CN1856035A - System and method for processing serial stream of cartoons - Google Patents
System and method for processing serial stream of cartoons Download PDFInfo
- Publication number
- CN1856035A CN1856035A CNA2005100647008A CN200510064700A CN1856035A CN 1856035 A CN1856035 A CN 1856035A CN A2005100647008 A CNA2005100647008 A CN A2005100647008A CN 200510064700 A CN200510064700 A CN 200510064700A CN 1856035 A CN1856035 A CN 1856035A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- real
- cartoons
- input
- 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
A system and method to process serial image animation, especially the system and the method that is about a real time processing and adjusts the serial image to create the animation, including: a dynamic image input module, a image changing module, a time-change module and a dynamic image output module that is the real-time change of an input dynamic image to create the animation technical effect.
Description
Technical field
The present invention relates to a kind of real-time processing and adjust the crossfire image, particularly with the system and method for a dynamic image real time altering of importing with the generation animation to produce the system and method for animation.
Background technology
In known techniques, the making of image animation roughly comprises following method:
(1), finishes in the Freehandhand-drawing mode according to the needs of the story of a play or opera by the animator.Owing to finish with manual fully, the person of painting needs suitable artistic gift and ability, and common people are difficult to finish.And Production Time is long, needs a few hours usually.
(2), computed software kit produces animation, this type of computer packages is made the principle of animation, basically be to carry out in the mode of permutation and combination, use this type of computer packages to make animation because of not needing too many specialized skills, anyone can be combined into interesting animation soon.But being subject to can be for the unit kind and the quantity of combination, and this type of computer packages is not easy to produce the animation of certain effects, for example, the crossfire making video that takes place is in real time become animation.
(3), use image processing software imaged object progressively to be handled with special function, for example, use distortion filter function among the Adobe PhotoShop with imaged object torsional deformation in addition, to reach the entertaining effect of similar distorting mirror.Make animation in this way, the image processing instrument that must use manually carries out the repeatable operation complexity, the user is necessary for the repertoire of skilled image processing instrument and possesses the professional of aesthstic attainment, all operating procedures are all manually and can't keep, and each imaged object all needs individual treated, the complicated professional knowledge that needs of process, non-common people can arbitrarily finish, and such image processing software there is no the function that the generation animation is provided for the crossfire image of real-time generation, is another serious deficiency of such image processing software.
(4), at our company's another piece patent document " Image-Adjusting System and Method " in, the mode of disclosed deformation of image or processing, though can utilize the mode of continuous processing static image, reach dynamic effect, but because each picture all need be through detecting and the processing of being out of shape, do not utilize the contextual practice each other, usefulness can't be satisfactory on the one hand, and the smoothness of picture all has incomplete place with continuous degree on the other hand.Though in known techniques, gradually, mention the relevant system and method that uses real-time crossfire image with the generation animation, so, this type of uses real-time crossfire image also only to limit with the system and method that produces animation and handles and export for the universe of real-time imaging object image, can't be at the part zone of real-time imaging object image, handle and export as prospect or background, also can't carry out audio-visual synchronous or audio-visual synthetic processing, so such system and method still has locating that many utmost points need improve to image with sound.
Therefore, at the problems referred to above and defective, the present invention proposes a kind of System and method for of processing serial stream of cartoons of innovation, and not only can improve needs the complicated image processing instrument and the defective of professional artistic accomplishment in the known techniques, also can produce animation at the crossfire image of real-time generation.
Summary of the invention
The purpose of this invention is to provide a kind of system and method for handling serial stream of cartoons, particularly relevant a kind of real-time processing is also adjusted the crossfire image to produce the system and method for animation.
If present disclosure is by becoming a module and a dynamic image output module in a dynamic image input module, image change module, a period of time with the technique effect of a dynamic image real time altering of importing with the generation animation.
The present invention is described in detail below in conjunction with accompanying drawing.
Description of drawings
Fig. 1 is a system architecture diagram of the present invention;
Fig. 2 is the system architecture diagram of one embodiment of the invention;
Fig. 3 is the system architecture diagram of another embodiment of the present invention;
Fig. 4 A to Fig. 4 F is the schematic diagram of one embodiment of the invention;
Fig. 5 A to Fig. 5 C is the schematic diagram of another embodiment of the present invention;
Fig. 6 A to Fig. 6 B is the schematic diagram of another embodiment of the present invention;
Fig. 7 A to Fig. 7 C is the schematic diagram of another embodiment of the present invention;
Fig. 8 A to Fig. 8 C is the schematic diagram of another embodiment of the present invention;
Fig. 9 A to Fig. 9 B is the schematic diagram of another embodiment of the present invention;
Figure 10 is an operational flowchart of the present invention.
Description of reference numerals: 100 the present invention; 101 dynamic image input modules; 102 images change module; Became module at 103 o'clock; 1031 signatures to predict modules; The level and smooth module of 1032 features; 104 dynamic image output modules; 105 image feature cutting modules; 106 acoustic processing modules; 1061 sound input modules; 1062 sound change module; 1063 voice output modules; 107 sound processing modules; 1071 audio-visual synchronization modules; 1072 audio-visual synthesis modules; 1011,1012,1013,1014,1015,1016-step.
Embodiment
See also the system architecture diagram of one embodiment of the invention shown in Figure 1.As shown in Figure 1, a kind of system that handles serial stream of cartoons of the present invention 100 can comprise a dynamic image input module 101, image in order to the input real-time continuous, this image can be serial stream of cartoons, for example import by the image of video camera, perhaps the network video animation of network video meeting also can be an existing dish case image animation, the image animation archives that for example store on the computer; One image changes module 102, in order to according to input image and its characteristic point, carries out the change of image; For the moment become module 103,, change the combination parameter and a dynamic image output module 104 of this deformation of image module, in order to the image of output real-time continuous in order to the foundation time variable.But the real-time imaging of function the present invention's real time altering one input by each module among above the present invention is to produce the animation of real-time continuous.
Please consult the system architecture diagram of another embodiment of the present invention shown in Figure 2 again.As shown in Figure 2, a kind of system that handles serial stream of cartoons of the present invention 100 also can comprise an image feature cutting module 105, in order to each characteristic image of the real-time imaging that separates input, and adjusts this each characteristic image to produce the animation of real-time continuous; One acoustic processing module 106 is in order to handle this voice data when also comprising voice data simultaneously in the real time image data of input; One sound processing module 107 is in order to handle real time image data and voice data.
Become the detailed architecture of module, acoustic processing module and sound processing module when please consulting Fig. 3 again and further describing among the present invention.As shown in Figure 3, become module 103 in the time of among the present invention and also comprise a signatures to predict module 1031, detect and the level and smooth module 1032 of a feature, use so that the feature motion track is more level and smooth in order to supplemental characteristic.Acoustic processing module 106 among the present invention also comprises a sound input module 1061, in order to receive the input of sound; One sound changes module 1062, in order to change the sound of input; And a voice output module 1063, change the sound of finishing in order to output.Sound processing module 107 among the present invention also can comprise an audio-visual synchronization module 1071, carries out synchronous work in order to image data and voice data with output; And an audio-visual synthesis module 1072, synthesize in order to image data and voice data output.
Also can clearly understand the situation of practice of the present invention by following embodiment.Please refer to Fig. 4, by among Fig. 4 as can be known, the portrait of Fig. 4 A is a real-time imaging picture of directly being imported by video camera, the data flow of input is continuous dynamic image, change module by image of the present invention and bring in constant renewal in each zone of change portrait face, cause the dynamic change of shape of face face and expression, produce real-time continuously image output stream, can obtain as the portrait effect as shown among Fig. 4 B, Fig. 4 C, Fig. 4 D, Fig. 4 E and Fig. 4 F.The disclosed technology of the present invention also can be according to the successional difference of the change vector of characteristic locus, and the decision image changes the change parameter of module, allows different change momentum is corresponding to produce different variation effects.
The animation effect that is produced when please refer to hypothesis shown in Figure 5 one woman dizziness.By among Fig. 5 as can be known, the portrait of Fig. 5 A is a real-time imaging picture of directly being imported by video camera, the data flow of input is dynamic continuous image, processing by image feature cutting module of the present invention, change module via image of the present invention again and constantly change each part zone of characteristic image, shifting gears is the change vector according to characteristic point, after corresponding this vector is finished each region deformation, produce real-time continuously image output stream, the effect of generation is shown in Fig. 5 B and Fig. 5 C.
Refer again to the embodiment of explanation shown in Figure 6 real time altering one woman's skin quality of the present invention.By among Fig. 6 as can be known, woman's portrait of Fig. 6 A is that the data flow of input is dynamic continuous image by the direct real-time imaging picture of input of video camera, change module constantly to the specific region by image of the present invention, do image processing as skin area, it is careful to obtain skin matter, colour of skin effect such as whiten.After image processing finishes, further produce real-time continuously image output stream, the effect of generation is shown in Fig. 6 B.
Refer again to the embodiment of explanation shown in Figure 7 real time altering object of the present invention background.By among Fig. 7 as can be known, man's portrait of Fig. 7 A is a real-time imaging picture of directly being imported by video camera, the data flow of input is dynamic continuous image, see through image feature cutting module of the present invention and pick out feature object (portrait) and background video data, change module by image of the present invention again and constantly feature object and background video are carried out image change processing, as change the expression of portrait, highlight and softening theme object (portrait) and change background data etc., after image processing finishes, further produce real-time continuously image output stream, the effect of generation is shown in Fig. 7 B and Fig. 7 C.
Refer again to embodiment shown in Figure 8, the present invention's situation of synthetic virtual objects in real time is described.By among Fig. 8 as can be known, man's portrait of Fig. 8 A is a real-time imaging picture of directly being imported by video camera, the data flow of input is dynamic continuous image, pick out feature object (portrait) by image feature cutting module of the present invention, position according to the feature object, dynamically with the virtual object of desiring to add, as the exaggeration eyeball in this example, via suitable swing offset convergent-divergent, place on the feature object the result is glutinous, and producing real-time continuously image output stream, the effect of generation is shown in Fig. 8 B and Fig. 8 C.The disclosed technology of the present invention also can be according to the successional difference of the change vector of characteristic locus, and the decision image changes the change parameter of module, allows different change momentum is corresponding to use different virtual objects.
Refer again to the embodiment of the explanation interactive virtual object of the present invention of Fig. 9.By among Fig. 9 as can be known, two woman's portraits of Fig. 9 A are real-time imaging pictures of directly being imported by video camera, the data flow of input is dynamic continuous image, isolate feature object and background by image feature cutting module of the present invention, see through image of the present invention again and change behavior and the position that module constantly determines interactive objects, with the sticking zone that places beyond the feature object of result, and produce real-time continuously image output stream, the effect of generation is shown in Fig. 9 B.
Refer again to the operational flowchart of one embodiment of the invention shown in Figure 10.As shown in figure 10, the operating process of one embodiment of the invention comprises following steps at least:
From the above mentioned as can be known, a kind of system and method for handling serial stream of cartoons of the present invention, by a dynamic image input module, in order to the input real-time imaging, this image can be real-time crossfire continuous animation image, for example import by the image of video camera, the perhaps network video animation of network video meeting, also can be an existing animation archives image, change module via an image again, carrying out image changes, or the prospect and the background of separating this input real-time imaging through an image feature cutting module, via becoming module for the moment,, change the combination parameter of deformation of image module again in order to the foundation time variable, at last again via a dynamic image output module, the real-time continuous image of finishing in order to output.Function the present invention by each above module can separate the characteristic image in the image, and adjusts each characteristic image to produce the animation of real-time continuous.The present invention not only can improve needs the complicated image processing instrument and the shortcoming of professional artistic accomplishment in the known technology, also can produce animation at the crossfire image of real-time generation.
The above only is preferred embodiment of the present invention, can not be used for limiting scope of the invention process.Therefore, all equalizations of doing according to claim of the present invention changes and modifies, and all should still belong to protection scope of the present invention.
Claims (18)
1, a kind of system that handles serial stream of cartoons comprises:
One dynamic image input module is in order to the image of input real-time continuous;
One image changes module, in order to change the real-time continuous image of this input;
For the moment become module,, change the combination parameter that this image changes module in order to the foundation time variable; And
One dynamic image output module is in order to export the image that changes the real-time continuous of finishing.
2, a kind of system that handles serial stream of cartoons comprises:
One dynamic image input module is in order to the image of input real-time continuous;
One image feature cutting module is in order to separate the feature object or the characteristic area of this input real-time continuous image;
One image changes module, in order to this feature object or the characteristic area of the real-time continuous image that changes this input;
For the moment become module,, change the combination parameter that this image changes module in order to the foundation time variable; And
One dynamic image output module is in order to export the image that changes the real-time continuous of finishing.
3, a kind of system that handles serial stream of cartoons as claimed in claim 1 or 2 wherein also comprises an acoustic processing module, in order to handle voice data.
4, a kind of system that handles serial stream of cartoons as claimed in claim 3, this acoustic processing module wherein becomes module when changing module and this according to this image and produces.
5, a kind of system that handles serial stream of cartoons as claimed in claim 3 wherein also comprises a sound processing module, in order to handle this real time image data and this voice data.
6, a kind of system that handles serial stream of cartoons as claimed in claim 1 or 2, wherein should the time become module and also comprise a signatures to predict module, detect in order to supplemental characteristic; And the level and smooth module of a feature, use so that the feature motion track is more level and smooth.
7, a kind of system that handles serial stream of cartoons as claimed in claim 3, wherein this acoustic processing module also can comprise a sound input module, in order to receive the input of sound; One sound changes module, in order to change the sound and a voice output module of input, changes the sound of finishing in order to output.
8, a kind of system that handles serial stream of cartoons as claimed in claim 5, wherein this sound processing module also can comprise an audio-visual synchronization module, carry out synchronously or an audio-visual synthesis module in order to image data and voice data, synthesize in order to image data and voice data with output with output.
9, a kind of system that handles serial stream of cartoons as claimed in claim 1 or 2, wherein, the image of the real-time continuous of this input is animated image file or the animated image crossfire that image-taking device produced.
10, a kind of system that handles serial stream of cartoons as claimed in claim 1 or 2, wherein, the image of the real-time continuous of this input is animated image file or the animated image crossfire that the image generating apparatus is produced.
11, a kind of system that handles serial stream of cartoons as claimed in claim 1 or 2, wherein, the image of the real-time continuous of this output can be animated image file or animated image crossfire.
12, a kind of method of handling serial stream of cartoons, it comprises following steps at least:
(a): obtain the real-time continuous image by a dynamic image input module;
(b): use become module a period of time and will transfer the parameter of adjusting this real-time continuous image the time to;
(c): use an image to change module and change this real-time continuous image;
(d): export the real-time continuous image that this change is finished via a dynamic image.
13, a kind of method of handling serial stream of cartoons, it comprises following steps at least:
(a): obtain the real-time continuous image by a dynamic image input module;
(b): use an image feature cutting module, cut at least one characteristic area according to image feature;
(c): utilize an image to change module this characteristic area is carried out image processing and produces at least one characteristic image;
(d): use to become module, the parameter of image processing in different time set-up procedure (c) for the moment;
(e): merge this at least one characteristic image that this adjustment of generation finishes; And
(f): the real-time continuous image after exporting this at least one each characteristic image that this adjustment finishes and coincide via a dynamic image output module.
14, as claim 12 or 13 described a kind of methods of handling serial stream of cartoons, wherein, when comprising voice data in the real-time continuous image of this input, this method also comprises a step in order to handle this real-time imaging and this voice data.
15, a kind of method of handling serial stream of cartoons as claimed in claim 14, wherein the method for this real-time imaging of this processing and this voice data comprises audio-visual synchronous or audio-visual synthetic.
16, as claim 12 or 13 described a kind of methods of handling serial stream of cartoons, wherein, the image of the real-time continuous of this input is animated image file or the animated image crossfire that image-taking device produced.
17, as claim 12 or 13 described a kind of methods of handling serial stream of cartoons, wherein, the image of the real-time continuous of this input is animated image file or the animated image crossfire that the image generating apparatus is produced.
18, as claim 12 or 13 described a kind of methods of handling serial stream of cartoons, wherein, the real-time continuous image of this output is animated image file or animated image crossfire.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2005100647008A CN1856035A (en) | 2005-04-20 | 2005-04-20 | System and method for processing serial stream of cartoons |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2005100647008A CN1856035A (en) | 2005-04-20 | 2005-04-20 | System and method for processing serial stream of cartoons |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN1856035A true CN1856035A (en) | 2006-11-01 |
Family
ID=37195820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2005100647008A Pending CN1856035A (en) | 2005-04-20 | 2005-04-20 | System and method for processing serial stream of cartoons |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1856035A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102157006A (en) * | 2010-02-11 | 2011-08-17 | 三星电子株式会社 | Method and apparatus for producing dynamic effect of character capable of interacting with image |
-
2005
- 2005-04-20 CN CNA2005100647008A patent/CN1856035A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102157006A (en) * | 2010-02-11 | 2011-08-17 | 三星电子株式会社 | Method and apparatus for producing dynamic effect of character capable of interacting with image |
| CN102157006B (en) * | 2010-02-11 | 2016-08-03 | 三星电子株式会社 | The method and apparatus of the dynamic effect of the role that generation can interact with image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cao et al. | Expressive speech-driven facial animation | |
| JP5344358B2 (en) | Face animation created from acting | |
| US5734794A (en) | Method and system for voice-activated cell animation | |
| CN107197385A (en) | A kind of real-time virtual idol live broadcasting method and system | |
| US8655152B2 (en) | Method and system of presenting foreign films in a native language | |
| US7791608B2 (en) | System and method of animating a character through a single person performance | |
| JPH11219446A (en) | Video/sound reproducing system | |
| CN1639738A (en) | Method and system for generating caricaturized talking heads | |
| CN112562722A (en) | Audio-driven digital human generation method and system based on semantics | |
| US20080165195A1 (en) | Method, apparatus, and software for animated self-portraits | |
| WO2018006377A1 (en) | Holographic projection system and method for real-time interactive animation, and artificial intelligence robot | |
| King et al. | Creating speech-synchronized animation | |
| CN101069417A (en) | Image processing method, image processing apparatus, image processing program, and image file format | |
| WO2009154821A1 (en) | Method and apparatus for providing natural facial animation | |
| JP2003529861A (en) | A method for animating a synthetic model of a human face driven by acoustic signals | |
| CN1547131A (en) | Virtual reality interactive control system | |
| Hong et al. | iFACE: a 3D synthetic talking face | |
| CN1856035A (en) | System and method for processing serial stream of cartoons | |
| King et al. | An anatomically-based 3D parametric lip model to support facial animation and synchronized speech | |
| JP3014647B2 (en) | Electronic kaleidoscope device | |
| CN1834984A (en) | Method of automatic generating amusing head picture by utilizing human face detection tech | |
| CN1462982A (en) | Intelligent method and system for creating motion pictures | |
| CN1477602A (en) | Cartoon making method and equipment | |
| CN113436302A (en) | Face animation synthesis method and system | |
| CN113362432A (en) | Facial animation generation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |