CN110933354B - Customizable multi-style multimedia processing method and terminal thereof - Google Patents
Customizable multi-style multimedia processing method and terminal thereof Download PDFInfo
- Publication number
- CN110933354B CN110933354B CN201911128692.7A CN201911128692A CN110933354B CN 110933354 B CN110933354 B CN 110933354B CN 201911128692 A CN201911128692 A CN 201911128692A CN 110933354 B CN110933354 B CN 110933354B
- Authority
- CN
- China
- Prior art keywords
- target
- style
- template
- target style
- video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
- H04N7/141—Systems for two-way working between two video terminals, e.g. videophone
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/4788—Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a customizable multi-style multimedia processing method and a terminal thereof, wherein the method comprises the following steps: collecting a picture, capturing key information of the picture, obtaining a target style characteristic template according to the key information, and calling the target style characteristic template to perform multimedia processing; the objects of the multimedia processing comprise video, photographing and pictures; when the multimedia processing is a multi-style video call, further comprising: collecting multi-angle multi-expression portrait pictures of a user, and applying a target style characteristic template to the multi-angle multi-expression portrait pictures to realize frame data collection; encoding the acquired frame data to obtain a target style video template; and calling the target style video template to carry out video call. According to the method and the device, the target style video template is customized according to the preference of the user, and is called in real time according to the requirement of the user in the video call, so that the different style requirements of the user in the video call with different people are met, and the user experience is improved.
Description
Technical Field
The invention relates to the technical field of video call, in particular to a customizable multi-style multimedia processing method and a terminal thereof.
Background
With the popularity of smart phones, wireless networks and rapid upgrades of data networks, video chat has gradually expanded and even replaced traditional telephone communication and text chat modes, and video chat has become a standard for instant messaging.
At present, the processing software based on pictures and short videos is endless, but most of the image and video processing software is a preset fixed template and cannot be customized according to the requirements of users, and the users cannot select the proper style according to the preference of the users. For example, the existing video call applications such as QQ or WeChat can achieve the effect of video beautification, but the templates are relatively single and are externally disclosed, and cannot be customized privately according to the requirements of users. In addition, because users have different styles of requirements when communicating with different people in video, the existing templates cannot meet the requirements of the users, i.e. no technical scheme for helping the users to solve the pain point exists at present. For the above reasons, it is necessary to develop a customizable multi-style multimedia processing method.
Disclosure of Invention
The invention aims to provide a customizable multi-style multimedia processing method and a customizable multi-style multimedia processing terminal, wherein a target style characteristic template (such as a target style video template) is customized according to user preference, and the customized multi-style multimedia processing method and the customizable multi-style multimedia processing terminal can be invoked in real time according to user requirements in a multimedia application request (such as video call), so that different style requirements (such as different style requirements when the user is in video call with different people) of the user are met, and user experience is improved.
In order to achieve the above purpose, the present invention is realized by the following technical scheme:
a customizable multi-compartment multimedia processing method, the method comprising: collecting a picture, capturing key information of the picture, obtaining a target style characteristic template according to the key information, and calling the target style characteristic template to perform multimedia processing.
Preferably, the objects of the multimedia processing include video, photographing and pictures.
Preferably, the target style feature template is generated in real time or stored in a terminal and/or a cloud.
Preferably, the step of capturing a picture includes: the user selects one or more favorite pictures to collect.
Preferably, the key information is a favorite picture sub-region, and the favorite picture sub-region contains at least a part of target face sub-regions.
Preferably, the customizable multi-style multimedia processing method further comprises the steps of: and analyzing the common characteristics of the target face subregions to obtain the target style characteristic template.
Preferably, the customizable multi-style multimedia processing method further comprises the steps of: the common characteristics of the target face subarea are one or more of five sense organs characteristics, filtering characteristics, hairstyle characteristics, beauty and body characteristics, clothes color characteristics and light characteristics.
Preferably, the step of obtaining the target style feature template includes optimizing the image processing, specifically, one or more of skin grinding processing, whitening processing, fat face processing, face thinning processing, eye brightening processing, acne removing processing, wrinkle removing processing, filter processing, makeup processing, hair style changing processing, mosaic processing, light supplementing processing, contrast processing, saturation processing, sharpening processing and background blurring processing.
Preferably, the customizable multi-style multimedia processing method further comprises: and automatically or manually invoking the target style feature template by capturing matching information corresponding to the target style feature template.
Preferably, capturing the matching information comprises: naming, face recognition, voice recognition and address book searching matching when the searching target style characteristic template is stored.
Preferably, when the multimedia processing is a multi-style video call, the method further comprises: collecting multi-angle multi-expression portrait pictures of a user; the target style characteristic template is applied to a multi-angle multi-expression portrait picture to realize frame data acquisition; processing the acquired frame data to obtain a target style video template; and calling the target style video template to carry out video call.
The present invention also includes a customizable multi-compartment multimedia processing terminal employing the multi-compartment multimedia processing method as described above, comprising: the input module is used for acquiring pictures to be processed; the extraction module is used for capturing key information of the picture; and the multimedia processing module is used for obtaining a target style characteristic module according to the key information and calling the target style characteristic template to perform corresponding multimedia processing.
Preferably, the multimedia processing module comprises a video processing module, a photographing processing module and a picture processing module.
Preferably, the target style feature template is generated in real time or stored in a terminal and/or a cloud.
The invention further provides a customizable multi-grid multimedia processing system adopting the multi-grid multimedia processing terminal, which comprises a first terminal, a server and a second terminal;
the first terminal and/or the second terminal comprises: the input module is used for acquiring the picture extraction module to be processed and capturing key information of the picture; the multimedia processing module is used for obtaining a target style characteristic module according to the key information and calling the target style characteristic module to perform corresponding multimedia processing;
when one terminal initiates a multimedia application request to the other terminal through a server, the server transfers the multimedia application request between the one terminal and the other terminal, when the other terminal receives the multimedia application request, the one terminal and the other terminal establish related connection, and one terminal and/or the other terminal realize multi-style multimedia application by calling a target style video template.
Preferably, the target style feature template is generated in real time or stored in a terminal and/or a cloud.
Compared with the prior art, the invention has the beneficial effects that:
(1) According to the method, the target style characteristic template (such as the target style video template) is customized according to the preference of the user, and is called in real time according to the requirements of the user in a multimedia application request (such as video call), so that the different style requirements (such as different style requirements when the user is in video call with different people) of the user are met, and the user experience is improved; (2) The invention can be automatically realized when meeting the requirements of different styles of users, does not need manual adjustment of the users, and is simple and convenient; (3) The invention can process the pictures by calling the image processing algorithm according to the favorites and the custom style wanted by the user, and the image processing algorithm is independently written, so that various custom target style feature templates can be obtained, and the application range is wider.
Drawings
FIG. 1 is a flow chart of a customizable multi-grid multimedia processing method of the present invention;
FIG. 1a is a flow chart of a customizable multi-grid photographing process according to the present invention;
FIG. 1b is a flow chart of a customizable multi-grid picture processing method of the present invention;
FIG. 1c is a flow chart of a customizable multi-format video call method of the present invention;
FIG. 2 is a flow chart of an automatic mode customized multi-style video call method according to the present invention;
FIG. 3 is a flow chart of another method for customizing a multi-style video call in an automatic mode according to the present invention;
FIG. 4 is a flow chart of a method for manually customizing a multi-style video call according to the present invention;
fig. 5 is a flow chart of another method for customizing a multi-style video call in a manual mode according to the present invention.
Detailed Description
In order to solve the characteristics, contents and advantages of the present invention and the effects achieved by the method, the present invention is combined with the accompanying drawings and described in detail in the form of an embodiment, wherein the drawings are used for illustration and auxiliary description only, and not necessarily for real proportion and precise configuration after the implementation of the present invention, so that the proportion and configuration relation of the drawings should not be interpreted to limit the scope of the present invention in practical implementation.
The advantages, features and technical approaches to the present invention will be more readily understood by reference to the following detailed description of exemplary embodiments and the accompanying drawings, and the invention may be embodied in different forms and should not be construed as limited to the embodiments set forth herein; rather, the embodiments will provide those skilled in the art with a more complete and thorough understanding of the scope of the present invention, and the present invention will only be defined by the scope of the appended claims.
As shown in fig. 1, the present invention provides a customizable multi-grid multimedia processing method, which includes the following steps: step 1, collecting pictures; step 2, capturing the picture key information; step 3, obtaining a target style characteristic template according to the key information; step 4, calling a target style characteristic template to perform multimedia processing; the objects of the multimedia processing include video, photographing and pictures.
Embodiment one:
as shown in fig. 1a, the present invention provides a customizable photographing method, which includes: step 1: inputting a target face picture; step 2, acquiring a target face subregion; step 3, obtaining a target style characteristic template based on the target face subregion; and 4, photographing by calling the obtained target style characteristic template.
The target style feature templates are generated in real time or stored in the terminal and/or the cloud. The step of collecting the picture comprises the following steps: the user selects one or more favorite pictures to collect. The key information is a favorite picture sub-region, the favorite picture sub-region comprises at least a part of target face sub-regions, and the target style feature template is obtained by analyzing common features of the target face sub-regions. The common features of the target face subregion are one or more of five sense organs, filtering features, hairstyle features, beauty and body features, clothing color features and light features.
In order to obtain the target style feature template, the image processing may be optimized, specifically, one or more of skin grinding processing, whitening processing, face fat processing, face thinning processing, eye brightening processing, acne removing processing, wrinkle removing processing, filter processing, makeup processing, hair style changing processing, mosaic processing, light supplementing processing, contrast processing, saturation processing, sharpening processing and background blurring processing.
According to the method, the matching information corresponding to the target style characteristic template is captured, and the target style characteristic template is automatically or manually called; and capturing the matching information further comprises: naming, face recognition, voice recognition and address book searching matching when the searching target style characteristic template is stored.
Embodiment two:
as shown in fig. 1b, the present invention provides a customizable picture processing method, which includes: step 1: inputting a target face picture; step 2, acquiring a target face subregion; step 3, obtaining a target style characteristic template based on the target face subregion; and 4, processing the picture to be beautified by calling the obtained target style characteristic template.
The target style feature templates are generated in real time or stored in the terminal and/or the cloud. The step of collecting the picture comprises the following steps: the user selects one or more favorite pictures to collect. The key information is a favorite picture sub-region, the favorite picture sub-region comprises at least a part of target face sub-regions, and the target style feature template is obtained by analyzing common features of the target face sub-regions. The common features of the target face subregion are one or more of five sense organs, filtering features, hairstyle features, beauty and body features, clothing color features and light features.
In order to obtain the target style feature template, the image processing may be optimized, specifically, one or more of skin grinding processing, whitening processing, face fat processing, face thinning processing, eye brightening processing, acne removing processing, wrinkle removing processing, filter processing, makeup processing, hair style changing processing, mosaic processing, light supplementing processing, contrast processing, saturation processing, sharpening processing and background blurring processing.
According to the method, the matching information corresponding to the target style characteristic template is captured, and the target style characteristic template is automatically or manually called; and capturing the matching information further comprises: naming, face recognition, voice recognition and address book searching matching when the searching target style characteristic template is stored.
Embodiment III:
as shown in fig. 1c, the present invention provides a customizable multi-style video call method, which includes: step 1, inputting a target face picture; step 2, acquiring a target face subregion; step 3, obtaining a target style characteristic template based on the target face subregion; step 4, collecting multi-angle multi-expression portrait pictures of the user; step 5, applying the target style characteristic template to the multi-angle multi-expression portrait picture to realize frame data acquisition; step 6, coding the acquired frame data to obtain a target style video template; and 7, carrying out video call by calling the obtained target style video template.
The target style feature templates are generated in real time or stored in the terminal and/or the cloud. The step of collecting the picture comprises the following steps: the user selects one or more favorite pictures to collect. The key information is a favorite picture sub-region, the favorite picture sub-region comprises at least a part of target face sub-regions, and the target style feature template is obtained by analyzing common features of the target face sub-regions. The common features of the target face subregion are one or more of five sense organs, filtering features, hairstyle features, beauty and body features, clothing color features and light features.
In order to obtain the target style feature template, the image processing may be optimized, specifically, one or more of skin grinding processing, whitening processing, face fat processing, face thinning processing, eye brightening processing, acne removing processing, wrinkle removing processing, filter processing, makeup processing, hair style changing processing, mosaic processing, light supplementing processing, contrast processing, saturation processing, sharpening processing and background blurring processing.
According to the method, the matching information corresponding to the target style characteristic template is captured, and the target style characteristic template is automatically or manually called; and capturing the matching information further comprises: naming, face recognition, voice recognition and address book searching matching when the searching target style characteristic template is stored.
Embodiment four:
as shown in fig. 2, the method for automatic mode customizable multi-style video call according to the present invention comprises the following steps:
s1, acquiring a target picture: and inputting a satisfactory N Zhang Bei selected picture of the face style.
In the step S1, the satisfactory N Zhang Bei face image received by the terminal may be a face image of the user, or may be any image selected by the user in the image database.
S2, obtaining M target face subregions: and carrying out region selection on the input N Zhang Bei selected pictures to obtain M sub-pictures corresponding to the M target sub-regions.
In the step S2, the generated M sub-images correspond to different regions in each target face, such as face shape, nose, eyes, eyebrow shape, forehead, bang, interocular distance, chin, teeth, lips, skin color, lip color, and the like. The M sub-pictures may be different five-sense organ regions of a plurality of images in the N pictures, or may be five-sense organ regions in one image.
In this embodiment, the M target face sub-areas are face sub-areas selected from at least two candidate face images, each sub-image corresponds to one face sub-area, and each candidate face image includes at least one face sub-area; n, M are integers greater than 1. M may be greater than N, or M may be less than N.
And S3, obtaining a target style characteristic template based on the face style characteristics of the M sub-pictures.
For example, when customizing the style of men, the input pictures are analyzed, processed and integrated to obtain favorite five sense organs features: if the eyes are slightly bigger than the actual eyes, the pupil is light brown, the eye shadow is a pale eye shadow, the eyelashes are characterized by curling, the root is of a distinct type, the eyebrow is a child eyebrow, and the like; face analysis of preference map: if the face is thinner than the actual face, the goose face is a little thinner; skin color analysis of favorites: the skin is liked to be slightly whiter, etc., so that the template can be integrated into a men's style.
S4, collecting X multi-angle multi-expression portrait pictures of the user.
S5, applying the target style characteristic template to the collected X pictures to realize frame data collection.
S6, coding the acquired frame data to obtain a target style video template.
It is worth noting that all video style templates are only one way to say, all processing is based on single frame image processing, multi-angle multi-expression portrait images are collected to make multi-angle multi-expression feature templates with customized styles, and then each frame is connected by applying feature templates which are wanted to be matched.
For example, customizing a mom style, firstly inputting 8 candidate pictures liked by a mom of a user to a terminal, receiving the 8 candidate pictures by the terminal, carrying out region selection on the input 8 candidate pictures to obtain 10 sub-pictures corresponding to 10 target sub-regions, and analyzing the sub-pictures by the terminal to obtain a target style picture template. And then, 5 multi-angle multi-expression portrait pictures of the user are acquired, the target style feature template is applied to the 5 multi-angle multi-expression portrait pictures, frame data acquisition is realized, and coding is carried out, so that a target style video template required by the user is obtained.
For example, customizing father style, firstly inputting 6 candidate pictures which are liked by father of a user to a terminal, receiving the 6 candidate pictures by the terminal, carrying out region selection on the input 6 candidate pictures to obtain 5 sub-pictures corresponding to 5 target sub-regions, and analyzing the sub-pictures by the terminal to obtain a target style picture template. And then 4 multi-angle multi-expression portrait pictures of the user are acquired, the target style feature template is applied to the 4 multi-angle multi-expression portrait pictures, frame data acquisition is realized, and coding is carried out, so that a target style video template required by the user is obtained.
In the embodiment of the invention, the terminal receives N Zhang Bei face images and acquires M Zhang Zitu images of M target face subregions selected, generates a target face template based on the M Zhang Zitu images, and applies a target style characteristic template to a plurality of multi-angle multi-expression portrait pictures of a user by acquiring the multi-angle multi-expression portrait pictures of the user to acquire frame data and encode the frame data so as to obtain a target style video template required by a specific user.
The target style video templates of this embodiment may be named and saved separately after they are generated.
And S7, when a video call event is required to be carried out, after the third party application program opens the video call, calling the obtained target style video template according to preference, and completing the video call.
Fifth embodiment:
as shown in fig. 3, the present invention provides another automatic mode customizable multi-style video call method, which includes the following steps:
p1, obtaining a target picture: and inputting a satisfactory N Zhang Bei selected picture of the face style.
P2, acquiring M target face subregions: and carrying out region selection on the input N Zhang Bei selected pictures to obtain M sub-pictures corresponding to the M target sub-regions.
And P3, obtaining a target style characteristic template based on the face style characteristics of the M sub-pictures.
And P4, collecting X multi-angle multi-expression portrait pictures of the user.
And P5, applying the target style characteristic template to the acquired X pictures to realize frame data acquisition.
And P6, encoding the acquired frame data to obtain the target style video template.
And P7, directly setting a target style video template in the video contact person according to preference, namely directly realizing automatic calling of the target style video template when the video call is opened by a third party application program, and completing the video call.
Example six:
as shown in fig. 4, the manual mode customized multi-style video call method of the present invention comprises the following steps:
t1, acquiring a target picture: and inputting a satisfactory N Zhang Bei selected picture of the face style.
In the step T1, the satisfactory N Zhang Bei face image received by the terminal may be a face image of the user, or may be any image selected by the user in the image database.
T2, acquiring M target face subregions: and carrying out region selection on the input N Zhang Bei selected pictures to obtain M sub-pictures corresponding to the M target sub-regions.
In the step T2, the generated M sub-images correspond to different regions in each target face, such as face shape, nose, eyes, eyebrow shape, forehead, bang, interocular distance, chin, teeth, lips, skin color, lip color, and the like. The M sub-pictures may be different five-sense organ regions of a plurality of images in the N pictures, or may be five-sense organ regions in one image.
In this embodiment, the M target face sub-areas are face sub-areas selected from at least two candidate face images, each sub-image corresponds to one face sub-area, and each candidate face image includes at least one face sub-area; n, M are integers greater than 1. M may be greater than N, or M may be less than N.
And T3, calling one or more image processing algorithms to process M sub-images according to the preference and the custom style wanted by the user, and obtaining the target style characteristic template.
In the step T3, the image processing algorithm includes a skin-polishing algorithm, a whitening algorithm, a face-fat algorithm, a face-thinning algorithm, an eye-brightening algorithm, an acne-removing algorithm, a wrinkle-removing algorithm, a filter algorithm, a makeup algorithm, a hairstyle replacement algorithm, a mosaic algorithm, a light-supplementing algorithm, a contrast algorithm, a saturation algorithm, a sharpening algorithm, a background blurring algorithm, and the like. Meanwhile, different calling modes can be provided for different image processing algorithms, for example, according to an object (such as an object or a position in an image) acted by the algorithm, parameter adjustment in the algorithm (such as the peeling strength or grade of the peeling algorithm) and the like.
In this embodiment, the image processing algorithm used in the foregoing is independently written.
And T4, collecting X multi-angle multi-expression portrait pictures of the user.
And T5, applying the target style characteristic template to the acquired X pictures to realize frame data acquisition.
And T6, encoding the acquired frame data to obtain the target style video template.
For example, when the mother style is customized, the face shape can be slightly adjusted to be fat, the skin is white, the hair style is braided with the tail, and the like, then the 8 candidate pictures which are liked by the mother of the user are firstly input into the terminal, the terminal receives the 8 candidate pictures, the input 8 candidate pictures are subjected to region selection to obtain 10 sub-pictures corresponding to 10 target sub-regions, and then the 10 sub-pictures are processed by a face fat algorithm, a whitening algorithm, a hair style replacement algorithm, and the like to obtain the target style feature template. And then, 5 multi-angle multi-expression portrait pictures of the user are acquired, the target style feature template is applied to the 5 multi-angle multi-expression portrait pictures, frame data acquisition is realized, and coding is carried out, so that a target style video template required by the user is obtained.
For example, when customizing a men style, the face shape is thinned, the eyes are enlarged, the lip color becomes a running color, the pupil is worn, the hairstyle is adjusted to be a big wave, and the like, then firstly, 6 candidate pictures which are liked by the men of the user are input to the terminal, the terminal receives the 6 candidate pictures, the input 6 candidate pictures are subjected to region selection to obtain 5 sub-pictures corresponding to 5 target sub-regions, and then, a face thinning algorithm, an eye brightening algorithm, a make-up algorithm, a hairstyle replacement algorithm and the like are called to process the 5 sub-pictures to obtain the target style characteristic template. And then 4 multi-angle multi-expression portrait pictures of the user are acquired, the target style feature template is applied to the 4 multi-angle multi-expression portrait pictures, frame data acquisition is realized, and coding is carried out, so that a target style video template required by the user is obtained.
The target style video templates of this embodiment may be named and saved separately after they are generated.
And T7, when a video call event is required to be carried out, after the third party application program opens the video call, calling the obtained target style video template according to preference, and completing the video call.
Embodiment seven:
as shown in fig. 5, the present invention provides another manual mode customized multi-style video call method, which includes the following steps:
q1, acquiring a target picture: and inputting a satisfactory N Zhang Bei selected picture of the face style.
Q2, acquiring M target face subregions: and carrying out region selection on the input N Zhang Bei selected pictures to obtain M sub-pictures corresponding to the M target sub-regions.
And Q3, calling one or more image processing algorithms to process M sub-images according to the preference and the self-wanted customization style, and obtaining the target style characteristic template.
And Q4, collecting X multi-angle multi-expression portrait pictures of the user.
Q5, applying the target style characteristic template to the collected X pictures to realize frame data collection.
And Q6, encoding the acquired frame data to obtain the target style video template.
And Q7, directly setting a target style video template in the video contact person according to preference, namely directly realizing automatic calling of the target style video template when the video call is opened by a third party application program, and completing the video call.
Example eight:
in the process of the multi-style video call method, in the step 3, the change of the appearance gender can be realized through characteristic adjustment (namely, the steps S3, T3 and the like are replaced, the method is the same as the step S3), so that a required target style characteristic template is obtained, then specific debugging style parameters are reserved and are respectively used for collecting frame data of a specific style when a face picture with X Zhang Duojiao degrees and multiple expressions is used, and finally, the collected frame data is encoded to obtain the target style video template.
Example nine:
the invention also provides a multi-wind-grid video terminal, which comprises: the alternative picture input module is used for inputting N Zhang Bei selected pictures of the face style satisfied by the user; the image processing module is used for receiving N Zhang Bei face images, acquiring M target face subregions so as to obtain corresponding M sub-pictures, and generating a target style characteristic template based on the M sub-pictures, wherein N, M is an integer greater than 1; the expression acquisition module is used for acquiring X multi-angle multi-expression portrait pictures of a user; the frame data acquisition module is used for realizing frame data acquisition when the target style characteristic template is applied to the acquired X pictures; and the video template generation module is used for encoding the acquired frame data to obtain the target style video template.
Example ten:
the invention also provides a customizable multi-style video call system, which comprises a first client, a server and a second client, wherein the first client comprises but is not limited to the following steps: the alternative picture input module is used for inputting N Zhang Bei selected pictures of the face style satisfied by the user; the image processing module is used for receiving N Zhang Bei face images, acquiring M target face subregions so as to obtain corresponding M sub-pictures, and generating a target style characteristic template based on the M sub-pictures, wherein N, M is an integer greater than 1; the expression acquisition module is used for acquiring X multi-angle multi-expression portrait pictures of a user; the frame data acquisition module is used for realizing frame data acquisition when the target style characteristic template is applied to the acquired X pictures; and the video template generation module is used for encoding the acquired frame data to obtain the target style video template.
When a first client opens a video call at a third party application program and initiates a video call request to a second client through a server, the server transfers the video call request between the first client and the second client, and the second client receives the video call request, so that the first client establishes the video call with the second client, and the first client calls the obtained target style video template according to preference to realize customizable multi-style video call. Or the first client side directly sets a target style video template in the video contact person according to preference, then opens the video call in the third party application program, namely the automatic call of the target style video template is directly realized, the first client side initiates a video call request to the second client side through the server, the server transfers the video call request between the first client side and the second client side, and when the second client side receives the video call request, the first client side and the second client side establish the video call, and customizable multi-style video call is realized.
In the invention, the method is not limited to the first client side which can realize the generation and application of the target style video template, and the second client side can also realize the generation and application of the target style video template, and specific functional modules and functions are the same as those of the first client side, and repeated description is omitted here. When the first client initiates a video call request to the second client, the second client establishes a video call when receiving the video call request, and the second client can call the obtained target style video template according to preference to realize customizable multi-style video call. In addition, the second client can also actively initiate a video call request to the first client, the first client establishes a video call when receiving the video call request, and the second client can also call the obtained target style video template according to preference to realize customizable multi-style video call, or the second client firstly sets the target style video template in the video contact according to preference, then opens the video call at a third party application program, namely, directly realizes automatic call of the target style video template, then actively initiates the video call request to the first client, and the first client establishes the video call when receiving the video call request, thereby automatically realizing customizable multi-style video call.
In summary, the method and the device can customize the target style characteristic template according to the preference of the user, and call the target style characteristic template in real time according to the requirement of the user in the multimedia application request, so that different style requirements of the user are met, and the user experience is improved.
While the present invention has been described in detail through the foregoing description of the preferred embodiment, it should be understood that the foregoing description is not to be considered as limiting the invention. Many modifications and substitutions of the present invention will become apparent to those of ordinary skill in the art upon reading the foregoing. Accordingly, the scope of the invention should be limited only by the attached claims.
Claims (7)
1. A customizable multi-compartment multimedia processing method, the method comprising:
receiving satisfied N face images input by a user, wherein N is an integer greater than or equal to 1;
carrying out region selection on the input N face images to obtain M sub-pictures corresponding to M target face sub-regions, wherein M is an integer greater than or equal to 1;
according to the custom style preferred by the user, one or more image processing algorithms are called to process the M sub-images to obtain a target style characteristic template, and the target style characteristic template is called to process multimedia;
when the multimedia processing is a multi-style video call, the method further comprises:
collecting multi-angle multi-expression portrait pictures of a user;
the target style characteristic template is applied to a multi-angle multi-expression portrait picture to realize frame data acquisition;
processing the acquired frame data to obtain a target style video template;
and calling the target style video template to carry out video call.
2. The customizable multi-compartment multimedia processing method of claim 1, further comprising the steps of: and analyzing the common characteristics of the target face subregions to obtain the target style characteristic template.
3. The customizable multi-compartment multimedia processing method of claim 1, further comprising the steps of: the common characteristics of the target face subarea are one or more of five sense organs characteristics, filtering characteristics, hairstyle characteristics, beauty and body characteristics, clothes color characteristics and light characteristics.
4. The customizable multi-compartment multimedia processing method according to claim 1, further comprising: and automatically or manually invoking the target style feature template by capturing matching information corresponding to the target style feature template.
5. The customizable multi-compartment multimedia processing method of claim 4,
capturing the matching information includes: naming, face recognition, voice recognition and address book searching matching when the searching target style characteristic template is stored.
6. A customizable multi-compartment multimedia processing terminal comprising:
the input module is used for receiving satisfied N face images input by a user, wherein N is an integer greater than or equal to 1;
the extraction module is used for carrying out region selection on the input N face images to obtain M sub-pictures corresponding to M target face sub-regions, wherein M is an integer greater than or equal to 1;
the image processing module is used for calling one or more image processing algorithms to process the M sub-images according to the custom style preferred by the user to obtain a target style characteristic template;
the multimedia processing module is used for calling the target style characteristic template to perform corresponding multimedia processing;
the expression acquisition module is used for acquiring multi-angle multi-expression portrait pictures of a user when the multimedia processing is multi-style video call;
the frame data acquisition module is used for applying the target style characteristic template to the multi-angle multi-expression portrait pictures to realize frame data acquisition;
the video module generating module is used for processing the acquired frame data to obtain a target style video template, and calling the target style video template to carry out video call.
7. The customizable multi-compartment multimedia processing terminal of claim 6,
the objects processed by the multimedia processing module comprise videos, photographing and pictures.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911128692.7A CN110933354B (en) | 2019-11-18 | 2019-11-18 | Customizable multi-style multimedia processing method and terminal thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911128692.7A CN110933354B (en) | 2019-11-18 | 2019-11-18 | Customizable multi-style multimedia processing method and terminal thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110933354A CN110933354A (en) | 2020-03-27 |
| CN110933354B true CN110933354B (en) | 2023-09-01 |
Family
ID=69854148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911128692.7A Active CN110933354B (en) | 2019-11-18 | 2019-11-18 | Customizable multi-style multimedia processing method and terminal thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110933354B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113420244A (en) * | 2020-07-20 | 2021-09-21 | 阿里巴巴集团控股有限公司 | Dynamic effect template generation method, dynamic picture display method and device and electronic equipment |
| CN112597320A (en) * | 2020-12-09 | 2021-04-02 | 上海掌门科技有限公司 | Social information generation method, device and computer readable medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017177768A1 (en) * | 2016-04-13 | 2017-10-19 | 腾讯科技（深圳）有限公司 | Information processing method, terminal, and computer storage medium |
| CN107705248A (en) * | 2017-10-31 | 2018-02-16 | 广东欧珀移动通信有限公司 | Image processing method, device, electronic equipment and computer-readable recording medium |
| CN108881782A (en) * | 2018-08-23 | 2018-11-23 | 维沃移动通信有限公司 | A kind of video call method and terminal device |
| WO2019000777A1 (en) * | 2017-06-27 | 2019-01-03 | 五邑大学 | Internet-based face beautification system |
| CN109448069A (en) * | 2018-10-30 | 2019-03-08 | 维沃移动通信有限公司 | A kind of template generation method and mobile terminal |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012060537A2 (en) * | 2010-11-02 | 2012-05-10 | 에스케이텔레콤 주식회사 | Recommendation system based on the recognition of a face and style, and method thereof |
-
2019
- 2019-11-18 CN CN201911128692.7A patent/CN110933354B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017177768A1 (en) * | 2016-04-13 | 2017-10-19 | 腾讯科技（深圳）有限公司 | Information processing method, terminal, and computer storage medium |
| WO2019000777A1 (en) * | 2017-06-27 | 2019-01-03 | 五邑大学 | Internet-based face beautification system |
| CN107705248A (en) * | 2017-10-31 | 2018-02-16 | 广东欧珀移动通信有限公司 | Image processing method, device, electronic equipment and computer-readable recording medium |
| CN108881782A (en) * | 2018-08-23 | 2018-11-23 | 维沃移动通信有限公司 | A kind of video call method and terminal device |
| CN109448069A (en) * | 2018-10-30 | 2019-03-08 | 维沃移动通信有限公司 | A kind of template generation method and mobile terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110933354A (en) | 2020-03-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108012081B (en) | Intelligent beautifying method, device, terminal and computer readable storage medium | |
| CN104346136B (en) | A kind of method and device of picture processing | |
| CN107862653B (en) | Image display method, image display device, storage medium and electronic equipment | |
| CN110933354B (en) | Customizable multi-style multimedia processing method and terminal thereof | |
| CN111583415B (en) | Information processing method and device and electronic equipment | |
| CN113850726A (en) | Image transformation method and device | |
| JP2005242566A (en) | Image composition device and method | |
| US20220385808A1 (en) | Selfie setup and stock videos creation | |
| KR20160030037A (en) | Portrait generating device, portrait generating method | |
| EP4116923A1 (en) | Auxiliary makeup method, terminal device, storage medium and program product | |
| CN108337465A (en) | Method for processing video frequency and device | |
| CN113298956A (en) | Image processing method, nail beautifying method and device, and terminal equipment | |
| CN114821675B (en) | Object processing method and system and processor | |
| CN112750176A (en) | Image processing method and device, electronic equipment and storage medium | |
| KR20220026252A (en) | Mobile terminal, server and method for composing beauty style | |
| CN108933891B (en) | Photographing method, terminal and system | |
| CN111316628A (en) | Image shooting method and image shooting system based on intelligent terminal | |
| CN113453027A (en) | Live video and virtual makeup image processing method and device and electronic equipment | |
| WO2022193573A1 (en) | Facial fusion method and apparatus | |
| CN114187166A (en) | Image processing method, intelligent terminal and storage medium | |
| CN106327588B (en) | Intelligent terminal and image processing method and device thereof | |
| US11812183B2 (en) | Information processing device and program | |
| CN113284229A (en) | Three-dimensional face model generation method, device, equipment and storage medium | |
| CN114915722B (en) | Method and device for processing video | |
| CN114972014A (en) | Image processing method and device and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |