CN103914803B - A kind of image processing method and device - Google Patents
A kind of image processing method and device Download PDFInfo
- Publication number
- CN103914803B CN103914803B CN201410171728.0A CN201410171728A CN103914803B CN 103914803 B CN103914803 B CN 103914803B CN 201410171728 A CN201410171728 A CN 201410171728A CN 103914803 B CN103914803 B CN 103914803B
- Authority
- CN
- China
- Prior art keywords
- voice data
- new object
- image
- primary object
- background image
- 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.)
- Active
Links
Abstract
The present invention provides a kind of image processing method and device, the method is according to image-capture instruction crawl primary object, the primary object of crawl is bound with corresponding voice data, obtain new object, and paste the new object in background image, the first operational order of the new object in then receiving to the background image, according to first operational order for receiving, the voice data of the new object binding is read, and is played.The present invention provides a kind of image processing method and device is processed to still image, there is provided the various features involved by image.
Description
Technical field
The present invention relates to image processing techniquess, more particularly to a kind of image processing method and device.
Background technology
Image procossing (image processing) technology is referred to and image is analyzed with computer, to reach required knot
The technology of fruit.Image procossing refers generally to the process to digital picture.Image processing techniquess mainly include compression of images, strengthen and multiple
Original, coupling, 3 parts of description and identification.Common process have image digitazation, picture coding, image enhaucament, image restoration,
Image segmentation, graphical analyses and image beautification etc..
Existing image processing method be in order to reduce the data volume of image, improve image definition or make image exhibition
The picture for showing is finer, after which is all only limitted to be processed the image of width static state, remains as the static image of a width, and
More features involved by image cannot be provided.
Content of the invention
The present invention provides a kind of image processing method and device, still image is processed, there is provided involved by image
Various features.
The present invention provides a kind of image processing method, including：
According to image-capture instruction crawl primary object；
The primary object of crawl is bound with corresponding voice data, obtains new object；
The new object is pasted in background image；
First operational order of the new object in receiving to the background image；
According to first operational order for receiving, the voice data of the new object binding is read, and is played.
The present invention provides a kind of image processing apparatus, including：
Placement unit, for according to image-capture instruction crawl primary object；
Voice binding unit, for tying up the primary object that the placement unit is captured with corresponding voice data
Fixed, obtain new object；
Application unit, for pasting the new object in background image；
First instruction reception unit, for the first operational order of the new object in receiving to the background image；
Voice output unit, for first operational order that instruction reception unit according to first is received, reads
The voice data of the new object binding, and play.
A kind of image processing apparatus and method that the present invention is provided, by capturing the corresponding voice data of object binding,
And still image is processed by the method for receiving operational order reading voice data, it is special sound to be provided for still image
Reference ceases.
Description of the drawings
By reading the detailed description made by non-limiting example that is made with reference to the following drawings, other of the invention
Feature, objects and advantages will become more apparent upon：
Fig. 1 is a kind of image processing method flow chart provided in an embodiment of the present invention；
Fig. 2 is a kind of image processing apparatus structural representation provided in an embodiment of the present invention.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment that states is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that, in order to just
Part related to the present invention rather than full content is illustrate only in description, accompanying drawing.
Fig. 1 is a kind of image processing method flow chart provided in an embodiment of the present invention.
A kind of image processing method provided in an embodiment of the present invention can be in the terminal with display and input equipment
Realize, such as computer, panel computer, mobile terminal etc..As described in Figure 1, a kind of image procossing provided in an embodiment of the present invention
Method includes：
Step 11, according to image-capture instruction crawl primary object.
Wherein, image-capture instruction can be shearing or selection operation to a width picture, and for example user is along picture
The object is cut by the profile of object, or user selects the picture with profile in kind that a system is provided, then be sheared
Or the object that chooses is primary object.
Step 12, the primary object of crawl is bound with corresponding voice data, obtains new object.
It is automobile that such as user is cut out an automobile i.e. primary object from a picture, and automobile can have electromotor
The sound characteristics such as roar, sound of blowing a whistle, these voice characteristics datas are embodied in data base in advance, when determining the original of crawl
After object is automobile, from data base, selects the voice characteristics data of automobile to be bound with the object, bound sound characteristic
The primary object of data is new object.
Step 13, the new object is pasted in background image.
Equally by taking automobile as an example, primary object is sheared from picture or chooses duplication out, and being one has automobile profile
Shearogram, this shearogram bound voice data and defined a new object, and the shearogram is pasted one now
In background image, background image can be blank page or the page with background content, and the paste position of picture can be by
User specifies, and for example user drags a certain region that shearogram places it in background image.
Step 14, the first operational order of the new object in receiving to the background image.
Wherein, first operational order can be the behaviour of the position of the screen display object that user clicks on panel computer
Make, because according to new object in the coordinate range of background image, the position of new object is it has been determined that so can judge that user clicks on
Position be whether position that new object is located, when user clicks the region at new object place, that is, represent and have input first
Operational order.
Step 15, according to first operational order for receiving, reads the voice data of the new object binding, and broadcasts
Put.
When have received the first operational order, then the above-mentioned sound with object with binding relationship is called from data base
Data, and can be by the device plays such as speaker sound.
Exemplary, according to image-capture instruction crawl primary object described in the embodiment of the present invention, including：
Primary object is captured from photo according to image-capture instruction.A true scape is shot by image unit for example
Thing, such as shoots a Fructus Mali pumilae, and user from electronic photo is described one time according to the profile of Fructus Mali pumilae or sheared out,
Then primary object is the Fructus Mali pumilae.Or, soft copy can will be saved as after papery photo scanning, for crawl.
Exemplary, the primary object of crawl is bound with corresponding voice data described in the embodiment of the present invention, can
Including：
The primary object is identified；
Corresponding voice data is searched for according to recognition result.
In order to strengthen the motility for choosing primary object, it is possible to use image recognition technology is known to described object
Not, do not limit user and how to select image as primary object, the content for going out image by the feature identification of image, that is, determine
The content of crawl object.Such as user have selected the personage according to the profile of a personage in picture from a width picture, i.e.,
The personage is crawl object, then the personage has the profile of mankind's body characteristicses such as extremity, head, and the image is identified
Can learn this object content be the mankind.
When recognize primary object for the mankind when, you can in data base search for the mankind voice data.The mankind have
Sound characteristic, such as one's voice in speech, can be specifically greetings etc..
The voice data for searching is bound with the primary object.Then by one section of greeting sound clip with should
Who object is bound.
Or, the primary object of crawl is bound with corresponding voice data, including：
Instructed according to the name to the primary object, the primary object is tied up with the title in the name instruction
Fixed；
According to the corresponding voice data of the name search；
The voice data for searching is bound with the primary object.
As the morphological characteristic of primary object may not enough substantially, so existing image recognition technology is unable to entirely accurate
Identify the content of image, or the precision of image recognition can not meet demand, such as when user is sheared from a picture
Go out a personage as original image, the content that image recognition technology can go out the image by the outline identification of personage is people
Class, but the concrete identity of the personage cannot be further identified, cannot if the sound clip for having multiple personages in data base
Confirm the relation of voice data and the object, so now receiving a name instruction, specified in primary object with title
Hold.
Voice data corresponding with primary object can be searched out according to specific title, then bound.
Exemplary, corresponding voice data is searched for according to recognition result described in the embodiment of the present invention, including：
Corresponding voice data is searched for from audio database according to recognition result, the sound number in the audio database
According to by record obtain；
Or, according to the corresponding voice data of the name search, including：
Corresponding voice data is searched for from the audio database according to the title.
The embodiment of the present invention can gather voice data by sound-recording function, and voice data is named or is sorted out etc. and grasp
Make, the sound of recording is made as the corresponding voice data of certain primary object.For example there is concrete identity when primary object is one
Personage, and in data base, do not include originally voice data corresponding with the personage, then the personage can be gathered in the way of with recording
Acoustic information be stored in data base as corresponding voice data.
Exemplary, after described in the embodiment of the present invention paste the new object in background image, methods described is also
Including：
According to position of the new object in the background image, movement locus and the speed of the new object is determined；
Receive the second operational order to the new object；
According to second operational order, the new object is moved according to the movement locus and speed that determine.
The embodiment of the present invention can also be that new object gives movement elements, after new object is adhered in background image, its
Position is fixed, so positional information of each pixel of the object in background image can be calculated, such as coordinate information,
Can be that the object arranges a kind of animation effect according to positional information, realize that animation effect can use graphics rendering techniques, right
Whole background image is repeatedly rendered, and in the image for rendering every time, the position of new object is different, continuously renders, makes quiet
State image presents dynamic effect, for example, the object is moved along a direction in background image, move a certain distance
After return to origin, the moving process of the new object is an animation effect, for mobile speed, then depends on image rendering
Parameter.
Wherein, the second instruction can be the operation that user clicks on screen display new object position, can be difference with
The action of the first operational order, or with the first operational order identical action, when the second operational order is received, then
Show the moving process of the object.
Exemplary, after described in the embodiment of the present invention paste the new object in background image, methods described is also
Including：
Receive edit instruction；
According to the background image that the edit instruction editor is pasted with the new object.When new object pastes background image
Afterwards, user can input editing instruction drawing input is carried out to image, such as using graphics rendering techniques, identifying user click on or
The position of slip screen, is carried out rendering forming Drawing image to the position, while can also be input into the parameter that renders to determine to draw
Color, line style and other effects.
Fig. 2 is a kind of image processing apparatus structural representation that the present embodiment is provided.
A kind of image processing apparatus that the present embodiment is provided are used for realizing above-mentioned image processing method.As shown in Fig. 2 the figure
Picture processing meanss, including：Placement unit 21, voice binding unit 22, application unit 23, the first instruction reception unit 24 and sound
Output unit 25.
Wherein, placement unit 21 is used for according to image-capture instruction crawl primary object.
Voice binding unit 22 is used for the primary object for capturing the placement unit 21 and corresponding voice data
Binding, obtains new object.
Application unit 23 is used for pasting the new object in background image.
First operational order of first instruction reception unit 24 for the new object in receiving to the background image.
Voice output unit 25 is used for first operational order received according to first instruction reception unit 24, reads
The voice data of the new object binding is taken, and is played.
Exemplary, placement unit 21 described in the present embodiment specifically for：
Primary object is captured from photo according to image-capture instruction.
Exemplary, described in the present embodiment, voice binding unit 22 includes：Image recognition subelement, the first data search
Unit and the first voice binding subelement.
Wherein, image recognition subelement is used for being identified the primary object.
First data search subelement is used for searching for corresponding voice data according to recognition result.
First voice binding subelement is used for being bound the voice data for searching with the primary object.
Or, described in the present embodiment, voice binding unit 22 includes：Object specifies subelement, the second data search subelement
Subelement is bound with second sound.
Wherein, object specifies subelement to be used for according to instructing to the name of the primary object, by the primary object with
Name binding in the name instruction.
Second data search module is used for according to the corresponding voice data of the name search.
Second sound binding module is used for being bound the voice data for searching with the primary object.
Exemplary, the first data search subelement described in the present embodiment specifically for according to recognition result from voice data
Corresponding voice data is searched in storehouse, and the voice data in the audio database is obtained by recording；
Or, the second data search subelement is specifically for searching for from the audio database according to the title
Corresponding voice data.
Exemplary, the present embodiment described device also includes：Second instruction reception unit, motion feature determining unit and fortune
Dynamic display unit.
Wherein, the second instruction reception unit is used for receiving the second operational order to the new object.
Motion feature determining unit is used for after the application unit pastes the new object in background image, root
According to position of the new object in the background image, movement locus and the speed of the new object is determined.
Movement display unit is used for second operational order received according to second instruction reception unit, according to institute
The movement locus and speed for stating the determination of motion feature determining unit move the new object.
Exemplary, the present embodiment described device also includes：3rd instruction reception unit and graphics edition unit.
Wherein, the 3rd instruction reception unit is used for, in the application unit, the new object is pasted in background image it
Afterwards, edit instruction is received.
Graphics edition unit is used for according to the edit instruction editor of the 3rd instruction reception unit reception is pasted with
The background image of new object.
Above are only presently preferred embodiments of the present invention and institute's application technology principle.The invention is not restricted to described here specific
Embodiment, can carry out various obvious changes for a person skilled in the art, readjust and substitute without departing from this
The protection domain of invention.Therefore, although the present invention is described in further detail by above example, but of the invention
Above example is not limited only to, without departing from the inventive concept, other Equivalent embodiments more can also be included,
And the scope of the present invention is determined by scope of the appended claims.
Claims (10)
1. a kind of image processing method, it is characterised in that include：
According to image-capture instruction crawl primary object；
The primary object of crawl is bound with corresponding voice data, obtains new object；
The new object is pasted in background image；
First operational order of the new object in receiving to the background image；
According to first operational order for receiving, the voice data of the new object binding is read, and is played；
The primary object of crawl is bound with corresponding voice data, including：
The primary object is identified；
Corresponding voice data is searched for according to recognition result；
The voice data for searching is bound with the primary object；
Or,
Instructed according to the name to the primary object, the name binding during the primary object is instructed with the name；
According to the corresponding voice data of the name search；
The voice data for searching is bound with the primary object.
2. method according to claim 1, it is characterised in that according to image-capture instruction crawl primary object, including：
Primary object is captured from photo according to image-capture instruction.
3. method according to claim 1, it is characterised in that corresponding voice data is searched for according to recognition result, including：
Corresponding voice data is searched for from audio database according to recognition result, the voice data in the audio database leads to
Copy sth. from a notebook to another one and be obtained；
Or, according to the corresponding voice data of the name search, including：
Corresponding voice data is searched for from the audio database according to the title.
4. the method according to any one of claim 1-3, it is characterised in that paste the new object in background image
Afterwards, methods described also includes：
According to position of the new object in the background image, movement locus and the speed of the new object is determined；
Receive the second operational order to the new object；
According to second operational order, the new object is moved according to the movement locus and speed that determine.
5. the method according to any one of claim 1-3, it is characterised in that paste the new object in background image
Afterwards, methods described also includes：
Receive edit instruction；
According to the background image that the edit instruction editor is pasted with the new object.
6. a kind of image processing apparatus, it is characterised in that include：
Placement unit, for according to image-capture instruction crawl primary object；
Voice binding unit, for being bound the primary object that the placement unit is captured with corresponding voice data, is obtained
Arrive new object；
Application unit, for pasting the new object in background image；
First instruction reception unit, for the first operational order of the new object in receiving to the background image；
Voice output unit, for first operational order received according to first instruction reception unit, reads described
The voice data of new object binding, and play；
The voice binding unit includes：
Image recognition subelement, for being identified to the primary object；
First data search subelement, for searching for corresponding voice data according to recognition result；
First voice binding subelement, for being bound the voice data for searching with the primary object；
Or, the voice binding unit includes：
Object specifies subelement, for being instructed according to the name to the primary object, by the primary object and the name
Name binding in instruction；
Second data search subelement, for according to the corresponding voice data of the name search；
Second sound binds subelement, for being bound the voice data for searching with the primary object.
7. device according to claim 6, it is characterised in that the placement unit specifically for：
Primary object is captured from photo according to image-capture instruction.
8. device according to claim 7, it is characterised in that the first data search subelement is specifically for according to knowledge
Other result searches for corresponding voice data from audio database, and the voice data in the audio database is by recording
Arrive；
Or, the second data search subelement is corresponding specifically for being searched for from the audio database according to the title
Voice data.
9. the device according to any one of claim 6-8, it is characterised in that described device also includes：
Motion feature determining unit, after paste in background image by the new object, according to
Position of the new object in the background image, determines movement locus and the speed of the new object；
Second instruction reception unit, for receiving the second operational order to the new object；
Movement display unit, for second operational order received according to second instruction reception unit, according to described
The movement locus and speed that motion feature determining unit determines move the new object.
10. the device according to any one of claim 6-8, it is characterised in that described device also includes：
3rd instruction reception unit, after paste in background image by the new object, receives
Edit instruction；
Graphics edition unit, it is described newly right that the edit instruction editor for being received according to the 3rd instruction reception unit is pasted with
The background image of elephant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410171728.0A CN103914803B (en) | 2014-04-25 | 2014-04-25 | A kind of image processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410171728.0A CN103914803B (en) | 2014-04-25 | 2014-04-25 | A kind of image processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103914803A CN103914803A (en) | 2014-07-09 |
| CN103914803B true CN103914803B (en) | 2017-03-15 |
Family
ID=51040464
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410171728.0A Active CN103914803B (en) | 2014-04-25 | 2014-04-25 | A kind of image processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103914803B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105704396A (en) * | 2014-11-24 | 2016-06-22 | 中兴通讯股份有限公司 | Picture processing method and device |
| CN105045840A (en) * | 2015-06-30 | 2015-11-11 | 广东欧珀移动通信有限公司 | Picture display method and mobile terminal |
| CN105975054A (en) * | 2015-11-23 | 2016-09-28 | 乐视网信息技术（北京）股份有限公司 | Method and device for information processing |
| CN106789576A (en) * | 2016-12-23 | 2017-05-31 | 上海青声网络科技有限公司 | A kind of image generating method and device |
| SG11202006616WA (en) * | 2018-01-12 | 2020-08-28 | Sp Innovation Pte Ltd | Data transmission system and method |
| CN110097619B (en) * | 2019-04-30 | 2022-12-13 | 腾讯科技（深圳）有限公司 | Animation effect implementation method, device and equipment in application program |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1704926A (en) * | 2004-06-01 | 2005-12-07 | 佳能株式会社 | Information processing device and method |
| CN103346955A (en) * | 2013-06-18 | 2013-10-09 | 腾讯科技（深圳）有限公司 | Method, device and terminal for processing picture |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5842545B2 (en) * | 2011-03-02 | 2016-01-13 | ヤマハ株式会社 | SOUND CONTROL DEVICE, SOUND CONTROL SYSTEM, PROGRAM, AND SOUND CONTROL METHOD |
-
2014
- 2014-04-25 CN CN201410171728.0A patent/CN103914803B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1704926A (en) * | 2004-06-01 | 2005-12-07 | 佳能株式会社 | Information processing device and method |
| CN103346955A (en) * | 2013-06-18 | 2013-10-09 | 腾讯科技（深圳）有限公司 | Method, device and terminal for processing picture |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103914803A (en) | 2014-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103914803B (en) | A kind of image processing method and device | |
| CN109618222B (en) | A kind of splicing video generation method, device, terminal device and storage medium | |
| US10692480B2 (en) | System and method of reading environment sound enhancement based on image processing and semantic analysis | |
| US7469064B2 (en) | Image display apparatus | |
| CN105340014B (en) | Touch optimization design for video editing | |
| CN111415399A (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| CN105786930B (en) | Based on the searching method and device for touching interaction | |
| CN108416018A (en) | Screenshotss searching method, device and intelligent terminal | |
| CN104735468A (en) | Method and system for synthesizing images into new video based on semantic analysis | |
| US20120196260A1 (en) | Electronic Comic (E-Comic) Metadata Processing | |
| CN111556332B (en) | Live broadcast method, electronic device and readable storage medium | |
| CN101295313A (en) | Display control apparatus and display control method | |
| CN105654532A (en) | Photo photographing and processing method and system | |
| JP2017162434A (en) | Method, program and device for generating web-based copy of document | |
| CN104065908B (en) | For creating and reproducing the device and method of lively picture file | |
| CN110750996B (en) | Method and device for generating multimedia information and readable storage medium | |
| KR20160119218A (en) | Sound image playing method and device | |
| CN104918060A (en) | Method and device for selecting position to insert point in video advertisement | |
| JP2017049968A (en) | Method, system, and program for detecting, classifying, and visualizing user interactions | |
| CN106407358A (en) | Image searching method and device and mobile terminal | |
| CN107103312A (en) | A kind of image processing method and device | |
| CN111813998A (en) | Video data processing method, device, equipment and storage medium | |
| CN112004031A (en) | Video generation method, device and equipment | |
| CN108108143B (en) | Recording playback method, mobile terminal and device with storage function | |
| CN110797001A (en) | Method and device for generating voice audio of electronic book and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |