that oneself grow up, but not
Photo, the video of former years on the same day can be found in time, and synthesis can not be compared；For in travelling, different cameral takes same
The photo of one position but can not classifying intelligently etc..
Video production can effectively arrange the materials such as rambling picture and video to together, and people will be facilitated quick
Generate photo and video that life growth record either Auto-matching arranges certain travelling.Video production application is very extensive,
The not only communication spheres such as video display, network have demand, and for today of scientific and technological high speed development, there is also to video by ordinary user
The demand of making.Simple video production system effectively arranges the daily photo and video content recorded by public users,
It is regular to draw class, a series of picture of themes is synthesized with video-splicing, forms theme.
The product for being made of video many splicing pictures at present, can be formed by way of adding music with music
Video so that be accompanied by background music in the process of picture playing, but widespread practice is that one section of selection is complete at present
A part for snatch of music is inserted directly into video, and the playing duration per pictures is distributed equally according to video total duration,
So that the correlation of the picture playing effect and snatch of music in the video that user spells out is relatively low, cannot by picture playing and
Musical features carry out depth combination, therefore seem very flat, and user experience is poor.And the use of background picture, and adopt
With direct-insert mode, combination degree is poor.
Invention content
To solve the above problems, the present invention provides a kind of graphical image plane processing method, picture can be converted into
Then background music, background picture, 3-D effect are perfectly combined together, provide to the user by dynamic threedimensional model
Feeling of immersion true to nature.
To achieve the above object, the technical solution that the present invention takes is：
A kind of graphical image plane processing method, includes the following steps：
S1, the distribution of statistics of histogram gradation of image is established, enhances picture contrast by being segmented grey linear transformation
Afterwards, it is smoothed using gaussian filtering, completes the pretreatment of image；
S2, the extraction that picture edge characteristic point is completed using Canny operators；
S3, pass through between coordinate system by the characteristic point of edge extracting and by the collected range information of auxiliary laser rangefinder
Conversion calculate 3 d space coordinate point, and these 3 d space coordinate points are shown in OpenGL, are rebuild accurate
Surface model tentatively generates 3-D effect；
S4, the boundary image A and B for obtaining gained surface model and a series of taken photochromes in kind,
And obtained boundary image A and B are registrated in advance, rough spatial transformation parameter is obtained, the spatial transformation parameter includes
The angle that floating image is rotated relative to template image, floating image relative to template image X-axis and Y-axis displacement；
S5, the rough spatial transformation parameter obtained by S4 are corrected the boundary image B of floating image, then lead to
The analysis for crossing the second differnce of generalized Hausdorff distance removes extra boundary point, obtains new floating image boundary C；
S6, boundary image B and new floating image boundary image C are accurately matched using mean Hausdorff distance
Standard obtains accurate spatial transformation parameter；
S7, step S5-S6 is repeated, so that accurate spatial transformation parameter is reached the required accuracy, obtains threedimensional model；
S8, the RGB data for obtaining gained threedimensional model, and according to the transparent background drawn gained threedimensional model, obtain
The a l pha channel datas of gained threedimensional model；
S9, according to gained threedimensional model RGB data and alpha channel datas, generate the PNG format number of gained threedimensional model
According to；
The RGB data and alpha channel datas of S10, the threedimensional model obtained by the PNG format extracting data, and root
The BMP formats being inserted into video are generated according to above-mentioned two data；
The snatch of music and background picture of S11, acquisition for generating video, and to the spy of the snatch of music and background picture
Sign is analyzed, and characteristic time is obtained；
S12, the characteristic time based on acquisition determine the switching instant of snatch of music and background picture, while determination is used for
Generate switching instant of each pictures in snatch of music and background picture in the picture of video；
S13, the PNG format data based on gained threedimensional model, according to determining switching instant, generate band background music and
The animation of background picture.
Preferably, the specific steps of step S11 include：It obtains snatch of music and background picture and obtains its different moments
Characteristic value；According to scheduled characteristic value siding-to-siding block length, at least one characteristic value section of snatch of music and background picture is determined；
According to scheduled characteristic value span order, selected successively according to the sequence of characteristic value from big to small from least one characteristic value section
The 5th group of characteristic value is taken, wherein quantity at the time of corresponding to the characteristic value in the 5th group of characteristic value is n-1, n is for generating
The quantity of the picture of video；It will make at the time of each characteristic value is corresponding in snatch of music and background picture in 5th group of characteristic value
It is characterized the moment.
Preferably, switching time of each pictures in the snatch of music is more than 0 in the picture for generating animation.
Preferably, in the characteristic time of acquisition, it is located at first characteristic time on snatch of music and the snatch of music
At the beginning of carve the distance between be not less than first threshold.
Preferably, in the characteristic time of acquisition, it is located at first characteristic time on background picture and the snatch of music
At the beginning of carve the distance between be not less than first threshold.
Preferably, the step S2 the specific steps are：Calculate gradient magnitude and the direction of each pixel；And utilize gained
Gradient magnitude, direction realize retain the maximum point of partial gradient, that is, inhibit the point of non-maximum, obtain accurate edge；So
Dual-threshold voltage is used to reduce false amount of edge afterwards.
Preferably, the process of inhibition of the non-maxima suppression includes：The direction of gradient is divided into four regions, this four
A region marked as 0~3, each area is compared with neighbouring different pixels, to obtain local maximum.
Preferably, the dual threashold value-based algorithm detection process includes：Two threshold value M1 are arranged to the image of non-maxima suppression
And M2, and 2M1 ≈ M2；Grey scale pixel value Grad less than M1 assigns zero, obtains retaining that marginal information is more, noise is larger
Image P1；Equally Grad less than M2 grey scale pixel value assign zero, since the threshold value of M2 is larger, obtain false marginal information it is few,
The smaller image P2 of noise, is linked to be profile in image P2 by edge, when reaching the endpoint of profile, constantly in image P1
Lookup may be coupled to the edge on profile, until connecting P2.
The invention has the advantages that：
Picture can be converted into dynamic threedimensional model, it is then that background music, background picture, 3-D effect is perfect
It is combined together, has provided feeling of immersion true to nature to the user.
Specific implementation mode
In order to make objects and advantages of the present invention be more clearly understood, the present invention is carried out with reference to embodiments further
It is described in detail.It should be appreciated that specific implementation described herein is only used to explain the present invention, it is not intended to limit the present invention.
An embodiment of the present invention provides a kind of graphical image plane processing methods, include the following steps：
A kind of graphical image plane processing method, includes the following steps：
S1, the distribution of statistics of histogram gradation of image is established, enhances picture contrast by being segmented grey linear transformation
Afterwards, it is smoothed using gaussian filtering, completes the pretreatment of image；
S2, the extraction that picture edge characteristic point is completed using Canny operators；
S3, pass through between coordinate system by the characteristic point of edge extracting and by the collected range information of auxiliary laser rangefinder
Conversion calculate 3 d space coordinate point, and these 3 d space coordinate points are shown in OpenGL, are rebuild accurate
Surface model tentatively generates 3-D effect；
S4, the boundary image A and B for obtaining gained surface model and a series of taken photochromes in kind,
And obtained boundary image A and B are registrated in advance, rough spatial transformation parameter is obtained, the spatial transformation parameter includes
The angle that floating image is rotated relative to template image, floating image relative to template image X-axis and Y-axis displacement；
S5, the rough spatial transformation parameter obtained by S4 are corrected the boundary image B of floating image, then lead to
The analysis for crossing the second differnce of generalized Hausdorff distance removes extra boundary point, obtains new floating image boundary C；
S6, boundary image B and new floating image boundary image C are accurately matched using mean Hausdorff distance
Standard obtains accurate spatial transformation parameter；
S7, step S5-S6 is repeated, so that accurate spatial transformation parameter is reached the required accuracy, obtains threedimensional model；
S8, the RGB data for obtaining gained threedimensional model, and according to the transparent background drawn gained threedimensional model, obtain
The alpha channel datas of gained threedimensional model；
S9, according to gained threedimensional model RGB data and alpha channel datas, generate the PNG format number of gained threedimensional model
According to；
The RGB data and alpha channel datas of S10, the threedimensional model obtained by the PNG format extracting data, and root
The BMP formats being inserted into video are generated according to above-mentioned two data；
The snatch of music and background picture of S11, acquisition for generating video, and to the spy of the snatch of music and background picture
Sign is analyzed, and characteristic time is obtained；
S12, the characteristic time based on acquisition determine the switching instant of snatch of music and background picture, while determination is used for
Generate switching instant of each pictures in snatch of music and background picture in the picture of video；
S13, the PNG format data based on gained threedimensional model, according to determining switching instant, generate band background music and
The animation of background picture.
The specific steps of step S11 include：Obtain snatch of music and background picture and the characteristic value for obtaining its different moments；
According to scheduled characteristic value siding-to-siding block length, at least one characteristic value section of snatch of music and background picture is determined；According to pre-
Fixed characteristic value span order chooses the 5th from least one characteristic value section according to the sequence of characteristic value from big to small successively
Characteristic value is organized, wherein quantity at the time of corresponding to the characteristic value in the 5th group of characteristic value is n-1, n is for generating video
The quantity of picture；Using at the time of each characteristic value is corresponding in snatch of music and background picture in the 5th group of characteristic value as feature
Moment.
Switching time of each pictures in the snatch of music is more than 0 in picture for generating animation.
In the characteristic time of acquisition, at the beginning of being located at first characteristic time and the snatch of music on snatch of music
The distance between quarter is not less than first threshold.
In the characteristic time of acquisition, at the beginning of being located at first characteristic time and the snatch of music on background picture
The distance between quarter is not less than first threshold.
The step S2 the specific steps are：Calculate gradient magnitude and the direction of each pixel；And utilize the gradient of gained
Amplitude, direction, which are realized, retains the maximum point of partial gradient, that is, inhibits the point of non-maximum, obtain accurate edge；Then it uses
Dual-threshold voltage reduces false amount of edge.
The process of inhibition of the non-maxima suppression includes：The direction of gradient is divided into four regions, thisFourA region
Marked as 0~3, each area is compared with neighbouring different pixels, to obtain local maximum.
The dual threashold value-based algorithm detection process includes：Two threshold values M1 and M2 are arranged to the image of non-maxima suppression, and
2M1≈M2；Grey scale pixel value Grad less than M1 assigns zero, obtains retaining the image P1 that marginal information is more, noise is larger；
Grey scale pixel value equally Grad less than M2 assigns zero, since the threshold value of M2 is larger, obtains that false marginal information is few, noise is smaller
Image P2, edge is linked to be profile in image P2, when reaching the endpoint of profile, constantly being searched in image P1 can be with
It is connected to the edge on profile, until connecting P2.
Wherein, the characteristic time of snatch of music is decibel feature or frequecy characteristic or tonality feature, the feature of background picture
For color characteristic or textural characteristics or shape feature or spatial relation characteristics.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the principle of the present invention, it can also make several improvements and retouch, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (8)
1. a kind of graphical image plane processing method, which is characterized in that include the following steps：
S1, the distribution of statistics of histogram gradation of image is established, after being segmented grey linear transformation enhancing picture contrast, made
It is smoothed with gaussian filtering, completes the pretreatment of image；
S2, the extraction that picture edge characteristic point is completed using Canny operators；
S3, pass through turn between coordinate system by the characteristic point of edge extracting and by the collected range information of auxiliary laser rangefinder
Change and calculate 3 d space coordinate point, and these 3 d space coordinate points are shown in OpenGL, rebuilds accurate surface
Model tentatively generates 3-D effect；
S4, the boundary image A and B for obtaining gained surface model and a series of taken photochromes in kind, and it is right
Obtained boundary image A and B is registrated in advance, obtains rough spatial transformation parameter, and the spatial transformation parameter includes floating
The angle that image is rotated relative to template image, floating image relative to template image X-axis and Y-axis displacement；
S5, the rough spatial transformation parameter obtained by S4 are corrected the boundary image B of floating image, then by wide
The analysis of the second differnce of adopted Hausdorff distances, removes extra boundary point, obtains new floating image boundary C；
S6, accuracy registration is carried out to boundary image B and new floating image boundary image C using mean Hausdorff distance, obtained
To accurate spatial transformation parameter；
S7, step S5-S6 is repeated, so that accurate spatial transformation parameter is reached the required accuracy, obtains threedimensional model；
S8, the RGB data for obtaining gained threedimensional model, and according to the transparent background drawn gained threedimensional model, obtain gained
The alpha channel datas of threedimensional model；
S9, according to gained threedimensional model RGB data and alpha channel datas, generate the PNG format data of gained threedimensional model；
The RGB data and alpha channel datas of S10, the threedimensional model obtained by the PNG format extracting data, and according to upper
It states two data and generates the BMP formats being inserted into video；
S11, obtain snatch of music and background picture for generating video, and to the feature of the snatch of music and background picture into
Row analysis, obtains characteristic time；
S12, the characteristic time based on acquisition determine the switching instant of snatch of music and background picture, while determining for generating
Switching instant of each pictures in snatch of music and background picture in the picture of video；
S13, the PNG format data based on gained threedimensional model generate band background music and background according to determining switching instant
The animation of picture.
2. a kind of graphical image plane processing method according to claim 1, which is characterized in that the specific step of step S11
Suddenly include：Obtain snatch of music and background picture and the characteristic value for obtaining its different moments；It is long according to scheduled characteristic value section
Degree, determines at least one characteristic value section of snatch of music and background picture；According to scheduled characteristic value span order, successively
The 5th group of characteristic value is chosen according to the sequence of characteristic value from big to small from least one characteristic value section, wherein the 5th group of feature
Quantity at the time of corresponding to characteristic value in value is n-1, and n is the quantity of the picture for generating video；By the 5th group of feature
As characteristic time at the time of each characteristic value is corresponding in snatch of music and background picture in value.
3. a kind of graphical image plane processing method according to claim 1, which is characterized in that the figure for generating animation
Switching time of each pictures in the snatch of music is more than 0 in piece.
4. a kind of graphical image plane processing method according to claim 1, which is characterized in that the characteristic time of acquisition
In, it is not less than first at the distance between quarter at the beginning of first characteristic time and the snatch of music on snatch of music
Threshold value.
5. a kind of graphical image plane processing method according to claim 1, which is characterized in that the characteristic time of acquisition
In, it is not less than first at the distance between quarter at the beginning of first characteristic time and the snatch of music on background picture
Threshold value.
6. a kind of graphical image plane processing method according to claim 1, which is characterized in that the step S2's is specific
Step is：Calculate gradient magnitude and the direction of each pixel；And it utilizes the gradient magnitude of gained, direction to realize and retains partial gradient
It is maximum, that is, inhibit the point of non-maximum, obtains accurate edge；Then dual-threshold voltage is used to reduce false amount of edge.
7. a kind of graphical image plane processing method according to claim 6, which is characterized in that the non-maxima suppression
Process of inhibition include：The direction of gradient is divided into four regions, this four regions marked as 0~3, each area with it is neighbouring
Different pixels be compared, to obtain local maximum.
8. a kind of graphical image plane processing method according to claim 6, which is characterized in that the dual threashold value-based algorithm inspection
Survey process includes：Two threshold values M1 and M2, and 2M1 ≈ M2 are arranged to the image of non-maxima suppression；Grad less than M1's
Grey scale pixel value assigns zero, obtains retaining the image P1 that marginal information is more, noise is larger；Equally Grad is less than the pixel of M2
Gray value assigns zero, since the threshold value of M2 is larger, the image P2 that false marginal information is few, noise is smaller is obtained, by side in image P2
Edge is linked to be profile, when reaching the endpoint of profile, is constantly searched in image P1 and may be coupled to the edge on profile, until
Until P2 is connected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610052897.1A CN105787995B (en) | 2016-01-17 | 2016-01-17 | A kind of graphical image plane processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610052897.1A CN105787995B (en) | 2016-01-17 | 2016-01-17 | A kind of graphical image plane processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105787995A CN105787995A (en) | 2016-07-20 |
| CN105787995B true CN105787995B (en) | 2018-09-28 |
Family
ID=56403141
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610052897.1A Expired - Fee Related CN105787995B (en) | 2016-01-17 | 2016-01-17 | A kind of graphical image plane processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105787995B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101831138B1 (en) | 2016-05-27 | 2018-02-22 | 주식회사 시어스랩 | Method and apparatus for manufacturing animation sticker using video |
| CN106557328B (en) * | 2016-11-29 | 2020-12-15 | 芜湖美智空调设备有限公司 | Method, system and client for realizing transition animation of household appliance |
| CN110544311B (en) * | 2018-05-29 | 2023-04-25 | 百度在线网络技术（北京）有限公司 | Security warning method, device and storage medium |
| CN109554894B (en) * | 2018-11-30 | 2020-12-08 | 安徽省华腾农业科技有限公司经开区分公司 | Children's garment care solution release platform |
| CN114821011A (en) * | 2022-04-11 | 2022-07-29 | 北京沃东天骏信息技术有限公司 | Dynamic picture generation method and device |
| CN116437063A (en) * | 2023-06-15 | 2023-07-14 | 广州科伊斯数字技术有限公司 | Three-dimensional image display system and method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007085950A3 (en) * | 2006-01-27 | 2007-10-18 | Imax Corp | Methods and systems for digitally re-mastering of 2d and 3d motion pictures for exhibition with enhanced visual quality |
| CN101216949A (en) * | 2008-01-14 | 2008-07-09 | 浙江大学 | A 3D face animation manufacturing method based on region segmentation and segmented learning |
| CN101339668A (en) * | 2008-08-08 | 2009-01-07 | 浙江大学 | Three-dimensional animations cartoon flame creation method |
| CN102231209A (en) * | 2011-04-19 | 2011-11-02 | 浙江大学 | Two-dimensional character cartoon generating method based on isomerism feature dimensionality reduction |
| CN103426195A (en) * | 2013-09-09 | 2013-12-04 | 天津常青藤文化传播有限公司 | Method for generating three-dimensional virtual animation scenes watched through naked eyes |
| CN104915978A (en) * | 2015-06-18 | 2015-09-16 | 天津大学 | Realistic animation generation method based on Kinect |
-
2016
- 2016-01-17 CN CN201610052897.1A patent/CN105787995B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007085950A3 (en) * | 2006-01-27 | 2007-10-18 | Imax Corp | Methods and systems for digitally re-mastering of 2d and 3d motion pictures for exhibition with enhanced visual quality |
| CN101216949A (en) * | 2008-01-14 | 2008-07-09 | 浙江大学 | A 3D face animation manufacturing method based on region segmentation and segmented learning |
| CN101339668A (en) * | 2008-08-08 | 2009-01-07 | 浙江大学 | Three-dimensional animations cartoon flame creation method |
| CN102231209A (en) * | 2011-04-19 | 2011-11-02 | 浙江大学 | Two-dimensional character cartoon generating method based on isomerism feature dimensionality reduction |
| CN103426195A (en) * | 2013-09-09 | 2013-12-04 | 天津常青藤文化传播有限公司 | Method for generating three-dimensional virtual animation scenes watched through naked eyes |
| CN104915978A (en) * | 2015-06-18 | 2015-09-16 | 天津大学 | Realistic animation generation method based on Kinect |
Non-Patent Citations (5)
| Title |
|---|
| Physically based modeling and animation of fire;Duc Quang N 等;《ACM Transactions on Graphics》;20020726;第21卷(第3期);721-728 * |
| 人脸动画方法综述;潘红艳 等;《计算机应用研究》;20080229;第25卷(第2期);327-331 * |
| 基于的交互建模与漫游;杨长寿 等;《云南民族大学学报：自然科学版》;20130430;第21卷(第S1期);51-54 * |
| 烟雾的快速模拟;袁雪霞，尹新富;《计算机工程与设计》;20080531;第29卷(第9期);2394-2396 * |
| 面向普通用户的3D虚拟人脸动画;罗常伟 等;《计算机辅助设计与图形学学报》;20150331;第27卷(第3期);492-498 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105787995A (en) | 2016-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105787995B (en) | A kind of graphical image plane processing method | |
| US20140198101A1 (en) | 3d-animation effect generation method and system | |
| CN104850850B (en) | A kind of binocular stereo vision image characteristic extracting method of combination shape and color | |
| CN108876723B (en) | Method for constructing color background of gray target image | |
| CN103927741B (en) | SAR image synthesis method for enhancing target characteristics | |
| CN108592823B (en) | Decoding method based on binocular vision color stripe coding | |
| CN102074040A (en) | Image processing apparatus, image processing method, and program | |
| CN101287142A (en) | Method for converting flat video to tridimensional video based on bidirectional tracing and characteristic points correction | |
| CN108829711A (en) | A kind of image search method based on multi-feature fusion | |
| CN107609562A (en) | A kind of metric space characteristic detection method based on SIFT algorithms | |
| JP2014016688A (en) | Non-realistic conversion program, device and method using saliency map | |
| KR101896193B1 (en) | Method for converting image into music | |
| CN106296632A (en) | A kind of well-marked target detection method analyzed based on amplitude spectrum | |
| JP5463269B2 (en) | Feature figure addition method, feature figure detection method, feature figure addition device, feature figure detection device, and program | |
| GB2504653A (en) | Vector contour coding methods | |
| Yang et al. | Depth map generation using local depth hypothesis for 2D-to-3D conversion | |
| US20100079448A1 (en) | 3D Depth Generation by Block-based Texel Density Analysis | |
| CN111383340B (en) | Background filtering method, device and system based on 3D image | |
| CN103888749A (en) | Method for converting double-view video into multi-view video | |
| Liu | An Improved Oil Painting Formation Using Advanced Image Processing | |
| Seo et al. | A Painterly Rendering Based on Stroke Profile and Database. | |
| CN104732505B (en) | A kind of hidden image generation method for recommending stowed position | |
| CN117853365B (en) | Artistic result display method based on computer image processing | |
| CN112070881B (en) | Electromechanical equipment digital reconstruction method and system based on Internet of things | |
| Raviya et al. | Real time depth data refurbishment in frequency domain and 3D modeling map using Microsoft kinect sensor |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180928 Termination date: 20190117 |