CN106791032A - The method and apparatus that still image is converted to dynamic image - Google Patents
The method and apparatus that still image is converted to dynamic image Download PDFInfo
- Publication number
- CN106791032A CN106791032A CN201611088517.6A CN201611088517A CN106791032A CN 106791032 A CN106791032 A CN 106791032A CN 201611088517 A CN201611088517 A CN 201611088517A CN 106791032 A CN106791032 A CN 106791032A
- Authority
- CN
- China
- Prior art keywords
- image
- electronic image
- dynamic
- region
- electronic
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
- H04M1/7243—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages
- H04M1/72439—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages for image or video messaging
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Human Computer Interaction (AREA)
- Computer Networks & Wireless Communication (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses the method and apparatus that a kind of still image is converted to dynamic image.Wherein, the method includes：Obtain electronic image；Obtain one or more characteristic areas in electronic image；Each region in one or more characteristic areas is processed, the corresponding multiple images in each region are obtained；Electronic image multiple images corresponding with each region are processed, the dynamic image that can be played is obtained.The present invention solves prior art and cannot realize that still image Dynamic Announce causes the technical problem of interactivity difference.
Description
Technical field
The present invention relates to image processing field, a kind of method that dynamic image is converted in particular to still image
And device.
Background technology
With the popularization and application of the intelligent electronic devices such as mobile phone, panel computer, especially with the continuous of camera hardware
Upgrading, and face recognition technology maturation, increasing user likes being taken pictures using mobile phone, and mobile phone photograph gradually takes
Taken pictures for camera.Although existing mobile phone photograph technology can carry out some simple treatment to photograph, for example, in photograph
Personage is beautified, is mixed colours, or background is blurred etc., but, the photograph after being processed using these image processing techniques is also
It is still image, interactivity is poor, this entertainment requirements for meeting people is also far from enough.
For above-mentioned problem, effective solution is not yet proposed at present.
The content of the invention
The method and apparatus that a kind of still image is converted to dynamic image are the embodiment of the invention provides, it is existing at least to solve
Having technology cannot realize that still image Dynamic Announce causes the technical problem of interactivity difference.
One side according to embodiments of the present invention, there is provided a kind of method that still image is converted to dynamic image, bag
Include：Obtain electronic image；Obtain one or more characteristic areas in electronic image；It is every in one or more characteristic areas
Individual region is processed, and obtains the corresponding multiple images in each region；To electronic image multiple images corresponding with each region
Processed, obtained the dynamic image that can be played.
Another aspect according to embodiments of the present invention, additionally provides the device that a kind of still image is converted to dynamic image,
Including：First acquisition module, for obtaining electronic image；Second acquisition module, for obtaining one or many in electronic image
Individual characteristic area；First processing module, for processing each region in one or more characteristic areas, obtains each
The corresponding multiple images in region；Second processing module, to electronic image multiple images corresponding with each region
Reason, obtains the dynamic image that can be played.
In embodiments of the present invention, by obtaining electronic image；Obtain one or more characteristic areas in electronic image；
Each region in one or more characteristic areas is processed, the corresponding multiple images in each region are obtained；To electronic chart
Picture multiple images corresponding with each region are processed, and obtain the dynamic image that can be played, and have been reached respectively to electronic chart
One or more characteristic areas as in are processed, and obtain the purpose of the dynamic image of whole electronic image, it is achieved thereby that
By the technique effect of still image Dynamic Announce, so solve prior art cannot realize still image Dynamic Announce cause hand over
The technical problem of mutual property difference.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this hair
Bright schematic description and description does not constitute inappropriate limitation of the present invention for explaining the present invention.In the accompanying drawings：
Fig. 1 is the method flow diagram that a kind of still image according to embodiments of the present invention is converted to dynamic image；
Fig. 2 is a kind of schematic diagram of cartoon figure's image shown on smart mobile phone according to embodiments of the present invention；
Fig. 3 is the method flow diagram that a kind of optional still image according to embodiments of the present invention is converted to dynamic image；
Fig. 4 is the method flow diagram that a kind of optional still image according to embodiments of the present invention is converted to dynamic image；
Fig. 5 is the method flow diagram that a kind of optional still image according to embodiments of the present invention is converted to dynamic image；
Fig. 6 is the signal that a kind of child shown on smart mobile phone according to embodiments of the present invention knows graph card picture
Figure；
Fig. 7 is the method flow diagram that a kind of optional still image according to embodiments of the present invention is converted to dynamic image；
Fig. 8 is the method flow diagram that a kind of optional still image according to embodiments of the present invention is converted to dynamic image；
Fig. 9 is the method flow diagram that a kind of optional still image according to embodiments of the present invention is converted to dynamic image；
Figure 10 is the method flow diagram that a kind of optional still image according to embodiments of the present invention is converted to dynamic image；
Figure 11 is the method flow diagram that a kind of optional still image according to embodiments of the present invention is converted to dynamic image；
Figure 12 is that one kind according to embodiments of the present invention preferably realizes that still image moves up method flow diagram；And
Figure 13 is the schematic device that a kind of still image according to embodiments of the present invention is converted to dynamic image.
Specific embodiment
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, is clearly and completely described to the technical scheme in the embodiment of the present invention, it is clear that described embodiment is only
The embodiment of a part of the invention, rather than whole embodiments.Based on the embodiment in the present invention, ordinary skill people
The every other embodiment that member is obtained under the premise of creative work is not made, should all belong to the model of present invention protection
Enclose.
It should be noted that term " first ", " in description and claims of this specification and above-mentioned accompanying drawing
Two " it is etc. for distinguishing similar object, without for describing specific order or precedence.It should be appreciated that so using
Data can exchange in the appropriate case, so as to embodiments of the invention described herein can with except illustrating herein or
Order beyond those of description is implemented.Additionally, term " comprising " and " having " and their any deformation, it is intended that cover
Lid is non-exclusive to be included, for example, the process, method, system, product or the equipment that contain series of steps or unit are not necessarily limited to
Those steps or unit clearly listed, but may include not list clearly or for these processes, method, product
Or other intrinsic steps of equipment or unit.
Embodiment 1
According to embodiments of the present invention, there is provided a kind of still image is converted to the embodiment of the method for dynamic image, it is necessary to say
It is bright, can be held in the such as one group computer system of computer executable instructions the step of the flow of accompanying drawing is illustrated
OK, and, although show logical order in flow charts, but in some cases, can be with different from order herein
Perform shown or described step.
Fig. 1 is the method flow diagram that a kind of still image according to embodiments of the present invention is converted to dynamic image, such as Fig. 1 institutes
Show, the method comprises the following steps：
Step S102, obtains electronic image；
Step S104, obtains one or more characteristic areas in electronic image；
Step S106, is processed each region in one or more characteristic areas, obtains each region corresponding
Multiple images；
Electronic image multiple images corresponding with each region are processed by step S108, and obtain playing is dynamic
State image.
Used as a kind of optional embodiment, above-mentioned electronic image can be the photo shot by camera head, it is also possible to
It is the picture made by graphics software or drawing tool；In a kind of optional embodiment, above-mentioned electronic image can be intelligence
Photo in equipment (for example, mobile phone, panel computer)；Features described above region can be the destination object in electronic image, also may be used
Being a certain biological characteristic region of destination object；In a kind of optional embodiment, if destination object is people in electronic image
Face, then features described above region can be eyes, face position, nose areas, ear position etc.；Above-mentioned each region correspondence
Multiple images can be corresponding some the row modified-images in above-mentioned each region, in a kind of optional embodiment, can for should
One two field picture of the corresponding dynamic image of characteristic area, if for example, characteristic area is eyes, the eyes are corresponding
Multiple images can for eyes close or opening action a two field picture.Above-mentioned dynamic image can be drawn with audio, video, flash
Deng.Based on above-mentioned steps S102 to S108, after electronic image is got, to electronic image cut etc. operation by electronic chart
As being divided into multiple characteristic areas, one or more characteristic areas in electronic image are then obtained, and in electronic image one
Individual or multiple characteristic areas are processed, and the corresponding multiple images of each characteristic area are obtained, finally to electronic image and electricity
The corresponding multiple images in each region in subgraph enter edlin, so as to obtain playing the dynamic image of display.
In a kind of optional embodiment, by taking mobile phone as an example, the cartoon figure's figure shown on smart mobile phone is illustrated in figure 2
As schematic diagram, user can get piece image by mobile phone, and the image can be that user is shot by the camera of mobile phone
The piece image transferred to piece image, or from mobile phone photo album or downloaded from network.Image as shown in Figure 2
In, the destination object in the image (cartoon person of low position) segmentation can be divided multiple characteristic areas, head, 203 as shown at 201
Shown face position, the neck shown in 205, the arm shown in 207, the waist shown in 209, the lower limb shown in 211, will split
The corresponding multiple images in features described above region afterwards are fabricated to multiple dynamic images by simple algorithm, finally to cartoon person of low position
And the corresponding multiple images of its multiple characteristic area enter edlin, are fabricated to the dynamic image that can be played.When user clicks on
In image during certain characteristic area of cartoon person of low position, the region will be presented corresponding Dynamic Announce effect, for example, working as user's point
Hitting or select the arm 207 of cartoon person of low position, the arm of cartoon person of low position will make various gesture motions；When user clicks on or selects
During the head of cartoon person of low position, the head of cartoon person of low position will be presented shakes the head or puts first-class action；When user clicks on or selection cartoon
The face face position of person of low position, cartoon person of low position can make various expressions；When user clicks on all characteristic areas of cartoon person of low position
During domain, cartoon person of low position can be presented the action such as dancing.
Preferably, the image in above-described embodiment can be the photograph that user is autodyned by mobile phone, and user can be with self-defined
Any one position of ground selection human body, allows the position to carry out Dynamic Announce, so as to obtain interesting take a picture certainly.
From the foregoing, it will be observed that in the above embodiments of the present application, by obtaining one or more characteristic areas in electronic image,
And corresponding each region is processed in electronic image to these characteristic areas, the multiple dynamic of each characteristic area is obtained
One or more characteristic areas in the electronic image and electronic image are finally entered edlin by image file, whole so as to obtain
The dynamic image of individual electronic image, Dynamic Announce is carried out by static electronic image.Easily note, the electronic image can be used
The photo that family camera head shoots, it is also possible to downloaded by the picture of software development or by network or directly transferred from disk
Picture；Characteristic area in above-mentioned electronic image can be destination object in electronic image, can also be destination object
Characteristic portion or one or more regions for arbitrarily being divided to electronic image.By scheme disclosed in above-described embodiment,
Reach one or more characteristic areas in electronic image have been processed respectively, obtained the dynamic image of whole electronic image
Purpose, it is achieved thereby that by the technique effect of still image Dynamic Announce, and then solve prior art and cannot realize static state
Image's dynamic display causes the technical problem of interactivity difference.
In a kind of optional embodiment, as shown in figure 3, processing electronic image image corresponding with each region
May include steps of：
Step S302, according to electronic image multiple images corresponding with each region, obtains the dynamic image that can be played
File；
Step S304, obtains audio file wherein, and audio file is generated by following any one mode：User is directly defeated
Enter voice, or, user input word；
Step S306, dynamic image is obtained according to dynamic image file and audio file.
Used as a kind of optional embodiment, above-mentioned electronic image can be the photo shot by camera head, it is also possible to
It is the picture made by graphics software or drawing tool；Above-mentioned dynamic image can be drawn with audio, video, flash, gif pictures
Deng；In a kind of optional embodiment, by taking the electronic image of the cartoon figure shown in Fig. 2 as an example, the electronic image of the cartoon figure
And the corresponding multiple images in each region in the electronic image, for example, the corresponding figure of nodding of the head 201 of the cartoon figure
The images of multiple expressions such as picture, image of shaking the head, corresponding pleasure, anger, sorrow, happiness in face position 203 of the cartoon figure, the cartoon character
The multiple images of the wobbling action of the corresponding front, rear, left and right four direction of neck 205 of thing, the arm 207 of the cartoon figure
Corresponding the motion images such as to stretch, roll up, the correspondence of waist 209 of the cartoon figure is bent over, straight waist, sway one's hips to the left, sway one's hips to the right
Deng the multiple images of action, and the corresponding dancing of lower limb 211 of the cartoon figure each motion images, according to the cartoon character
The electronic image of thing multiple images corresponding with each characteristic area, combination obtains the dynamic image file that can be played, then
Audio file corresponding with these dynamic images is obtained, so as to these dynamic image files and audio file matching are obtained into corresponding
Dynamic image.
In a kind of optional embodiment, as shown in figure 4, obtain audio file above by the generation of user input word can
To comprise the following steps：
Step S402, obtains the text information of user input；
Step S404, carries out being converted to audio file to text information.
Used as a kind of optional embodiment, above-mentioned text information can be text of the user for the input of above-mentioned dynamic image
Word, by after the corresponding image file of multiple characteristic area is fabricated to dynamic image in electronic image and the electronic image, obtains
The text information corresponding with the electronic image of user input is taken, and these text informations is converted into corresponding audio file,
Such that it is able to when the dynamic image file of electronic image is played, play corresponding audio-frequency information, very impressive dynamic is obtained
Image display effect.
By above-described embodiment, the purpose that audio file is made for dynamic image is realized, such that it is able to meet electronics
The rendering effect of audio element is carried out during the Dynamic Announce of image.
In a kind of optional embodiment, as shown in figure 5, obtaining one or more the characteristic area bags in electronic image
Include：
Step S502, obtains one or more regions that user divides in electronic image；
Step S504, using the image in one or more regions as one or more characteristic areas.
Used as a kind of optional embodiment, above-mentioned electronic image can be the photo shot by camera head, it is also possible to
It is the picture made by graphics software or drawing tool；In a kind of optional embodiment, the electronic image can be such as Fig. 6 institutes
The child that the utilization mobile phone for showing shoots knows the image of graph card piece, will can be divided according to the identification object in figure in the electronic image
It is multiple regions (for example, the electronic image for knowing graph card piece is divided into 12 parts in Fig. 6), and by the corresponding figure in these regions
As the characteristic area as the electronic image.
A kind of optional embodiment, can be fabricated to corresponding Dynamic Graph by the corresponding identification object of above-mentioned 12 parts
Picture, and audio file corresponding with the title of each identification object is made, each identification in the identification card and identification card
The corresponding multiple images of object are fabricated to dynamic image file, and with audio file together as the identification card dynamic shadow
Picture.When any one identification object in child's click recognition card graphic, then corresponding dynamic image and audio letter can be presented
Breath.
In an alternative embodiment, as shown in fig. 7, obtaining one or more the characteristic area bags in electronic image
Include：
Step S702, is identified to the object in electronic image；
Step S704, using one or more parts of object as one or more characteristic areas.
Used as a kind of optional embodiment, above-mentioned electronic image can be the photo shot by camera head, it is also possible to
It is the picture made by graphics software or drawing tool；In a kind of optional embodiment, the electronic image can be such as Fig. 2 institutes
Cartoon figure's image that the utilization mobile phone for showing shoots；Said one or multiple characteristic areas can be the cartoon character shown in Fig. 2
Each position such as head 201, face position 203, neck 205, arm 207, waist 209, the lower limb 211 of thing.
By above-mentioned two embodiment, realize carries out segmentation and is divided into multiple features to electronic image according to certain rule
The purpose in region, corresponding dynamic image file and audio file are made such that it is able to the multiple regions in electronic image.
In a kind of optional embodiment, as shown in figure 8, special using one or more parts of object as one or more
Levying region includes：
Step S802, one or more parts for the object that will identify that show user；
Step S804, receives the editor that user is carried out to one or more parts of object；
Step S806, using one or more parts of the object after editor as one or more characteristic areas.
As a kind of optional embodiment, after being identified to the object in electronic image, the object (example that will identify that
Such as, the cartoon figure shown in Fig. 2) one or more parts (for example, the head 201 of cartoon figure, face position in Fig. 2
203rd, each position such as neck 205, arm 207, waist 209, lower limb 211) user is showed, user can respectively to identifying
One or more parts of object carry out edit operation, the head of cartoon figure can be replaced as another cartoon character
The head of thing, or the corresponding site of another cartoon figure is replaced with to some position in the face position of cartoon figure
Deng, to each position edit after, be the multiple as new electronic image using one or more parts of the object after editor
Characteristic area.
In a kind of optional embodiment, object can be taking a picture certainly for people in above-mentioned electronic image, and user can be to certainly
Take a picture certain position (for example, eyes) of middle face replaces with the eyes of cartoon figure.
By above-described embodiment, it is possible to achieve any one portion of destination object in User Defined editing electronic image
Position, and by the purpose of electronic image Dynamic Announce, so as to strengthen the interest of display.
Alternatively, as shown in figure 9, being identified including to the object in electronic image：
Step S902, identifies the figure image or cartoon character in electronic image；
Step S904, identifies body part or the face of figure image or cartoon character, wherein, body part or
Face is one or more parts of object.
Used as a kind of optional embodiment, above-mentioned electronic image can be the photo shot by camera head, it is also possible to
It is the picture made by graphics software or drawing tool；Above-mentioned figure image can be that the taking pictures certainly, take a group photo of user, whole body shine
Deng；Above-mentioned cartoon character can be for shoot child's reading matter in cartoon figure photo, or by Software for producing
Or cartoon figure's picture that drawing tool makes.When object is identified in electronic image, electronic image is recognized first
Middle destination object, can be character image or cartoon image, then recognize the character image or cartoon image body part or
Person face.
By above-described embodiment, the effect that static electronic image is carried out Dynamic Announce is realized.
In a kind of optional embodiment, as shown in Figure 10, the figure image or cartoon character in electronic image are identified,
Including：
Step S9021, carry out rim detection, color space characteristic to electronic image scratch picture, obtain figure image or card
Lead to the contour feature data of image；
Step S9023, according to contour feature data, obtains figure image or cartoon character.
As a kind of optional embodiment, rim detection can be carried out to electronic image or color region is scratched at the images such as picture
Reason operation, obtains the contour feature data of the target figure's image or cartoon character in electronic image, including figure image or card
The outline data at each position in logical image.
By above-described embodiment, it is possible to achieve by each position of destination object and destination object in Two-dimensional electron image
The purpose being identified, such that it is able to be used to make corresponding threedimensional model.
In a kind of optional embodiment, as shown in figure 11, to electronic image multiple images corresponding with each region
Enter edlin, obtain after the dynamic image that can be played, method also includes：
Step S112, receive dynamic image driving instruction, wherein, driving instruction include it is following any one：Voice is believed
Number, countenance or limb motion；
Step S114, according to driving instruction, plays corresponding dynamic image.
As a kind of optional embodiment, above-mentioned driving instruction can be the voice signal of user input, countenance or
Limb motion, in a kind of optional embodiment, if user has been autodyned a photo using mobile phone, when user plane is to mobile phone screen
Upper still photo makees various countenances or face change, and the still image on mobile phone just can be to move accordingly
Come, when user plane makees various gestures etc. to mobile phone to be acted, still photo also can be moved up and then, it is preferable that can be by photo
In figure image change various cartoon characters into, or figural certain body part is replaced with into corresponding cartoon character
Body part.
By above-described embodiment, it is possible to achieve by countenance (that is, face express one's feelings) or gesture motion by static map
As the effect for moving up.
As one kind preferred embodiment, the method flow diagram for moving up still image shown in Figure 12 can be combined
Carry out specification above-described embodiment, specifically, the method comprises the following steps：
Step S121, obtains electronic image.
Specifically, in above-mentioned steps, an image is obtained, obtains the electronic pictures data of image.
Step S122, extracts the contour feature of object in electronic image, obtains image in the profile of object.
Specifically, in above-mentioned steps, the outline that the electronic pictures to being obtained in step S121 carry out destination object is special
Proposition is levied, by the rim detection to image, stingy picture (when necessary, can manually participate in regulation) of color space characteristic etc.
Operation, obtains contour feature edge location data (feature locations information data).
Step S123, based on topological structure ReebGraph analyses, obtains the corresponding animation bone information text of image in profile
Part.
Specifically, in above-mentioned steps, to feature locations information data in step S123, according to topological structure
ReebGraph analyses obtain specific object skeleton model (can also perform skeleton model), bind corresponding animation bone letter
Breath file.
Step S124, according to image in profile and corresponding animation bone information file, object in electronic image is changed
It is vector model.
Specifically, in above-mentioned steps, needs, bone and associated steps S123 according to step S125 are driven according to actual
Profile in image, view data triangularization, obtain the new vector model with skeleton data.
Step S125, according to image in vector model and corresponding profile, obtains the vector model with face.
Specifically, in above-mentioned steps, according to view data in vector model and the profile of association, identification obtains object face
The official rank information of portion five (can manually adjust), face information triangularization, has obtained the vector model with face.
Step S126, by the way of face express one's feelings driving or limbs driving, drives still image to move up.
Specifically, in above-mentioned steps, after the vector model of generation electronic image, what user can be expressed one's feelings by face
Change or limb motion are driven so that static electronic image is moved up.
Alternatively, above-mentioned face expression type of drive can for it is following any one：
(1) directly face can be driven to express one's feelings using the face action message animation file in storehouse；
(2) according to acoustic information data, (sound source can be input word conversion sound, typing or read thread text
Part) vowel-consonant and energy information, drive face expression.
(3) caught by countenance, capture the change information of face's face to carry out the face table in vector model
Feelings；
(4) by external control (such as mouse or Touching controlling lamp drag control point, are driven animation)
By (1) to (4) any one mode, you can make the face in vector model, move the face in still image
Gas comes.
Alternatively, above-mentioned limbs type of drive can for it is following any one：
(1) according to corresponding skeleton cartoon information in storehouse, skeleton cartoon is driven；
(2) limbs animation can be driven by acting stream information by obtaining real-time capture stream of action；
(3) by external control, (such as mouse or touch etc. drag control point, are driven animation.
By (1) to (3) any one mode, both can be with the limb action in driving vector model, in making still image
Limbs move up；
In a kind of optional embodiment, above-mentioned still image can only express one's feelings comprising above-mentioned face and drive or limb motion drive
One of dynamic mode, i.e. only face or only limbs, moves up still image.
By above-described embodiment, realize and expressed one's feelings by face or limb motion mode is come so that still image is moved up,
Increased interest.
Embodiment 2
According to embodiments of the present invention, the device embodiment that a kind of still image is converted to dynamic image is additionally provided.This hair
The method that still image in bright embodiment 1 is converted to dynamic image can be performed in the device of the embodiment of the present invention 2.
Figure 13 is the schematic device that a kind of still image according to embodiments of the present invention is converted to dynamic image, such as Figure 13
Shown, the device includes：First acquisition module 131, the second acquisition module 133, first processing module 135 and Second processing module
137。
Wherein, the first acquisition module 131, for obtaining electronic image；Second acquisition module 133, for obtaining electronic chart
One or more characteristic areas as in；First processing module 135, for each region in one or more characteristic areas
Processed, obtained the corresponding multiple images in each region；Second processing module 137, for electronic image and each region
Corresponding multiple images are processed, and obtain the dynamic image that can be played.
From the foregoing, it will be observed that in the above embodiments of the present application, by obtaining one or more characteristic areas in electronic image,
And corresponding each region is processed in electronic image to these characteristic areas, the multiple dynamic of each characteristic area is obtained
One or more characteristic areas in the electronic image and electronic image are finally entered edlin by image file, whole so as to obtain
The dynamic image of individual electronic image, Dynamic Announce is carried out by static electronic image.Easily note, the electronic image can be used
The photo that family camera head shoots, it is also possible to downloaded by the picture of software development or by network or directly transferred from disk
Picture；Characteristic area in above-mentioned electronic image can be destination object in electronic image, can also be destination object
Characteristic portion or one or more regions for arbitrarily being divided to electronic image.By scheme disclosed in above-described embodiment,
Reach one or more characteristic areas in electronic image have been processed respectively, obtained the dynamic image of whole electronic image
Purpose, it is achieved thereby that by the technique effect of still image Dynamic Announce, and then solve prior art and cannot realize static state
Image's dynamic display causes the technical problem of interactivity difference.
In a kind of optional embodiment, above-mentioned Second processing module 137 can include：3rd processing module, for root
According to electronic image multiple images corresponding with each region, the dynamic image file that can be played is obtained；3rd acquisition module, uses
In acquisition audio file；Fourth processing module, for obtaining dynamic image according to dynamic image file and audio file.
In a kind of optional embodiment, above-mentioned 3rd acquisition module includes：4th acquisition module, it is defeated for obtaining user
The text information for entering；Modular converter, for carrying out being converted to audio file to text information.
In a kind of optional embodiment, above-mentioned second acquisition module includes：3rd acquisition module, exists for obtaining user
One or more regions divided in electronic image；5th processing module, for using the image in one or more regions as
One or more characteristic areas.
In a kind of optional embodiment, above-mentioned second acquisition module includes：Identification module, in electronic image
Object is identified；6th processing module, for using one or more parts of object as one or more characteristic areas.
In a kind of optional embodiment, above-mentioned 6th processing module includes：First output module, for what be will identify that
One or more parts of object show user；One or more parts of object are entered by receiver module for receiving user
Capable editor；7th processing module, for using one or more parts of the object after editor as one or more characteristic areas
Domain.
In a kind of optional embodiment, above-mentioned identification module includes：First identification submodule, for identifying electronic chart
Figure image or cartoon character as in；Second identification submodule, the body for identifying figure image or cartoon character
Position or face, wherein, body part or face are one or more parts of object.
In a kind of optional embodiment, above-mentioned first identification submodule includes：6th acquisition module, for electronic chart
Carry out rim detection, the color space characteristic of picture scratch picture, obtain the contour feature data of figure image or cartoon character；Determine mould
Block, for according to contour feature data, determining figure image or cartoon character.
In a kind of optional embodiment, said apparatus also include：Second receiver module, the drive for receiving dynamic image
Dynamic instruction, wherein, driving instruction include it is following any one：Voice signal, countenance or limb motion；Second output mould
Block, for according to driving instruction, playing corresponding dynamic image.
The embodiments of the present invention are for illustration only, and the quality of embodiment is not represented.
In the above embodiment of the present invention, the description to each embodiment all emphasizes particularly on different fields, and does not have in certain embodiment
The part of detailed description, may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed technology contents, can be by other
Mode is realized.Wherein, device embodiment described above is only schematical, the division of such as unit, can be one kind
Division of logic function, can there is other dividing mode when actually realizing, such as multiple units or component can combine or can
To be integrated into another system, or some features can be ignored, or not perform.It is another, it is shown or discussed each other
Coupling or direct-coupling or communication connection can be the INDIRECT COUPLING or communication connection of unit or module by some interfaces,
Can be electrical or other forms.
The unit illustrated as separating component can be or may not be physically separate, be shown as unit
Part can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple units
On.Some or all of unit therein can be according to the actual needs selected to realize the purpose of this embodiment scheme.
In addition, during each functional unit in each embodiment of the invention can be integrated in a processing unit, it is also possible to
It is that unit is individually physically present, it is also possible to which two or more units are integrated in a unit.Above-mentioned integrated list
Unit can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If integrated unit, can to realize in the form of SFU software functional unit and as independent production marketing or when using
To store in a computer read/write memory medium.Based on such understanding, technical scheme substantially or
Saying all or part of the part or technical scheme contributed to prior art can be embodied in the form of software product
Out, computer software product storage is in a storage medium, including some instructions are used to so that a computer equipment
(can be personal computer, server or network equipment etc.) performs all or part of step of each embodiment method of the invention
Suddenly.And foregoing storage medium includes：USB flash disk, read-only storage (ROM, Read-Only Memory), random access memory
(RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various can be with the medium of store program codes.
The above is only the preferred embodiment of the present invention, it is noted that come for those skilled in the art
Say, under the premise without departing from the principles of the invention, can also make some improvements and modifications, these improvements and modifications also should be regarded as
Protection scope of the present invention.
Claims (18)
1. a kind of method that still image is converted to dynamic image, it is characterised in that including：
Obtain electronic image；
Obtain one or more characteristic areas in electronic image；
Each region in one or more characteristic areas is processed, the corresponding multiple images in each region are obtained；
Electronic image multiple images corresponding with each region are processed, the dynamic image that can be played is obtained.
2. method according to claim 1, it is characterised in that process electronic image image corresponding with each region,
The dynamic image that can be played is obtained, including：
According to electronic image multiple images corresponding with each region, the dynamic image file that can be played is obtained；
Audio file is obtained, wherein, audio file is generated by following any one mode：User directly inputs voice, or, with
Family is input into word；
Dynamic image is obtained according to dynamic image file and audio file.
3. method according to claim 2, it is characterised in that generating audio file by user input word includes：
Obtain the text information of user input；
Text information is carried out to be converted to audio file.
4. method according to claim 1, it is characterised in that one or more characteristic areas obtained in electronic image include：
Obtain one or more regions that user divides in electronic image；
Using the image in one or more regions as one or more characteristic areas.
5. method according to claim 1, it is characterised in that one or more characteristic areas obtained in electronic image include：
Object in electronic image is identified；
Using one or more parts of object as one or more characteristic areas.
6. method according to claim 5, it is characterised in that using one or more parts of object as one or more features
Region includes：
One or more parts for the object that will identify that show user；
Receive the editor that user is carried out to one or more parts of object；
Using one or more parts of the object after editor as one or more characteristic areas.
7. according to the method for claim 5 or 6, it is characterised in that the object in electronic image is identified including：
Identify the figure image or cartoon character in electronic image；
Body part or the face of figure image or cartoon character are identified, wherein, body part or face are object
One or more parts.
8. method according to claim 7, it is characterised in that identify the figure image or cartoon character in electronic image, wraps
Include：
Carry out rim detection, color space characteristic to electronic image scratch picture, and the profile for obtaining figure image or cartoon character is special
Levy data；
According to contour feature data, figure image or cartoon character are obtained.
9. method according to claim 1, it is characterised in that carried out to electronic image multiple images corresponding with each region
Treatment, obtains after the dynamic image that can be played, and method also includes：
Receive dynamic image driving instruction, wherein, driving instruction include it is following any one：Voice signal, countenance or
Limb motion；
According to driving instruction, corresponding dynamic image is played.
10. a kind of still image is converted to the device of dynamic image, it is characterised in that including：
First acquisition module, for obtaining electronic image；
Second acquisition module, for obtaining one or more characteristic areas in electronic image；
First processing module, for processing each region in one or more characteristic areas, obtains each region pair
The multiple images answered；
Second processing module, for processing electronic image multiple images corresponding with each region, obtains playing
Dynamic image.
11. devices according to claim 10, it is characterised in that Second processing module includes：
3rd processing module, for according to electronic image multiple images corresponding with each region, obtaining the dynamic that can be played
Image file；
3rd acquisition module, for obtaining audio file, wherein, audio file is generated by following any one mode：User
Voice is directly inputted, or, user input word；
Fourth processing module, for obtaining dynamic image according to dynamic image file and audio file.
12. devices according to claim 11, it is characterised in that the 3rd acquisition module includes：
4th acquisition module, the text information for obtaining user input；
Modular converter, for carrying out being converted to audio file to text information.
13. devices according to claim 10, it is characterised in that the second acquisition module includes：
5th acquisition module, for obtaining one or more regions that user divides in electronic image；
5th processing module, for using the image in one or more regions as one or more characteristic areas.
14. devices according to claim 10, it is characterised in that the second acquisition module includes：
Identification module, for being identified to the object in electronic image；
6th processing module, for using one or more parts of object as one or more characteristic areas.
15. devices according to claim 14, it is characterised in that the 6th processing module includes：
First output module, one or more parts of the object for will identify that show user；
First receiver module, for receiving the editor that user is carried out to one or more parts of object；
7th processing module, for using one or more parts of the object after editor as one or more characteristic areas.
16. according to the device of claims 14 or 15, it is characterised in that identification module includes：
First identification submodule, for identifying figure image or cartoon character in electronic image；
Second identification submodule, body part or face for identifying figure image or cartoon character, wherein, body
Position or face are one or more parts of object.
17. devices according to claim 16, it is characterised in that the first identification submodule includes：
6th acquisition module, for electronic image carry out rim detection, color space characteristic scratch picture, obtain figure image or
The contour feature data of cartoon character；
Determining module, for according to contour feature data, determining figure image or cartoon character.
18. devices according to claim 10, it is characterised in that device also includes：
Second receiver module, the driving instruction for receiving dynamic image, wherein, driving instruction include it is following any one：Language
Message number, countenance or limb motion；
Second output module, for according to driving instruction, playing corresponding dynamic image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611088517.6A CN106791032A (en) | 2016-11-30 | 2016-11-30 | The method and apparatus that still image is converted to dynamic image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611088517.6A CN106791032A (en) | 2016-11-30 | 2016-11-30 | The method and apparatus that still image is converted to dynamic image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106791032A true CN106791032A (en) | 2017-05-31 |
Family
ID=58915314
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611088517.6A Pending CN106791032A (en) | 2016-11-30 | 2016-11-30 | The method and apparatus that still image is converted to dynamic image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106791032A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107657638A (en) * | 2017-10-30 | 2018-02-02 | 努比亚技术有限公司 | A kind of image processing method, device and computer-readable recording medium |
| CN107798710A (en) * | 2017-10-26 | 2018-03-13 | 上海熠鸪智能灯科技有限公司 | Light method for making picture and system based on passive pictorial element |
| CN108712603A (en) * | 2018-04-27 | 2018-10-26 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
| CN111212269A (en) * | 2020-01-16 | 2020-05-29 | 深圳慧源创新科技有限公司 | Unmanned aerial vehicle image display method and device, electronic equipment and storage medium |
| CN111598977A (en) * | 2020-05-21 | 2020-08-28 | 北京中科深智科技有限公司 | Method and system for transferring and animating expression |
| CN114898022A (en) * | 2022-07-15 | 2022-08-12 | 杭州脸脸会网络技术有限公司 | Image generation method, image generation device, electronic device, and storage medium |
| CN115061348A (en) * | 2022-08-01 | 2022-09-16 | 世优（北京）科技有限公司 | Three-dimensional dynamic holographic display method and device based on object points |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105049747A (en) * | 2015-08-06 | 2015-11-11 | 广州市博源数码科技有限公司 | System for identifying static image and converting static image into dynamic display |
| CN105187736A (en) * | 2015-07-28 | 2015-12-23 | 广东欧珀移动通信有限公司 | Method and system for converting static human face image into video, and mobile terminal |
| CN105447896A (en) * | 2015-11-14 | 2016-03-30 | 华中师范大学 | Animation creation system for young children |
-
2016
- 2016-11-30 CN CN201611088517.6A patent/CN106791032A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105187736A (en) * | 2015-07-28 | 2015-12-23 | 广东欧珀移动通信有限公司 | Method and system for converting static human face image into video, and mobile terminal |
| CN105049747A (en) * | 2015-08-06 | 2015-11-11 | 广州市博源数码科技有限公司 | System for identifying static image and converting static image into dynamic display |
| CN105447896A (en) * | 2015-11-14 | 2016-03-30 | 华中师范大学 | Animation creation system for young children |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107798710A (en) * | 2017-10-26 | 2018-03-13 | 上海熠鸪智能灯科技有限公司 | Light method for making picture and system based on passive pictorial element |
| CN107657638A (en) * | 2017-10-30 | 2018-02-02 | 努比亚技术有限公司 | A kind of image processing method, device and computer-readable recording medium |
| CN108712603A (en) * | 2018-04-27 | 2018-10-26 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
| CN111212269A (en) * | 2020-01-16 | 2020-05-29 | 深圳慧源创新科技有限公司 | Unmanned aerial vehicle image display method and device, electronic equipment and storage medium |
| CN111598977A (en) * | 2020-05-21 | 2020-08-28 | 北京中科深智科技有限公司 | Method and system for transferring and animating expression |
| CN114898022A (en) * | 2022-07-15 | 2022-08-12 | 杭州脸脸会网络技术有限公司 | Image generation method, image generation device, electronic device, and storage medium |
| CN115061348A (en) * | 2022-08-01 | 2022-09-16 | 世优（北京）科技有限公司 | Three-dimensional dynamic holographic display method and device based on object points |
| CN115061348B (en) * | 2022-08-01 | 2024-05-17 | 世优（北京）科技有限公司 | Three-dimensional dynamic holographic display method and device based on object points |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106791032A (en) | The method and apparatus that still image is converted to dynamic image | |
| US11790589B1 (en) | System and method for creating avatars or animated sequences using human body features extracted from a still image | |
| CN111833418B (en) | Animation interaction method, device, equipment and storage medium | |
| US11736756B2 (en) | Producing realistic body movement using body images | |
| JP2020529084A (en) | Image processing method, equipment and storage medium | |
| KR101306221B1 (en) | Method and apparatus for providing moving picture using 3d user avatar | |
| CN106713896A (en) | Static image multimedia presentation method, device and system | |
| Sun et al. | SmartPaint: a co-creative drawing system based on generative adversarial networks | |
| CN109271018A (en) | Exchange method and system based on visual human's behavioral standard | |
| CN104508680B (en) | Improved video signal is tracked | |
| de Lima et al. | Draw your own story: Paper and pencil interactive storytelling | |
| CN1901665A (en) | Facial feature-localized and global real-time video morphing | |
| CN109324688A (en) | Exchange method and system based on visual human's behavioral standard | |
| CN104240277A (en) | Augmented reality interaction method and system based on human face detection | |
| CN112272295B (en) | Method for generating video with three-dimensional effect, method for playing video, device and equipment | |
| TW202008143A (en) | Man-machine interaction method and apparatus | |
| CN106127828A (en) | The processing method of a kind of augmented reality, device and mobile terminal | |
| US20200074736A1 (en) | Transmutation of virtual entity sketch using extracted features and relationships of real and virtual objects in mixed reality scene | |
| CN109343695A (en) | Exchange method and system based on visual human's behavioral standard | |
| CN109992187A (en) | A kind of control method, device, equipment and storage medium | |
| CN117519477A (en) | Digital human virtual interaction system and method based on display screen | |
| US11544889B2 (en) | System and method for generating an animation from a template | |
| CN110298925A (en) | A kind of augmented reality image processing method, calculates equipment and storage medium at device | |
| CN106980847A (en) | A kind of method and system based on generation with shared ARMark AR game and activity | |
| US20080122867A1 (en) | Method for displaying expressional image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |