CN110298904A - A kind of information processing method and device - Google Patents
A kind of information processing method and device Download PDFInfo
- Publication number
- CN110298904A CN110298904A CN201910585982.8A CN201910585982A CN110298904A CN 110298904 A CN110298904 A CN 110298904A CN 201910585982 A CN201910585982 A CN 201910585982A CN 110298904 A CN110298904 A CN 110298904A
- Authority
- CN
- China
- Prior art keywords
- information
- background
- imaged object
- input content
- background information
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/60—Editing figures and text; Combining figures or text
-
- 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
- H04N5/265—Mixing
-
- 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
- H04N5/272—Means for inserting a foreground image in a background image, i.e. inlay, outlay
Abstract
The embodiment of the invention provides a kind of information processing method and devices, and the method includes receiving input content, input content can be used in describing scene information；Based on the input content, the background information of imaged object is changed to the second background information by the first background information, the imaged object includes foreground information and first background information different from the foreground information, and second background information corresponds to the scene information.The information processing method and device provided through the invention, can do not find new Background and simply by receiving the direct replacement for realizing the Background of short-sighted frequency or image for describing the input content of scene information, need to find the technical issues of a large amount of new Background is so as to cause replacement background inconvenience and inefficiency to efficiently solve the replacement background faced in the prior art, meanwhile the process of replacement background picture can be simplified by using information processing method provided by the invention and device.
Description
Technical field
This application involves field of image processing, in particular to a kind of information processing method and device.
Background technique
Currently in photograph album short-sighted frequency or image to change background be essentially all to be completed by scratching figure, however scratch
Figure requires to find new Background to assist completing, for example, when needing for current first Background of the first video to be changed to
It when the second Background, requires a great deal of time and looks for the second Background, result in the process for changing background complicated in this way, drop
The low efficiency for changing background picture, while also will cause that user is inconvenient to use, reduce the Experience Degree of user.
Summary of the invention
In view of the above-mentioned problems in the prior art, the application provides a kind of information processing method and information processing apparatus
It sets.
To solve the above problems, technical solution provided by the present application is:
First aspect present invention provides a kind of information processing method, including,
Input content is received, the input content can be used in describing scene information；
Based on the input content, the background information of imaged object is changed to the second background letter by the first background information
Breath, the imaged object include foreground information and first background information different from the foreground information, second background
Information corresponds to the scene information.
Preferably, described be based on the input content, the background information of imaged object is changed by the first background information
For the second background information, including,
To input content processing, characteristic information is obtained；
The second background information is generated based on the characteristic information；
The background information of imaged object is changed to the second background information by the first background information.
Preferably, it is described to input content processing, obtain characteristic information；Second is generated based on the characteristic information
Background information, including,
To whole and/or partial input content processing, at least one corresponding characteristic information is obtained；
At least one described second background information is generated based at least one corresponding characteristic information.
Preferably, the imaged object includes video, dynamic picture and static images.
Preferably, the background information by imaged object is changed to the second background information by the first background information, packet
It includes,
Obtain imaged object；
Extract the foreground information of the imaged object；
Based on the foreground information and second background information, the imaged object is updated.
Preferably, the foreground information for extracting the imaged object, including,
Based on the input content and the imaged object, foreground information is determined；
Extract the foreground information of the imaged object.
Preferably, described be based on the foreground information and second background information, the imaged object is updated, is wrapped
It includes,
Analyze the feature of the foreground information；
According to the feature of the foreground information, the second background information corresponding with this feature is matched；
To update the imaged object by matched second background information.
Preferably, the imaged object includes frame image, in which:
The acquisition imaged object, including,
Obtain the frame image of the imaged object.
Preferably, the foreground information for extracting the imaged object, including, extract the foreground information in frame image.
Second aspect of the present invention provides a kind of information processing unit, memory, processor is included at least, on the memory
It is stored with computer program, the processor executes following steps:
Input content is received, the input content can be used in describing scene information；
Based on the input content, the background information of imaged object is changed to the second background letter by the first background information
Breath；
Wherein, the imaged object includes foreground information and first background information different from the foreground information, institute
The second background information is stated corresponding to the scene information.
Compared with prior art, the beneficial effects of the present application are as follows:
The information processing method and device provided through the invention, can not find new Background and simply by connecing
Receive the direct replacement that the Background of short-sighted frequency or image is realized for describing the input content of scene information, that is to say, that
In the embodiment of the present invention, new background picture only can be generated by the input content, thus realize for short-sighted frequency or
The direct replacement of the Background of person's image needs to find largely to efficiently solve the replacement background faced in the prior art
New Background so as to cause replacement background inconvenience and the technical issues of inefficiency, meanwhile, mentioned by using the present invention
The information processing method and device of confession can simplify the process of replacement background picture, improve the efficiency of replacement background picture, thus
It is user-friendly, greatly improve user experience.
Detailed description of the invention
Fig. 1 is the flow diagram of information processing method provided in an embodiment of the present invention；
Fig. 2 is the structural schematic diagram of information processing unit provided in an embodiment of the present invention.
Specific embodiment
In the following, specific embodiments of the present invention are described in detail in conjunction with attached drawing, but not as the limitation of the invention.
It should be understood that various modifications can be made to disclosed embodiments.Therefore, description above should not regard
To limit, and only as the example of embodiment.Those skilled in the art will expect within the scope and spirit of this
Other modifications.
The attached drawing being included in the description and forms part of the description shows embodiment of the disclosure, and with it is upper
What face provided is used to explain the disclosure together to substantially description and the detailed description given below to embodiment of the disclosure
Principle.
It is of the invention by the description of the preferred form with reference to the accompanying drawings to the embodiment for being given as non-limiting example
These and other characteristic will become apparent.
Although being also understood that invention has been described referring to some specific examples, those skilled in the art
Member realizes many other equivalents of the invention in which can determine, they have feature as claimed in claim and therefore all
In the protection scope defined by whereby.
When read in conjunction with the accompanying drawings, in view of following detailed description, above and other aspect, the feature and advantage of the disclosure will become
It is more readily apparent.
The specific embodiment of the disclosure is described hereinafter with reference to attached drawing；It will be appreciated, however, that the disclosed embodiments are only
Various ways implementation can be used in the example of the disclosure.Known and/or duplicate function and structure and be not described in detail to avoid
Unnecessary or extra details makes the disclosure smudgy.Therefore, specific structural and functionality disclosed herein is thin
Section is not intended to restrictions, but as just the basis of claim and representative basis be used to instructing those skilled in the art with
Substantially any appropriate detailed construction diversely uses the disclosure.
This specification can be used phrase " in one embodiment ", " in another embodiment ", " in another embodiment
In " or " in other embodiments ", it can be referred to one or more of the identical or different embodiment according to the disclosure.
In the following, the embodiment of the present invention is described in detail in conjunction with attached drawing,
As shown in Figure 1, first embodiment of the invention provides a kind of information processing method, including,
Input content is received, the input content can be used in describing scene information；
Based on the input content, the background information of imaged object is changed to the second background letter by the first background information
Breath, the imaged object include foreground information and first background information different from the foreground information, second background
Information corresponds to the scene information.
In the present embodiment, by receiving input content, so that it may the received input content of institute are converted to picture, also
It is to be converted to second background information, to use the first back original in second background information replacement imaged object
Scape information completes the replacement for imaged object background information.
In embodiment provided by the invention, there is no any restrictions for the type of imaged object, for example, the image pair
As that can be one of video, dynamic picture and static images, the imaged object include foreground information and with the prospect
The different background information of information, the original background information of the imaged object are the first background information, that is to say, that the shadow
As the background information of object before changing is the first background information, the second background information is formed by using based on the input content
Afterwards, then the first background information original in replacement imaged object is gone with second background information, to complete for image pair
As the replacement of background information.
The information processing method provided through the invention can be used for not finding new Background simply by reception
The input content of scene information is described to realize the direct replacement of the Background of short-sighted frequency or image, that is to say, that the present invention
In embodiment, new background picture only can be generated by the input content, to realize for short-sighted frequency or image
Background direct replacement, thus efficiently solve the replacement background that is faced in the prior art need to find it is a large amount of new
The technical issues of Background is so as to cause replacement background inconvenience and inefficiency, meanwhile, by using letter provided by the invention
Breath treating method and apparatus can simplify the process of replacement background picture, the efficiency of replacement background picture be improved, to facilitate use
Family uses, and greatly improves user experience.
In another embodiment provided by the invention, there is no any restriction for the type of the input content, only
It wants that scene can be described, described scene is capable of forming a picture, and the scene of the description for example can be " rainy
Red umbrella in it ", " Statue of Liberty when dawn ", " cartoon figure is under blue sky on meadow ", " packet of black " or
Person can also be " a pile book " etc., and the present invention is not especially limited herein, and user can be according to required to be formed specific
Picture inputs the input content for describing the picture, wherein the type of the input content for example can for word content,
At least one content in audio content, video content.
When the input content is word content, then the full content of word content or partial content are extracted crucial
Then word generates picture.For example, when word content is " Statue of Liberty when dawn ", then it can be based in above-mentioned whole
Hold and forms the width picture comprising the sun and Statue of Liberty；When word content be " Statue of Liberty under fine day, rainy day ", then
Keyword can be extracted based on partial content, then generate picture, for example, the freedom under display fine day can be generated in above content
Statue of Liberty under Lady Liberty and display rainy day.
When the input content is audio content, then text can be extracted based on audio content, to form word content,
Then according still further to above-mentioned when the form that input content is word content generates picture.In addition, for being sound when the input content
The case where frequency content, can also extract the tone in audio content in addition to it can extract the word content in audio content.
When the input content is video content, generation picture can be extracted based on many aspects of video content
Element, for example, can based on the caption recognition word content of video content, extract word content after, then according still further to above-mentioned
When the form that input content is word content generates picture；The audio content for being also based on video content extracts text, extracts
After word content, then according still further to above-mentioned when the form that input content is word content generates picture；Except above-mentioned based in video
The caption content and audio content of appearance are extracted outside the form of text, and a certain image content for being also based on video content directly mentions
Take picture, for example, video content be by many frame image constructions, can be directly based upon a certain width frame image directly as
Picture；Or the composograph of a few width frame images is also based on as the picture of generation；Again alternatively, working as the video content
In when including personage, can the contents such as body language based on the personage, movement, expression shape change or the dress ornament feature worn come
Text is extracted, or extracts word content alternatively to generate a kind of supplementary form of picture.
It is described to be based on the input content in one embodiment provided by the invention, by the background information of imaged object
Second background information is changed to by the first background information, including,
To input content processing, characteristic information is obtained；
The second background information is generated based on the characteristic information；
The background information of imaged object is changed to the second background information by the first background information.
In the present embodiment, if wanting the background information of the imaged object being changed to the second background by the first background information
Information, firstly, first to generate the second required background information, second background information is namely being replaced with original back
A different background picture of scape picture, will obtain second background information it is necessary to first handle the input content,
Characteristic information is obtained, for example, can use Recognition with Recurrent Neural Network RNN in embodiment provided by the invention and given birth to by input content
At characteristic information, the second background information is then obtained based on the characteristic information again.
Specifically, for convenience of description, following embodiment of the present invention is described so that input content is word content as an example, but
It does not constitute to any restriction of the invention, when the input content of other forms is converted to the input content of word content, with
The method that the word content obtains the second background information is consistent.
In a specific embodiment, when input content is " Statue of Liberty when dawn ", when by above-mentioned text
It should include the sun and Statue of Liberty in the picture, that is to say, that obtained characteristic information is just answered when content generates picture
When for " sun " and " Statue of Liberty ", then generating a pair picture based on " sun " and " Statue of Liberty " the two features.
In another specific embodiment, when input content is " cartoon figure is under blue sky on meadow ", when by above-mentioned
It should include cartoon figure, blue sky and meadow in the picture, that is to say, that obtained feature when word content generates picture
Information just should be " cartoon figure ", " blue sky " and " meadow ", then based on " cartoon figure ", " blue sky " and " meadow ", these three are special
Sign generates picture, certainly, in the present embodiment, due to the concrete image of cartoon figure and personage's picture that is uncertain, therefore generating
Nor it is unique, for example, a secondary picture can be generated based on " The Incredible Hulk " cartoon figure, " blue sky " and " meadow "；It can
To generate a secondary picture based on " Thunder God " cartoon figure, " blue sky " and " meadow "；It is also based on " The Incredible Hulk ", " Thunder God "
Two cartoon figures, " blue sky " and " meadow " generate secondary picture ... etc., in short, since " cartoon figure " is one wide in range
Concept, many qualified pictures can be generated based on above three feature, just do not enumerated herein, formed very
After several qualified pictures, user can according to condition or personal preference, select wherein a width or a few width carry out using.
It is described to input content processing in other embodiments provided by the invention, obtain characteristic information；Based on institute
It states characteristic information and generates the second background information, including,
To whole and/or partial input content processing, at least one corresponding characteristic information is obtained；
At least one described second background information is generated based at least one corresponding characteristic information.
In the present embodiment, the partial content of input content can be handled to obtain at least one corresponding feature
Information；The full content of input content can be handled to obtain at least one corresponding characteristic information；It can also be to defeated
The partial content and full content for entering content are all handled to obtain at least one corresponding characteristic information, and being then based on again should
At least one corresponding characteristic information generates at least one described second background information.
For example, in a specific embodiment, when the input content is " Statue of Liberty under fine day, rainy day ",
The partial content of above-mentioned input content can be handled, respectively obtain different characteristic informations, believed based on different features
Breath can obtain the second different background informations.For example, obtaining the characteristic information of " fine day ", can be given birth to based on features described above information
At the picture for having the sun；The characteristic information of " rainy day " is obtained, the picture with raindrop can be generated based on features described above information；
The characteristic information of " Statue of Liberty " is obtained, the picture with Statue of Liberty can be generated based on features described above information；It obtains
The characteristic information of " Statue of Liberty under fine day " can be generated based on features described above information with the sun and Statue of Liberty
Picture；The characteristic information of " Statue of Liberty under the rainy day " is obtained, can be generated based on features described above information with the sun and oneself
By the picture of Lady Liberty；Or the characteristic information of " fine day, rainy day " is obtained, it can be generated based on features described above information with raindrop
With the picture of the sun, that is, the picture of sun rain.
It, can be with when the input content is " Statue of Liberty under fine day, rainy day " in another specific embodiment
The full content of above-mentioned input content is handled, the characteristic information is obtained, can be obtained based on the characteristic information
Two background informations.For example, the characteristic information of " fine day, rainy day and Statue of Liberty " is obtained based on above-mentioned input content, based on upper
The picture with the sun, raindrop and Statue of Liberty, that is, the Statue of Liberty to rain in the sun can be generated by stating characteristic information
The picture of picture.
It, can be right when the input content is " Statue of Liberty under fine day, rainy day " in other specific embodiments
The partial content and full content of above-mentioned input content are all handled, and the different characteristic informations are obtained, based on different
The characteristic information can obtain the second different background informations.For example, being to carry out full content to above-mentioned input content
Processing again carry out part progress processing, available picture be respectively as follows: the picture with the sun, the picture with raindrop,
Picture with Statue of Liberty, the picture with the sun and Statue of Liberty, the picture with the sun and Statue of Liberty, band
There are the picture of raindrop and the sun and the picture with the sun, raindrop and Statue of Liberty, after generating above-mentioned different pictures, user
Can according to it is specific using need personal preference select one of picture or several pictures therein carry out using.
In another embodiment provided by the invention, due to having the different modes handled input content, example
The partial content of input content can such as be handled, the full content of input content can be handled, it can also be right
The partial content and full content of input content are all handled to obtain picture, in general, to the complete of the input content
Portion's content, which is handled, only can be obtained a qualified picture, and handling the partial content of the input content can
To obtain several qualified pictures, and all handled then can be with for the partial content and full content to the input content
More more fully qualified pictures are obtained, user can be based on the particular content of input content, to select specifically to scheme
Piece generates mode, or whithin a period of time, and user can choose a picture and generate mode, in this regard, can be according to user's
Specifically used needs or personal use habit are selected, and the present invention is not specifically limited.For example, for the first input content,
User can choose the schema creation all handled input content characteristic information corresponding with first input content；
For the second input content, user, which can choose, carries out in the schema creation and second input of part processing input content
Hold corresponding characteristic information；Further for example, in some day, what user selected all to be handled to this day all input content
Schema creation characteristic information；In another day, user selects this day all input content the mode for carrying out part processing raw
At characteristic information etc..
It is provided by the invention in one embodiment, the background information by imaged object is by the first background information
It is changed to the second background information, including,
Obtain imaged object；
Extract the foreground information of the imaged object；
Based on the foreground information and second background information, the imaged object is updated.
In the present embodiment, it if wanting to complete the replacement of the background information to the imaged object, first has to first obtain described
Imaged object, the present invention in, for obtain imaged object mode do not limit, can be obtained according to any mode will replace back
The influence object of scape picture.After getting the imaged object, the foreground information of the imaged object is extracted, for example, can be with
The foreground information of the imaged object is extracted using image Segmentation Technology, in embodiments of the present invention, for the foreground information
Can be personage, animal or trees also without any restriction, as long as that is, user want the content extracted can be by
Referred to as foreground information；After having extracted foreground information, using extracted foreground information and it is described using input content generate
Second background information synthesizes new imaged object, that is, completes the update for the imaged object.
It is provided by the invention in one embodiment, the foreground information for extracting the imaged object, including,
Based on the input content and the imaged object, foreground information is determined；
Extract the foreground information of the imaged object.
In the present embodiment, the specific method for extracting foreground information is provided, the foreground information is extracted, first have to elder generation
Determine foreground information, the determination of the foreground information will be determined together based on the input content and the imaged object, be determined
After the complete foreground information, then the foreground information is extracted from the imaged object.For example, in a specific embodiment,
The picture that the imaged object is presented is an adult and a spadger, and the input content is " green grassland ", and is needed
The result screen wanted is that only one spadger is on green grassland, so passing through above-mentioned imaged object and the input content
The foreground information determined is a spadger, that is to say, that although there are two people in the imaged object, one is into
Year people, a people spadger, when be not to say that two people will as foreground information, and according to the needs of final result picture,
Only selected one personal accomplishment foreground information of spadger extracts the foreground information after determining foreground information.
It is described to be based on the foreground information and second background information in other embodiments provided by the invention, more
The new imaged object, including,
Analyze the feature of the foreground information；
According to the feature of the foreground information, the second background information corresponding with this feature is matched；
To update the imaged object by matched second background information.
In the present embodiment, the feature for first having to analysis foreground information, is then based on the feature of the foreground information, matches
The second background information corresponding with this feature provides two kinds of corresponding with the feature of foreground information second backgrounds of matching in the present invention
The mode of information.
First way:
It handles to obtain the second all background informations to whole and/or the partial input content, is then based on institute
The second all background informations is obtained to be matched with the foreground information, thus select one with the foreground information the most
Matched picture.For example, the feature of foreground information is " little girl to hold up an umbrella ", the input content is " fine day, rainy day ",
The picture that then can be at most formed based on the input content is, the picture with raindrop, the picture with the sun and with rain
The picture of drop and the sun, since the umbrella that little girl beats both may be the parasol for sunshade, it is also possible to the umbrella to keep off the rain, therefore
Three pictures of above-mentioned formation can be effectively matched with the foreground information, be based on foreground information and three Zhang Shengcheng at this time
The second background information can generate three kinds of final result images, further, user can according to specifically use need
To select wherein one carry out using.
The second way:
According to the specific features of foreground information, to be adjusted to the second background information, so that second background information
It is matched with the foreground information.For example, in a specific embodiment, the imaged object is to wear the spadger of green jacket to lie
On sandy beach, the input content is green grassland, and the objective result picture needed to form is to wear the spadger of green jacket to lie in
On green grassland, at this point, being the spadger for wearing green jacket by the foreground information that the imaged object is determined, by the extraction
Foreground information and the second background information generated based on the input content generate new imaged object, that is to say, that complete
Replacement for the imaged object background, but since objective result picture is to wear the spadger of green jacket to lie in green grass
On the ground, if the two green contrasts it is unobvious, it is easy to cause visual coincidence, so when the second background information
Green grassland green contrast can be adjusted based on the green of the green jacket of the spadger in foreground information so that described
Although green grassland and the green jacket are all green, but have certain color contrast, also be can be realized as two
The differentiation of person.
In other embodiments provided by the invention, the foreground information for extracting the imaged object, including,
It identifies the first background information, the imaged object is handled based on different first background informations；
The foreground information of the imaged object after extraction process.
In the present embodiment, if the imaged object is one section of video, which shares 2 minutes contents, but the video
0-1 minute be shown a spadger climb snow mountain again, the 1-2 minute content of video is shown a little girl and is leaking informaton
Zither, so if wanting the foreground information of the extraction video, it should be carried out respectively according to video in the content that different periods are shown
Stage extraction, this also just needs to identify the first different background informations, that is to say, that piecewise to first background information into
Row identification, is then based on different first background informations and handles the imaged object, for example, 0-1 points in above-mentioned video
First background information of clock is the snow mountain of white, and 1-2 minute the first background informations are blue sky in video, that is,
It says, 0-1 minutes videos are same background information in video, and 1-2 minute videos are same background information in video, then may be used
Selectively to be handled the imaged object using background information as boundary, such as can choose to 0-1 minutes in video
Video does not do the processing of replacement background information, and background picture is changed to blue to 1-2 minutes in video video selections
There are many balloons of animals shaped white clouds and various colors for sky.
Further, based on to video in different time periods by the way of different replacement backgrounds, therefore between also wanting timesharing
Section extracts the foreground information.For example, the embodiment continued the above, since 0-1 minutes in video videos are not done more
The processing of background information is changed, therefore does not also need the video extraction foreground information to described 0-1 minutes, and for 1-2 minutes views
Frequency needs replacing background information, then only needs to extract the foreground information of 1-2 minutes videos.
In another embodiment provided by the invention, the imaged object includes frame image, in which:
The acquisition imaged object, including,
Obtain the frame image of the imaged object.
In the present embodiment, for video and dynamic picture, frame image, a video or Dynamic Graph are all had
Piece is by many frame image constructions；It include only a width frame image for static images.Therefore in implementation provided by the invention
In example, if wanting to complete the replacement of the background information for the imaged object, being substantially will be to the every of the imaged object
One frame image all carries out the replacement of background information.For example, in one embodiment, the acquisition imaged object exactly obtains institute
State the frame image of imaged object, that is to say, that obtain the every of the imaged object for the certain time period for needing to carry out replacing background
One frame image.In another embodiment, the foreground information for extracting the imaged object, before extracting in frame image
Scape information, that is to say, that before each frame image that extract the imaged object for the certain time period for needing to carry out replacing background
Scape information.
Based on the same inventive concept, as shown in Fig. 2, second embodiment of the invention provides a kind of information processing unit, until
Less include memory, processor, computer program be stored on the memory, the processor executes following steps:
Input content is received, the input content can be used in describing scene information；
Based on the input content, the background information of imaged object is changed to the second background letter by the first background information
Breath；
Wherein, the imaged object includes foreground information and first background information different from the foreground information, institute
The second background information is stated corresponding to the scene information.
It is apparent to those skilled in the art that for convenience and simplicity of description, the information of foregoing description
Information processing unit corresponding to processing method, can be with reference to the corresponding description in aforementioned information processing method embodiment, herein
It repeats no more.
Above embodiments are only the exemplary embodiment of the application, are not used in limitation the application, the protection scope of the application
It is defined by the claims.Those skilled in the art can make respectively the application in the essence and protection scope of the application
Kind modification or equivalent replacement, this modification or equivalent replacement also should be regarded as falling within the scope of protection of this application.
Claims (10)
1. a kind of information processing method, including,
Input content is received, the input content can be used in describing scene information；
Based on the input content, the background information of imaged object is changed to the second background information, institute by the first background information
Stating imaged object includes foreground information and first background information different from the foreground information, second background information pair
Scene information described in Ying Yu.
2. according to the method described in claim 1, described be based on the input content, by the background information of imaged object by first
Background information is changed to the second background information, including,
To input content processing, characteristic information is obtained；
The second background information is generated based on the characteristic information；
The background information of imaged object is changed to the second background information by the first background information.
3. obtaining characteristic information according to the method described in claim 2, described handle the input content；Based on the spy
Reference breath generates the second background information, including,
To whole and/or partial input content processing, at least one corresponding characteristic information is obtained；
At least one described second background information is generated based at least one corresponding characteristic information.
4. according to the method described in claim 1, the imaged object includes video, dynamic picture and static images.
5. according to the method described in claim 2, the background information by imaged object is changed to by the first background information
Two background informations, including,
Obtain imaged object；
Extract the foreground information of the imaged object；
Based on the foreground information and second background information, the imaged object is updated.
6. according to the method described in claim 5, the foreground information for extracting the imaged object, including,
Based on the input content and the imaged object, foreground information is determined；
Extract the foreground information of the imaged object.
7. according to the method described in claim 5, described be based on the foreground information and second background information, described in update
Imaged object, including,
Analyze the feature of the foreground information；
According to the feature of the foreground information, the second background information corresponding with this feature is matched；
To update the imaged object by matched second background information.
8. according to the method described in claim 5, the imaged object includes frame image, in which:
The acquisition imaged object, including,
Obtain the frame image of the imaged object.
9. according to the method described in claim 8, the foreground information for extracting the imaged object, including, extract frame image
In foreground information.
10. a kind of information processing unit includes at least memory, processor, is stored with computer program on the memory, institute
It states processor and executes following steps:
Input content is received, the input content can be used in describing scene information；
Based on the input content, the background information of imaged object is changed to the second background information by the first background information；
Wherein, the imaged object includes foreground information and first background information different from the foreground information, and described the
Two background informations correspond to the scene information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910585982.8A CN110298904A (en) | 2019-07-01 | 2019-07-01 | A kind of information processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910585982.8A CN110298904A (en) | 2019-07-01 | 2019-07-01 | A kind of information processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110298904A true CN110298904A (en) | 2019-10-01 |
Family
ID=68029737
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910585982.8A Pending CN110298904A (en) | 2019-07-01 | 2019-07-01 | A kind of information processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110298904A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200402214A1 (en) * | 2018-02-08 | 2020-12-24 | Samsung Electronics Co., Ltd. | Method and electronic device for rendering background in image |
| CN112689196A (en) * | 2021-03-09 | 2021-04-20 | 北京世纪好未来教育科技有限公司 | Interactive video playing method, player, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105120189A (en) * | 2015-08-31 | 2015-12-02 | 河海大学常州校区 | Weather forecast program direction method based on Kinect |
| JP2017191501A (en) * | 2016-04-14 | 2017-10-19 | キヤノン株式会社 | Information processing apparatus, information processing method, and program |
| CN107547804A (en) * | 2017-09-21 | 2018-01-05 | 北京奇虎科技有限公司 | Realize the video data handling procedure and device, computing device of scene rendering |
| CN109377502A (en) * | 2018-10-15 | 2019-02-22 | 深圳市中科明望通信软件有限公司 | A kind of image processing method, image processing apparatus and terminal device |
-
2019
- 2019-07-01 CN CN201910585982.8A patent/CN110298904A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105120189A (en) * | 2015-08-31 | 2015-12-02 | 河海大学常州校区 | Weather forecast program direction method based on Kinect |
| JP2017191501A (en) * | 2016-04-14 | 2017-10-19 | キヤノン株式会社 | Information processing apparatus, information processing method, and program |
| CN107547804A (en) * | 2017-09-21 | 2018-01-05 | 北京奇虎科技有限公司 | Realize the video data handling procedure and device, computing device of scene rendering |
| CN109377502A (en) * | 2018-10-15 | 2019-02-22 | 深圳市中科明望通信软件有限公司 | A kind of image processing method, image processing apparatus and terminal device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200402214A1 (en) * | 2018-02-08 | 2020-12-24 | Samsung Electronics Co., Ltd. | Method and electronic device for rendering background in image |
| CN112689196A (en) * | 2021-03-09 | 2021-04-20 | 北京世纪好未来教育科技有限公司 | Interactive video playing method, player, equipment and storage medium |
| CN112689196B (en) * | 2021-03-09 | 2021-06-11 | 北京世纪好未来教育科技有限公司 | Interactive video playing method, player, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108012081B (en) | Intelligent beautifying method, device, terminal and computer readable storage medium | |
| US8908904B2 (en) | Method and system for make-up simulation on portable devices having digital cameras | |
| WO2021036853A1 (en) | Image processing method and electronic apparatus | |
| CN108197574B (en) | Character style recognition method, terminal and computer readable storage medium | |
| CN110110118A (en) | Dressing recommended method, device, storage medium and mobile terminal | |
| CN110464633A (en) | Acupuncture point recognition methods, device, equipment and storage medium | |
| US20230154083A1 (en) | Method for Assisting Makeup, Terminal Device, Storage Medium, and Program Product | |
| CN104157001A (en) | Method and device for drawing head caricature | |
| CN110298904A (en) | A kind of information processing method and device | |
| CN110866139A (en) | Cosmetic treatment method, device and equipment | |
| CN109359317A (en) | A kind of lipstick is matched colors the model building method and lipstick color matching selection method of selection | |
| CN106649465A (en) | Recommendation and acquisition method and device of cosmetic information | |
| CN106530309A (en) | Video matting method and system based on mobile platform | |
| CN111147751B (en) | Photographing mode generation method and device and computer readable storage medium | |
| CN105913400A (en) | Device for obtaining high-quality and real-time beautiful image | |
| CN110290426A (en) | Method, apparatus, equipment and the storage medium of showing resource | |
| WO2023109829A1 (en) | Image processing method and apparatus, electronic device, and storage medium | |
| JP2004005534A (en) | Image preserving method, retrieving method and system of registered image, image processing method of registered image and program for executing these methods | |
| CN107766803B (en) | Video character decorating method and device based on scene segmentation and computing equipment | |
| CN105976309A (en) | High-efficiency and easy-parallel implementation beauty mobile terminal | |
| CN114758027A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| JP2004240622A (en) | Image processing method, image processor and image processing program | |
| KR102599194B1 (en) | Hair styling service providing system and hair image extraction apparatus and method for extracting hair image using the same | |
| CN108171716B (en) | Video character decorating method and device based on self-adaptive tracking frame segmentation | |
| CN110933354B (en) | Customizable multi-style multimedia processing method and terminal thereof |
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 |