CN104869346A - Method and electronic equipment for processing image in video call - Google Patents

Method and electronic equipment for processing image in video call Download PDF

Info

Publication number
CN104869346A
CN104869346A CN201410066656.3A CN201410066656A CN104869346A CN 104869346 A CN104869346 A CN 104869346A CN 201410066656 A CN201410066656 A CN 201410066656A CN 104869346 A CN104869346 A CN 104869346A
Authority
CN
China
Prior art keywords
image
head portrait
user
field picture
difference
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
Application number
CN201410066656.3A
Other languages
Chinese (zh)
Inventor
杨黎波
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Mobile Communications Group Co Ltd
Original Assignee
China Mobile Communications Group Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Mobile Communications Group Co Ltd filed Critical China Mobile Communications Group Co Ltd
Priority to CN201410066656.3A priority Critical patent/CN104869346A/en
Publication of CN104869346A publication Critical patent/CN104869346A/en
Pending legal-status Critical Current

Links

Abstract

The embodiment of the invention provides a method and electronic equipment for processing images in a video call. The method comprises the steps of receiving a user head portrait after image stylized processing sent by a target terminal when in video call with the target terminal, retrieving a prestored background image, generating an image to be displayed containing the user head portrait and the background image according to the user head portrait and the background image, and finally displaying the generated image to be displayed. That is, the terminal receives the user head portrait after image stylized processing during the video call process, thus the user can retrieve any background image prestored in terminal equipment to be combined with the user head portrait, so that the final displaying effect is more diverse, thereby avoiding the problem of single display format during the video call process, and enhancing the interestingness in the video call process.

Description

Image processing method in a kind of video calling and electronic equipment
Technical field
The present invention relates to the Display Technique field in mechanics of communication, particularly relate to the image processing method electronic equipment in a kind of video calling.
Background technology
Along with the rise of image editing software, to the stylization process of image and video and share and become new focus.Stylization process processes original image and video exactly, to generate specific artistic effect, comprises filter, cartoon, oil painting, sketch etc.
Video calling avatars business is that the one enriching video telephony applications is attempted, user orders virtual image by business platform, show at mobile phone terminal in calling course of video telephone, to increase the interest of video telephone, but virtual image is the fixing several of systemic presupposition, the display format of therefore current video calling is comparatively single, and the experience of user is poor.
Summary of the invention
The invention provides the image processing method in a kind of video calling and electronic equipment, comparatively single in order to solve in prior art display format in video call process.
Its concrete technical scheme is as follows:
An image processing method in video calling, comprising:
When carrying out video calling with object terminal, receive the user's head portrait through image stylization process that object terminal sends;
Transfer the background image prestored, according to described user's head portrait and described background image, generate the image to be displayed comprising described user's head portrait and described background image;
The described image to be displayed that display generates.
Optionally, according to described user's head portrait and described background image, generate the image to be displayed comprising described user's head portrait and described background image, comprising:
According to pre-set zoom ratio, convergent-divergent process is carried out to the described user's head portrait received, and generate described image to be displayed according to the user's head portrait after convergent-divergent process and described background image.
Optionally, described pre-set zoom ratio is specially:
( M × N ) = ( 3 4 * H l ) · ( J × K )
Wherein, J × K is the length of described user's head portrait and wide, M × N is the length of user's head portrait after convergent-divergent process and wide, and H is longitudinal pixel number of the display screen for showing image to be displayed, and l is for showing longitudinal pixel number of the viewing area of user's head portrait in display screen.
An image processing method in video calling, comprising:
When carrying out video calling with object terminal, in the image collected, extract user's head portrait;
Image stylization process is carried out to the described user's head portrait extracted, and the user's head portrait to be shown after synthetic image stylization process;
Described user's head portrait to be shown is sent to described object terminal, shows according to described user's head portrait to be shown to make described object terminal.
Optionally, collection to image in extract user's head portrait, comprising:
Collected the N continuous two field picture comprising user's head portrait by image acquisition device, wherein, N be more than or equal to 2 positive integer;
In described N two field picture, determine a frame key frame images, and in described key frame images, extract described user's head portrait.
Optionally, in described N two field picture, determine a frame key frame images, comprising:
In described N two field picture, determine the image-region that user's head portrait in every two field picture is corresponding, and determine the average pixel value of the image-region that user's head portrait in every two field picture is corresponding;
Difference between the average pixel value obtaining the image-region in described N two field picture in every two continuous frames image;
Judge whether have the difference being greater than threshold value in the difference obtained;
When being greater than the difference of described threshold value if exist, then determine maximum difference in all being greater than in the difference of described threshold value, and the two field picture gathered rear in two continuous frames image corresponding for described maximum difference is defined as described key frame images;
If when there is not the difference being greater than described threshold value, then in continuous print N two field picture, an arbitrary two field picture of choosing is defined as described key frame images.
Optionally, the difference between the average pixel value of the described image-region of two continuous frames image is obtained by following formula:
S = 1 h · l Σ i = 1 , j = 1 h , l ( | p t , i , j - p t - 1 , i , j | )
Wherein, S characterizes the difference between the average pixel value of two continuous frames image, the frame number of t token image, h characterizing consumer head portrait longitudinal pixel number in the picture, l characterizing consumer head portrait pixels across is in the picture counted, p characterizes the value of each pixel, the pixel value shared by the height of i token image, the wide shared pixel value of j token image.
A kind of electronic equipment, comprising:
Communication module, for when carrying out video calling with object terminal, receives the user's head portrait through image stylization process that object terminal sends;
Processor, for transferring the background image prestored, according to described user's head portrait and described background image, generates the image to be displayed comprising described user's head portrait and described background image;
Display, for showing the described image to be displayed of generation.
Optionally, described processor, specifically for carrying out convergent-divergent process according to pre-set zoom ratio to the described user's head portrait received, and generates described image to be displayed according to the user's head portrait after convergent-divergent process and described background image.
A kind of electronic equipment, comprising:
Image acquisition device, for when carrying out video calling with object terminal, gathers image;
Processor, for extracting user's head portrait in the image collected, carries out image stylization process to the described user's head portrait extracted, and the user's head portrait to be shown after synthetic image stylization process;
Communication interface, for described user's head portrait to be shown is sent to described object terminal, shows according to described user's head portrait to be shown to make described object terminal.
Optionally, described processor specifically determines a frame key frame images in comprising in the N continuous two field picture of user's head portrait of being collected by image acquisition device, and in described key frame images, extract described user's head portrait, wherein, N be more than or equal to 2 positive integer.
Optionally, described processor specifically for determining the image-region that user's head portrait in every two field picture is corresponding in described N two field picture, and determine the average pixel value of the image-region that user's head portrait in every two field picture is corresponding, difference between the average pixel value obtaining the image-region in described N two field picture in every two continuous frames image, judge whether have the difference being greater than threshold value in the difference obtained, when being greater than the difference of described threshold value if exist, then determine maximum difference in all being greater than in the difference of described threshold value, and the rear two field picture in two continuous frames image corresponding for described maximum difference is defined as described key frame images, if when there is not the difference being greater than described threshold value, then in continuous print N two field picture, an arbitrary two field picture of choosing is defined as described key frame images.
A kind of video interactive system, comprising:
When source terminal and object terminal set up video calling be connected time, described source terminal extracts user's head portrait in the image collected, and to described user's head portrait carry out image stylization process;
User's head portrait after image stylization process is sent to described object terminal by source terminal;
Described object terminal, when receiving described user's head portrait, transfers the background image prestored, and based on described user's head portrait and described background image, generates and show the image to be displayed comprising described user's head portrait and described background image.
Optionally, described source terminal, specifically for being collected the N continuous two field picture comprising user's head portrait by the image acquisition device of self, a frame key frame images is determined in described N two field picture, and in described key frame images, extract described user's head portrait, wherein, N be more than or equal to 2 positive integer.
Optionally, described source terminal, specifically for determining the image-region that user's head portrait in every two field picture is corresponding in described N two field picture, and determine the average pixel value of the image-region that user's head portrait of every two field picture is corresponding, difference between the average pixel value obtaining the image-region in described N two field picture in every two continuous frames image, judge whether have the difference being greater than threshold value in the difference obtained, when being greater than the difference of described threshold value if exist, then determine maximum difference in all being greater than in the difference of described threshold value, and the rear two field picture in two continuous frames image corresponding for described maximum difference is defined as described key frame images, if when there is not the difference being greater than described threshold value, then in continuous print N two field picture, an arbitrary two field picture of choosing is defined as described key frame images.
Optionally, described object terminal, specifically for carrying out convergent-divergent process according to pre-set zoom ratio to the described user's head portrait received, and generates described image to be displayed according to the user's head portrait after convergent-divergent process and described background image.
The image processing method in a kind of video calling is provided in the embodiment of the present invention, the method comprises: when with object terminal set up video calling be connected time, user's head portrait is extracted in comprising in the image of user's head portrait of being collected by image acquisition device, then image stylization process is carried out to the user's head portrait extracted, and the user's head portrait to be shown obtained after image stylization process, finally user's head portrait to be shown is sent to object terminal, with the user's head portrait making object terminal demonstration to be shown, this pre-set image process can be treated to cartoon head portrait or animal head etc. by user's head portrait in embodiments of the present invention, which not only adds the formation of video calling, and the user's head portrait be just transferred through in video call process after image procossing, decrease taking of Internet resources, save the network bandwidth.
Accompanying drawing explanation
Fig. 1 is the flow chart of the image processing method in the embodiment of the present invention in a kind of video calling;
Fig. 2 is the video call process schematic diagram in the embodiment of the present invention between terminal;
Fig. 3 is the flow chart of the image processing method in the embodiment of the present invention in another kind of video calling;
Fig. 4 is the structural representation of a kind of electronic equipment in the embodiment of the present invention;
Fig. 5 is the structural representation of another kind of electronic equipment in the embodiment of the present invention;
Fig. 6 is the structural representation of a kind of video interactive system in the embodiment of the present invention.
Embodiment
Below by specific embodiment, technical solution of the present invention is described in detail.
Embodiment one:
Current, video calling is widely used, but in the process of present video calling be all terminal directly by the image transmitting that collects to object terminal, such video calling mode form is single.
In order to solve the problem that in current video communication process, display format is single in the embodiment of the present invention, embodiments provide the image processing method in video calling, the method comprises: when carrying out video calling with object terminal, receive the user's head portrait through image stylization process that object terminal sends, transfer the background image prestored, and according to user's head portrait and background image, generate the image to be displayed comprising user head's picture and background image, finally show the image to be displayed of generation.That is in video call process, user's head portrait after image stylization process that what terminal received is, such user just can transfer out any background image of prestoring in terminal equipment and user's head portrait combines, thus make the effect of last display more various, and then avoid the problem of the single display form in video call process, improve the interest in video call process.
Below technical solution of the present invention is described in detail.
Be illustrated in figure 1 the flow chart of the image processing method in the embodiment of the present invention in a kind of video calling, the method comprises:
S101, when carrying out video calling with object terminal, receives the user's head portrait through image stylization process that object terminal sends;
First, carry out in the process of video calling at present terminal and object terminal, what present terminal received will be the user's head portrait after image stylization process that object terminal sends, and image stylization process here can be cartoon style, ink and wash style, sketch style, filter style etc.
S102, transfers the background image prestored, and according to user's head portrait and background image, generates the image to be displayed comprising user's head portrait and background image;
The mode transferring the background image prestored herein has multiple: the first, user a width background image in the background image prestored in present terminal, can be selected; The second, can be the background image that user transfers out user corresponding to present terminal and commonly uses in the webserver, can meet the demand of different user to different background image like this; The third, by present terminal random in the background image prestored, select a width background image; 4th kind, present terminal goes out the background image identical with the image stylization mode of user's head portrait according to the image stylization way selection of the user's head portrait received, such as user's head portrait is cartoon style, then present terminal just selects the background image of a width cartoon style.
The mode of certain selection background image can also have other selection mode except above-mentioned four kinds of modes, does not just enumerate in embodiments of the present invention.In addition, reserved viewing area also in the background image selected user's head portrait, after that is present terminal obtains user's head portrait, this user's head portrait will be added in the viewing area that background image reserves.
Further, because the display screen size of present terminal and object terminal may exist certain difference, therefore the user's head portrait sent in order to avoid object terminal cannot show or show in present terminal, therefore, present terminal is after the user's head portrait receiving the transmission of object terminal, present terminal carries out convergent-divergent process by according to pre-set zoom ratio to the user's head portrait received, and concrete zoom operation formula can carry out according to formula (1):
( M × N ) = ( 3 4 * H l ) · ( J × K )
Wherein, J × K is the length of user's head portrait and wide, and M × N is the length of user's head portrait after convergent-divergent process and wide, and H is longitudinal pixel number of the display screen of present terminal, l is for showing longitudinal pixel number of the viewing area of user's head portrait in the display screen of present terminal, here be scaling.
Specifically, if the display screen of present terminal is less, and the size of user's head portrait that object terminal sends is comparatively large, now present terminal will reduce process according to formula (1) to the user's head portrait received, thus ensures that user's head portrait can in the display screen display of present terminal; Certainly, be exactly that amplification process is carried out to user's head portrait conversely, ensure that user's head portrait that present terminal shows is in preferably size like this, user is watched more convenient.
Certainly, the user's head portrait sent between the terminal for same model carries out convergent-divergent process with regard to no longer needing.
After selecting background image and user's head portrait processed, present terminal generates image to be displayed by based on the user's head portrait after background image and process, ratio as shown in Figure 2, after present terminal receives user's head portrait of the cartoon style that object terminal sends in fig. 2, present terminal determines background image, then user's head portrait is added in the viewing area reserved in background image, thus form the image to be displayed finally demonstrated, the compound mode of wherein a kind of user's head portrait and background image is just shown in certain Fig. 2, the compound mode of user's head portrait and background image can be determined according to the self-defined selection of user in the application of reality.
S103, the image to be displayed that display generates.
Carry out in video call process in terminal in embodiments of the present invention, after terminal receives the user's head portrait after image stylization process, terminal will determine that any background image of prestoring and user's head portrait combine, thus make the effect of last display more various, and then the single display format avoided in video call process, improve the interest in video call process.
Embodiment two:
Carry out in the process of video calling at two terminals, in order to ensure that object terminal can receive the user's head portrait after stylization process, simultaneously also in order to reduce terminal data traffic in video call process, therefore the image processing method in a kind of video calling is provided in the embodiment of the present invention, the method comprises: when carrying out video calling with object terminal, user's head portrait is extracted in the image collected, then image stylization process is carried out to the user's head portrait extracted, and the user's head portrait to be shown after synthetic image stylization process, finally user's head portrait to be shown is sent to object terminal, that is the just user's head portrait sent in video call process, and the user's head portrait be through after image stylization process, the display which not only adds video calling is formed and interest, and also reduce data traffic consumption in video call process, reduce taking of Internet resources, save the network bandwidth.
Below by accompanying drawing and specific embodiment, technical solution of the present invention is described in detail.
Be illustrated in figure 3 the schematic diagram of a kind of video call method in the embodiment of the present invention, the method comprises:
S301, when carrying out video calling with object terminal, extracts user's head portrait in the image collected;
S302, carries out image stylization process to the user's head portrait extracted, and obtains the user's head portrait to be shown after image stylization process;
S303, is sent to object terminal by user's head portrait to be shown.
In embodiments of the present invention, at present terminal and object terminal in the process at video calling, present terminal can be extract after user's head portrait carries out image stylization process to be sent to object terminal in the every two field picture collected; Also in the image collected, first can determine key frame images, and then extract in key frame images user's head portrait carry out image stylization process after be sent to object terminal.
Be described for two kinds of different situation methods to video calling below.
Situation one: all extract user's head portrait in every two field picture
First, when present terminal will carry out video calling with object terminal, the image acquisition device in present terminal, such as camera, the real-time collection of meeting comprises the image of user's head portrait.
After present terminal obtains the first two field picture, present terminal will identify user's head portrait in the first two field picture, that is: this terminal detects in the image collected whether there is face characteristic, if when there is face characteristic, the viewing area of corresponding face characteristic is then got according to pre-set dimension frame, and the image in this viewing area is defined as user's head portrait, be exactly simply the process of recognition of face.
Present terminal extracts user's head portrait from the first two field picture, and to the image stylization processing mode that user's head portrait presets, can certainly be that user selects the interim image stylization processing mode selected, such as user's head portrait is treated to cartoon style head portrait, or be treated to sketch style head portrait, also or be treated to ink and wash style head portrait etc., certainly be not only three kinds of lifted stylized processing modes, user's head portrait through stylization process will be formed according to adding display, also improve the interest of display simultaneously, improve Consumer's Experience.
User's head portrait to be shown after stylization process is sent to object terminal by present terminal, user's head portrait to be shown adds in default background image by object terminal, thus generate the image comprising background image and user's head portrait to be shown, last object terminal just can show the image comprising background image and user's head portrait to be shown, so also make the display mode of object terminal abundanter, and also improve the interest of whole video calling, improve Consumer's Experience.
Certainly, each follow-up two field picture is all identical with the processing mode of the first two field picture.
Situation two: first determine key frame images in the image collected, and then in key frame images, extract user's head portrait
Owing in video call process being continuous print collection image, in general, difference between continuous print two two field picture or continuous print three two field picture is all less, if each two field picture all extracts user's head portrait, and user's head portrait of each two field picture is all sent to object terminal, then can cause the waste of certain Internet resources, therefore first key frame images can be selected in continuous print N two field picture in embodiments of the present invention in video call process, and then in key frame images, extract user's head portrait, wherein, N be more than or equal to 2 positive integer.Such as select 1 two field picture in 3 two field pictures as key frame images, then only identify and extract the user's head portrait in key frame,
Specifically, key frame images can be determined by following mode in continuous print N two field picture:
The head portrait region that user's head portrait is corresponding is determined in N two field picture, specifically can determine head portrait region by the mode of recognition of face, then terminal is by the difference between the average pixel value in the head portrait region of every two continuous frames image in acquisition N two field picture, this difference just characterizes the change of divergence of user's head portrait in fact, and this difference can be passed through formula (1) and obtain:
S = 1 h · l Σ i = 1 , j = 1 h , l ( | p t , i , j - p t - 1 , i , j | ) - - - ( 1 )
Wherein, S characterizes the difference between the average pixel value of two continuous frames image, the frame number of t token image, h characterizing consumer head portrait longitudinal pixel number in the picture, l characterizing consumer head portrait pixels across is in the picture counted, p characterizes the value of each pixel, the pixel value shared by the height of i token image, the wide shared pixel value of j token image.
After terminal gets all differences, all differences and threshold value compare by terminal, threshold value herein can be selected according to different application scenarioss or arrange, if when existence is greater than the difference of threshold value, then in the difference being greater than threshold value, determine maximum difference, then the rear two field picture in two continuous frames image corresponding for maximum difference is defined as key frame images.
Such as: need to determine key frame images in continuous print 4 two field picture, therefore terminal can determine head portrait region in the first two field picture, the second two field picture, the 3rd two field picture, the 4th two field picture, then terminal starts the difference of the average pixel value in the head portrait region calculated in the first two field picture and the second two field picture, and second difference of average pixel value in head portrait region in two field picture and the 3rd two field picture, and the difference of the average pixel value in head portrait region in the 3rd two field picture and the 4th two field picture.If the difference of the first two field picture and the second two field picture is greater than threshold value, and when the difference of the second two field picture and the 3rd two field picture is also greater than threshold value, the difference comparing the first two field picture and the second two field picture is then also needed whether to be greater than the difference of the second two field picture and the 3rd two field picture, if when the difference of the second two field picture and the 3rd two field picture is larger, then using the 3rd two field picture as key frame images, and other remaining images can directly abandon, if when certainly only having the difference of the second two field picture and the 3rd two field picture to be greater than threshold value, then using the 3rd image as key frame images.
Certainly, if when all differences that present terminal gets all are less than threshold value, then using the arbitrary two field picture in N two field picture as key frame images, or last frame image is as key frame images, and abandons other remaining images.
By determining key frame images in continuous print N two field picture, the number of times of present terminal to object terminal transmission user head portrait can be reduced, namely decrease the data transfers between present terminal and object terminal, thus decrease taking of Internet resources.
After present terminal obtains key frame images, to identify in key frame images and extract user's head portrait, then process according to pre-set image stylization, image stylization process is carried out to the user's head portrait extracted, finally user's head portrait of having processed of image stylization is sent to object terminal, thus object terminal can be combined with default background image according to the user's head portrait received and to generate final display image.
Embodiment three:
The method of a kind of video calling in the corresponding embodiment of the present invention one, the embodiment of the present invention additionally provides a kind of electronic equipment, and be illustrated in figure 4 a kind of electronic devices structure schematic diagram in the embodiment of the present invention, this electronic equipment comprises:
Communication module 401, for when carrying out video calling with object terminal, receives the user's head portrait through image stylization process that object terminal sends;
Processor 402, for transferring the background image prestored, according to described user's head portrait and described background image, generates the image to be displayed comprising user's head portrait and background image;
Display 403, for showing the image to be displayed of generation.
Further, if when user's head portrait that this electronic equipment receives in embodiments of the present invention cannot show over the display or show less, processor 402 in this electronic equipment specifically for carrying out convergent-divergent process according to pre-set zoom ratio to the described user's head portrait received, and generates described image to be displayed according to the user's head portrait after convergent-divergent process and described background image.
After user's head portrait after obtaining image stylization process, processor 402 in this electronic equipment is by a width background image in transferring in the background image prestored, and the user's head portrait obtained and background image are combined, ratio as shown in Figure 2, thus the processor 402 in electronic equipment will generate image to be displayed, image to be displayed is sent to display 403 by last processor 402, and display 403 shows according to the image to be displayed obtained.
Embodiment four:
A kind of method of video calling in the corresponding embodiment of the present invention two, the embodiment of the present invention additionally provides a kind of electronic equipment, is illustrated in figure 5 the structural representation of a kind of electronic equipment in the embodiment of the present invention, and this electronic equipment comprises:
Image acquisition device 501, for when carrying out video calling with object terminal, gathers image;
Processor 502, for extracting user's head portrait in the image collected, is carrying out image stylization process to the user's head portrait extracted, and the user's head portrait to be shown after synthetic image stylization process;
Communication interface 503, for user's head portrait to be shown is sent to object terminal, shows according to user's head portrait to be shown to make object terminal.
Wherein, image acquisition device 501 can for camera or other can carry out the equipment of IMAQ, and be connected with processor 502, after image acquisition device 501 collects image, processor 502 processes to the image collected, namely by recognition of face, identify the user's head portrait in the image collected.
Further, processor 502 is specifically for determining a frame key frame images being collected by image acquisition device in the N continuous two field picture comprising user's head portrait in embodiments of the present invention, and in described key frame images, extract described user's head portrait, wherein, N be more than or equal to 2 positive integer.
Further, processor 502 specifically for determining the image-region that user's head portrait in every two field picture is corresponding in N two field picture in embodiments of the present invention, and determine the average pixel value of the image-region that user's head portrait of every two field picture is corresponding, difference between the average pixel value of the image-region in acquisition N two field picture in every two continuous frames image, judge whether have the difference being greater than threshold value in the difference obtained, when being greater than the difference of threshold value if exist, then determine maximum difference in all being greater than in the difference of threshold value, and the rear two field picture in two continuous frames image corresponding for maximum difference is defined as key frame images, if when there is not the difference being greater than threshold value, then in continuous print N two field picture, an arbitrary two field picture of choosing is defined as key frame images.
Embodiment five:
The embodiment of the present invention additionally provides a kind of video interactive system, be illustrated in figure 6 the structural representation of a kind of video interactive system in the embodiment of the present invention, this system comprises source terminal 601 and object terminal 602, at source terminal 601 with the video call process of object terminal 602:
Source terminal 601, extracts user's head portrait in the image collected, and carries out image stylization process to user's head portrait, and the user's head portrait after image stylization process is sent to object terminal 602;
Object terminal 602, when receiving described user's head portrait that source terminal 601 sends, transfer the background image prestored, and based on described user's head portrait and described background image, generate and show the image to be displayed comprising described user's head portrait and described background image.
In the application of reality, in the process of video calling, source terminal 601 and object terminal 602 are all carrying out identical processing procedure, that is, while source terminal 601 sends the user's head portrait after image stylization process to object terminal 602, the user head portrait of object terminal 602 also after send image stylization process to source terminal 601.Communication process between certain source terminal 601 and object terminal 602 is completed by network.
In addition, source terminal 601 in embodiments of the present invention, specifically for being collected the N continuous two field picture comprising user's head portrait by the image acquisition device of self, a frame key frame images is determined in described N two field picture, and in described key frame images, extract described user's head portrait, wherein, N be more than or equal to 2 positive integer.
Then source terminal 601 determines the image-region that user's head portrait in every two field picture is corresponding in N two field picture, and determine the average pixel value of the image-region that user's head portrait of every two field picture is corresponding, difference between the average pixel value of the image-region in acquisition N two field picture in two continuous frames image, judge whether have the difference being greater than threshold value in the difference obtained, when being greater than the difference of described threshold value if exist, then determine maximum difference in all being greater than in the difference of threshold value, and the rear two field picture in two continuous frames image corresponding for maximum difference is defined as key frame images, if when there is not the difference being greater than threshold value, then in continuous print N two field picture, an arbitrary two field picture of choosing is defined as key frame images.Effectively can reduce the data interaction amount between source terminal 601 and object terminal 602 like this, thus reduce the transfer of data pressure in network, save the network bandwidth.
Further, object terminal 602 is after the user's head portrait after image stylization process receiving source terminal 601 transmission, this object terminal 602 can also carry out convergent-divergent process according to pre-set zoom ratio to the described user's head portrait received, and generate described image to be displayed according to the user's head portrait after convergent-divergent process and described background image, so also just avoid object terminal 602 and cannot show this user's head portrait or the poor problem of display effect.
The present invention describes with reference to according to the flow chart of the method for the embodiment of the present invention, equipment (system) and computer program and/or block diagram.Should understand can by the combination of the flow process in each flow process in computer program instructions realization flow figure and/or block diagram and/or square frame and flow chart and/or block diagram and/or square frame.These computer program instructions can being provided to the processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device to produce a machine, making the instruction performed by the processor of computer or other programmable data processing device produce device for realizing the function of specifying in flow chart flow process or multiple flow process and/or block diagram square frame or multiple square frame.
These computer program instructions also can be stored in can in the computer-readable memory that works in a specific way of vectoring computer or other programmable data processing device, the instruction making to be stored in this computer-readable memory produces the manufacture comprising command device, and this command device realizes the function of specifying in flow chart flow process or multiple flow process and/or block diagram square frame or multiple square frame.
These computer program instructions also can be loaded in computer or other programmable data processing device, make on computer or other programmable devices, to perform sequence of operations step to produce computer implemented process, thus the instruction performed on computer or other programmable devices is provided for the step realizing the function of specifying in flow chart flow process or multiple flow process and/or block diagram square frame or multiple square frame.
Although describe the preferred embodiments of the present invention, those skilled in the art once obtain the basic creative concept of cicada, then can make other change and amendment to these embodiments.So claims are intended to be interpreted as comprising preferred embodiment and falling into all changes and the amendment of the scope of the invention.
Obviously, those skilled in the art can carry out various change and modification to the present invention and not depart from the spirit and scope of the present invention.Like this, if these amendments of the present invention and modification belong within the scope of the claims in the present invention and equivalent technologies thereof, then the present invention is also intended to comprise these change and modification.

Claims (16)

1. the image processing method in video calling, is characterized in that, comprising:
When carrying out video calling with object terminal, receive the user's head portrait through image stylization process that object terminal sends;
Transfer the background image prestored, according to described user's head portrait and described background image, generate the image to be displayed comprising described user's head portrait and described background image;
The described image to be displayed that display generates.
2. the method for claim 1, is characterized in that, according to described user's head portrait and described background image, generates the image to be displayed comprising described user's head portrait and described background image, comprising:
According to pre-set zoom ratio, convergent-divergent process is carried out to the described user's head portrait received, and generate described image to be displayed according to the user's head portrait after convergent-divergent process and described background image.
3. method as claimed in claim 2, it is characterized in that, described pre-set zoom ratio is specially:
( M × N ) = ( 3 4 * H l ) · ( J × K )
Wherein, J × K is the length of described user's head portrait and wide, M × N is the length of user's head portrait after convergent-divergent process and wide, and H is longitudinal pixel number of the display screen for showing image to be displayed, and l is for showing longitudinal pixel number of the viewing area of user's head portrait in display screen.
4. the image processing method in video calling, is characterized in that, comprising:
When carrying out video calling with object terminal, in the image collected, extract user's head portrait;
Image stylization process is carried out to the described user's head portrait extracted, and the user's head portrait to be shown after synthetic image stylization process;
Described user's head portrait to be shown is sent to described object terminal, shows according to described user's head portrait to be shown to make described object terminal.
5. method as claimed in claim 4, is characterized in that, collection to image in extract user's head portrait, comprising:
Collected the N continuous two field picture comprising user's head portrait by image acquisition device, wherein, N be more than or equal to 2 positive integer;
In described N two field picture, determine a frame key frame images, and in described key frame images, extract described user's head portrait.
6. method as claimed in claim 5, is characterized in that, determine a frame key frame images, comprising in described N two field picture:
In described N two field picture, determine the image-region that user's head portrait in every two field picture is corresponding, and determine the average pixel value of the image-region that user's head portrait in every two field picture is corresponding;
Difference between the average pixel value obtaining the image-region in described N two field picture in every two continuous frames image;
Judge whether have the difference being greater than threshold value in the difference obtained;
When being greater than the difference of described threshold value if exist, then determine maximum difference in all being greater than in the difference of described threshold value, and the two field picture gathered rear in two continuous frames image corresponding for described maximum difference is defined as described key frame images;
If when there is not the difference being greater than described threshold value, then in continuous print N two field picture, an arbitrary two field picture of choosing is defined as described key frame images.
7. method as claimed in claim 6, is characterized in that, the difference between the average pixel value of the described image-region of two continuous frames image is obtained by following formula:
S = 1 h · l Σ i = 1 , j = 1 h , l ( | p t , i , j - p t - 1 , i , j | )
Wherein, S characterizes the difference between the average pixel value of two continuous frames image, the frame number of t token image, h characterizing consumer head portrait longitudinal pixel number in the picture, l characterizing consumer head portrait pixels across is in the picture counted, p characterizes the value of each pixel, the pixel value shared by the height of i token image, the wide shared pixel value of j token image.
8. an electronic equipment, is characterized in that, comprising:
Communication module, for when carrying out video calling with object terminal, receives the user's head portrait through image stylization process that object terminal sends;
Processor, for transferring the background image prestored, according to described user's head portrait and described background image, generates the image to be displayed comprising described user's head portrait and described background image;
Display, for showing the described image to be displayed of generation.
9. electronic equipment as claimed in claim 8, it is characterized in that, described processor, specifically for carrying out convergent-divergent process according to pre-set zoom ratio to the described user's head portrait received, and generates described image to be displayed according to the user's head portrait after convergent-divergent process and described background image.
10. an electronic equipment, is characterized in that, comprising:
Image acquisition device, for when carrying out video calling with object terminal, gathers image;
Processor, for extracting user's head portrait in the image collected, carries out image stylization process to the described user's head portrait extracted, and the user's head portrait to be shown after synthetic image stylization process;
Communication interface, for described user's head portrait to be shown is sent to described object terminal, shows according to described user's head portrait to be shown to make described object terminal.
11. electronic equipments as claimed in claim 10, it is characterized in that, described processor specifically determines a frame key frame images in comprising in the N continuous two field picture of user's head portrait of being collected by image acquisition device, and in described key frame images, extract described user's head portrait, wherein, N be more than or equal to 2 positive integer.
12. electronic equipments as claimed in claim 10, it is characterized in that, described processor specifically for determining the image-region that user's head portrait in every two field picture is corresponding in described N two field picture, and determine the average pixel value of the image-region that user's head portrait in every two field picture is corresponding, difference between the average pixel value obtaining the image-region in described N two field picture in every two continuous frames image, judge whether have the difference being greater than threshold value in the difference obtained, when being greater than the difference of described threshold value if exist, then determine maximum difference in all being greater than in the difference of described threshold value, and the rear two field picture in two continuous frames image corresponding for described maximum difference is defined as described key frame images, if when there is not the difference being greater than described threshold value, then in continuous print N two field picture, an arbitrary two field picture of choosing is defined as described key frame images.
13. 1 kinds of video interactive systems, is characterized in that, comprising:
When source terminal and object terminal set up video calling be connected time, described source terminal extracts user's head portrait in the image collected, and to described user's head portrait carry out image stylization process;
User's head portrait after image stylization process is sent to described object terminal by source terminal;
Described object terminal, when receiving described user's head portrait, transfers the background image prestored, and based on described user's head portrait and described background image, generates and show the image to be displayed comprising described user's head portrait and described background image.
14. systems as claimed in claim 13, it is characterized in that, described source terminal, specifically for being collected the N continuous two field picture comprising user's head portrait by the image acquisition device of self, a frame key frame images is determined in described N two field picture, and in described key frame images, extract described user's head portrait, wherein, N be more than or equal to 2 positive integer.
15. systems as claimed in claim 14, it is characterized in that, described source terminal, specifically for determining the image-region that user's head portrait in every two field picture is corresponding in described N two field picture, and determine the average pixel value of the image-region that user's head portrait of every two field picture is corresponding, difference between the average pixel value obtaining the image-region in described N two field picture in every two continuous frames image, judge whether have the difference being greater than threshold value in the difference obtained, when being greater than the difference of described threshold value if exist, then determine maximum difference in all being greater than in the difference of described threshold value, and the rear two field picture in two continuous frames image corresponding for described maximum difference is defined as described key frame images, if when there is not the difference being greater than described threshold value, then in continuous print N two field picture, an arbitrary two field picture of choosing is defined as described key frame images.
16. systems as claimed in claim 13, it is characterized in that, described object terminal, specifically for carrying out convergent-divergent process according to pre-set zoom ratio to the described user's head portrait received, and generates described image to be displayed according to the user's head portrait after convergent-divergent process and described background image.
CN201410066656.3A 2014-02-26 2014-02-26 Method and electronic equipment for processing image in video call Pending CN104869346A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410066656.3A CN104869346A (en) 2014-02-26 2014-02-26 Method and electronic equipment for processing image in video call

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410066656.3A CN104869346A (en) 2014-02-26 2014-02-26 Method and electronic equipment for processing image in video call

Publications (1)

Publication Number Publication Date
CN104869346A true CN104869346A (en) 2015-08-26

Family

ID=53914822

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410066656.3A Pending CN104869346A (en) 2014-02-26 2014-02-26 Method and electronic equipment for processing image in video call

Country Status (1)

Country Link
CN (1) CN104869346A (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105407313A (en) * 2015-10-28 2016-03-16 掌赢信息科技（上海）有限公司 Video calling method, equipment and system
CN105554429A (en) * 2015-11-19 2016-05-04 掌赢信息科技（上海）有限公司 Video conversation display method and video conversation equipment
WO2017067375A1 (en) * 2015-10-23 2017-04-27 宇龙计算机通信科技(深圳)有限公司 Video background configuration method and terminal device
CN107950021A (en) * 2015-08-28 2018-04-20 三星电子株式会社 Apparatus for video communication and its operation
CN108010037A (en) * 2017-11-29 2018-05-08 腾讯科技（深圳）有限公司 Image processing method, device and storage medium
CN109740476A (en) * 2018-12-25 2019-05-10 北京琳云信息科技有限责任公司 Instant communication method, device and server
CN110189246A (en) * 2019-05-15 2019-08-30 北京字节跳动网络技术有限公司 Image stylization generation method, device and electronic equipment
CN111163216A (en) * 2019-12-11 2020-05-15 维沃移动通信有限公司 Image transmission method and electronic equipment
WO2021057463A1 (en) * 2019-09-25 2021-04-01 北京字节跳动网络技术有限公司 Image stylization processing method and apparatus, and electronic device and readable medium
CN113114970A (en) * 2018-05-07 2021-07-13 苹果公司 Creative camera
CN115550704A (en) * 2022-12-01 2022-12-30 成都掌声如雷网络科技有限公司 Remote family interaction activity system and method based on multifunctional household appliance

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1272192A (en) * 1998-05-19 2000-11-01 索尼电脑娱乐公司 Image processing apparatus and method, and providing medium
CN1484451A (en) * 1994-07-28 2004-03-24 ��ʽ����뵼����Դ�о��� Information processing system
CN1639738A (en) * 2002-02-25 2005-07-13 皇家飞利浦电子股份有限公司 Method and system for generating caricaturized talking heads
CN101159873A (en) * 2007-11-16 2008-04-09 中国科学院计算技术研究所 Inter-frame mode selecting method
CN101287290A (en) * 2007-04-10 2008-10-15 株式会社Ntt都科摩 Communication control device and communication terminal
CN101610421A (en) * 2008-06-17 2009-12-23 深圳华为通信技术有限公司 Video communication method, Apparatus and system
CN102625129A (en) * 2012-03-31 2012-08-01 福州一点通广告装饰有限公司 Method for realizing remote reality three-dimensional virtual imitated scene interaction
WO2013082325A1 (en) * 2011-12-01 2013-06-06 Tangome, Inc. Augmenting a video conference
CN103368816A (en) * 2012-03-29 2013-10-23 深圳市腾讯计算机系统有限公司 Instant communication method based on virtual character and system
WO2014022022A1 (en) * 2012-08-01 2014-02-06 Google Inc. Using an avatar in a videoconferencing system

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1484451A (en) * 1994-07-28 2004-03-24 ��ʽ����뵼����Դ�о��� Information processing system
CN1272192A (en) * 1998-05-19 2000-11-01 索尼电脑娱乐公司 Image processing apparatus and method, and providing medium
CN1639738A (en) * 2002-02-25 2005-07-13 皇家飞利浦电子股份有限公司 Method and system for generating caricaturized talking heads
CN101287290A (en) * 2007-04-10 2008-10-15 株式会社Ntt都科摩 Communication control device and communication terminal
CN101159873A (en) * 2007-11-16 2008-04-09 中国科学院计算技术研究所 Inter-frame mode selecting method
CN101610421A (en) * 2008-06-17 2009-12-23 深圳华为通信技术有限公司 Video communication method, Apparatus and system
WO2013082325A1 (en) * 2011-12-01 2013-06-06 Tangome, Inc. Augmenting a video conference
CN103368816A (en) * 2012-03-29 2013-10-23 深圳市腾讯计算机系统有限公司 Instant communication method based on virtual character and system
CN102625129A (en) * 2012-03-31 2012-08-01 福州一点通广告装饰有限公司 Method for realizing remote reality three-dimensional virtual imitated scene interaction
WO2014022022A1 (en) * 2012-08-01 2014-02-06 Google Inc. Using an avatar in a videoconferencing system

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107950021A (en) * 2015-08-28 2018-04-20 三星电子株式会社 Apparatus for video communication and its operation
CN107950021B (en) * 2015-08-28 2020-04-07 三星电子株式会社 Video communication device and operation thereof
WO2017067375A1 (en) * 2015-10-23 2017-04-27 宇龙计算机通信科技(深圳)有限公司 Video background configuration method and terminal device
CN105407313A (en) * 2015-10-28 2016-03-16 掌赢信息科技（上海）有限公司 Video calling method, equipment and system
CN105554429A (en) * 2015-11-19 2016-05-04 掌赢信息科技（上海）有限公司 Video conversation display method and video conversation equipment
CN108010037A (en) * 2017-11-29 2018-05-08 腾讯科技（深圳）有限公司 Image processing method, device and storage medium
CN113114970A (en) * 2018-05-07 2021-07-13 苹果公司 Creative camera
CN109740476A (en) * 2018-12-25 2019-05-10 北京琳云信息科技有限责任公司 Instant communication method, device and server
CN110189246A (en) * 2019-05-15 2019-08-30 北京字节跳动网络技术有限公司 Image stylization generation method, device and electronic equipment
WO2021057463A1 (en) * 2019-09-25 2021-04-01 北京字节跳动网络技术有限公司 Image stylization processing method and apparatus, and electronic device and readable medium
CN111163216A (en) * 2019-12-11 2020-05-15 维沃移动通信有限公司 Image transmission method and electronic equipment
CN115550704A (en) * 2022-12-01 2022-12-30 成都掌声如雷网络科技有限公司 Remote family interaction activity system and method based on multifunctional household appliance
CN115550704B (en) * 2022-12-01 2023-03-14 成都掌声如雷网络科技有限公司 Remote family interaction activity method based on multifunctional household appliance

Similar Documents

Publication Publication Date Title
CN104869346A (en) Method and electronic equipment for processing image in video call
CN106998477A (en) The front cover display methods and device of live video
CN105554549A (en) VoLTE network video display method and device
CN104899832A (en) Splicing screenshot method of mobile terminal and splicing screenshot device
CN105447125A (en) Electronic equipment and makeup assisting method
CN112306607A (en) Screenshot method and device, electronic equipment and readable storage medium
CN112055244B (en) Image acquisition method and device, server and electronic equipment
JP6378323B2 (en) Image editing transmission to subordinate video sequences via dense motion fields
CN109656495A (en) The display methods and device of Mosaic screen, terminal
EP2696338B1 (en) Terminal and method for generating live image
CN105516638A (en) Video call method, device and system
CN108810610A (en) screen sharing method and device
CN105407313A (en) Video calling method, equipment and system
CN105578110A (en) Video call method, device and system
CN105657323A (en) Video calling method, device and system
CN113709368A (en) Image display method, device and equipment
CN107580228B (en) Monitoring video processing method, device and equipment
CN111381749A (en) Image display and processing method, device, equipment and storage medium
CN105183288B (en) Single-window multi-task display method and intelligent mobile terminal thereof
CN105163196A (en) Real-time video coding method and electronic equipment
CN105163194A (en) Real-time video coding method and electronic equipment
CN112558854B (en) Multi-picture split-screen mode customization method and device and computer equipment
CN105163199A (en) Real-time video coding method and electronic equipment
CN113393391B (en) Image enhancement method, image enhancement device, electronic apparatus, and storage medium
CN113535645B (en) Display method and device of shared document, electronic equipment and storage medium

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
EXSB Decision made by sipo to initiate 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: 20150826