CN112102195A - Beautifying method, parameter maintenance method, device, electronic equipment and storage medium - Google Patents
Beautifying method, parameter maintenance method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112102195A CN112102195A CN202010975503.6A CN202010975503A CN112102195A CN 112102195 A CN112102195 A CN 112102195A CN 202010975503 A CN202010975503 A CN 202010975503A CN 112102195 A CN112102195 A CN 112102195A
- Authority
- CN
- China
- Prior art keywords
- beauty
- parameter
- space variable
- image
- variable table
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 63
- 230000003796 beauty Effects 0.000 claims abstract description 349
- 230000000694 effects Effects 0.000 claims abstract description 58
- 238000012545 processing Methods 0.000 claims description 37
- 230000000977 initiatory effect Effects 0.000 claims description 24
- 238000006243 chemical reaction Methods 0.000 claims description 22
- 238000004891 communication Methods 0.000 claims description 10
- 238000010801 machine learning Methods 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 9
- 230000002787 reinforcement Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 12
- 239000003999 initiator Substances 0.000 description 8
- 241001396014 Priacanthus arenatus Species 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- 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
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
- H04N21/4318—Generation of visual interfaces for content selection or interaction; Content or additional data rendering by altering the content in the rendering process, e.g. blanking, blurring or masking an image region
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Bioinformatics & Computational Biology (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The application provides a beauty method, a parameter maintenance device, electronic equipment and a storage medium, and relates to the technical field of the Internet, wherein the beauty parameters in a first space variable table and the beauty parameters in a second space variable table are obtained and the obtained corresponding relations are recorded in a space variable maintenance strategy, so that the beauty parameters aiming at the first space variable table and the beauty parameters aiming at the second space variable table are mutually converted based on the obtained space variable maintenance strategy; therefore, when the anchor starts live broadcast on different live broadcast platforms, the same beauty parameters can be used for realizing the same live broadcast effect on different live broadcast platforms without adjusting the beauty parameters of each live broadcast platform, and the live broadcast efficiency is improved.
Description
Technical Field
The application relates to the technical field of internet, in particular to a beautifying method, a parameter maintenance method, a device, electronic equipment and a storage medium.
Background
In scenes such as network live broadcast and the like, the live broadcast platform can adopt some beauty strategies to perform some beauty decoration on target objects such as anchor figures and the like in live broadcast code streams, so that the live broadcast effect is improved.
However, different beauty strategies are generally adopted by different live broadcast platforms, and although the beauty modification effects are similar, the used beauty parameters may have differences, so that when the anchor broadcasts on different live broadcast platforms, in order to make the live broadcast effects similar, it takes a lot of time to adjust the beauty parameters, and the live broadcast efficiency is low.
Disclosure of Invention
The application aims to provide a beautifying method, a parameter maintenance method, a device, an electronic device and a storage medium, which can improve live broadcast efficiency.
In order to achieve the purpose, the technical scheme adopted by the application is as follows:
in a first aspect, the present application provides a beauty parameter maintenance method, including:
acquiring a first space variable table and a second space variable table; the first space variable table and the second space variable table respectively comprise a plurality of groups of beautifying parameters, and each beautifying parameter corresponds to a beautifying effect;
for a first beauty parameter in the first space variable table, determining a second beauty parameter with the same beauty effect corresponding to the first beauty parameter in the second space variable table;
storing the corresponding relation between the first beauty parameter and the second beauty parameter, and recording the corresponding relation in a space variable maintenance strategy; the space variable maintenance strategy records the corresponding relation between the beauty parameters in the first space variable table and the beauty parameters in the second space variable table.
In a second aspect, the present application provides a method for beautifying, which is applied to a server, where the server establishes communication with a live broadcast initiating terminal; the server stores a space variable maintenance strategy obtained by the beautifying parameter maintenance method provided by the first aspect of the application;
the method comprises the following steps:
receiving a to-be-processed live broadcast image sent by the live broadcast initiating terminal and a parameter conversion request aiming at an initial beauty parameter; wherein the initial beauty parameter is a beauty parameter for the first space variable table;
in response to the parameter conversion request, finding out a target beauty parameter corresponding to the initial beauty parameter in the space variable maintenance strategy; wherein the target beauty parameter is a beauty parameter for the second space variable table;
and performing beauty treatment on the live broadcast image to be treated by using the target beauty parameter, and sending out the live broadcast image after the beauty treatment.
In a third aspect, the present application provides a beauty parameter maintenance device, the device comprising:
the first processing module is used for acquiring a first space variable table and a second space variable table; the first space variable table and the second space variable table respectively comprise a plurality of groups of beautifying parameters, and each beautifying parameter corresponds to a beautifying effect;
the first processing module is further configured to determine, in the second space variable table, a second beauty parameter corresponding to the same beauty effect as the first beauty parameter for the first beauty parameter in the first space variable table;
the storage module is used for storing the corresponding relation between the first beauty parameter and the second beauty parameter and recording the corresponding relation in a space variable maintenance strategy; the space variable maintenance strategy records the corresponding relation between the beauty parameters in the first space variable table and the beauty parameters in the second space variable table.
In a fourth aspect, the present application provides a beauty device, which is applied to a server, where the server establishes communication with a live broadcast initiating terminal; the server stores a space variable maintenance strategy obtained by the beautifying parameter maintenance method provided by the first aspect of the application;
the device comprises:
the receiving module is used for receiving the live broadcast image to be processed sent by the live broadcast initiating terminal and a parameter conversion request aiming at the initial beautifying parameter; wherein the initial beauty parameter is a beauty parameter for the first space variable table;
the second processing module is used for responding to the parameter conversion request, and finding out a target beauty parameter corresponding to the initial beauty parameter in the space variable maintenance strategy; wherein the target beauty parameter is a beauty parameter for the second space variable table;
and the second processing module is also used for performing beauty treatment on the live broadcast image to be treated by using the target beauty parameter and sending out the live broadcast image after the beauty treatment.
In a fifth aspect, the present application provides an electronic device comprising a memory for storing one or more programs; a processor; the one or more programs, when executed by the processor, implement the beauty parameter maintenance method or the beauty method described above.
In a sixth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the beauty parameter maintenance method or the beauty method described above.
According to the beauty method, the parameter maintenance device, the electronic equipment and the storage medium, the corresponding relation between each beauty parameter in the first space variable table and each beauty parameter in the second space variable table is obtained, and the obtained corresponding relation is recorded in the space variable maintenance strategy, so that the beauty parameters aiming at the first space variable table and the beauty parameters aiming at the second space variable table are mutually converted based on the obtained space variable maintenance strategy; therefore, when the anchor starts live broadcast on different live broadcast platforms, the same beauty parameters can be used for realizing the same live broadcast effect on different live broadcast platforms without adjusting the beauty parameters of each live broadcast platform, and the live broadcast efficiency is improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly explain the technical solutions of the present application, the drawings needed for the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also derive other related drawings from these drawings without inventive effort.
Fig. 1 is a schematic view illustrating an interactive scene of a live broadcast system provided in the present application;
FIG. 2 shows a schematic diagram of a space variable table;
FIG. 3 is a block diagram of a schematic configuration of an electronic device provided herein;
FIG. 4 illustrates an exemplary flow chart of a beauty parameter maintenance method provided herein;
fig. 5 shows a schematic diagram of a DQN model;
FIG. 6 illustrates an exemplary flow chart of a beauty method provided herein;
fig. 7 is a block diagram illustrating an exemplary structure of a beauty parameter maintaining apparatus provided in the present application;
fig. 8 shows an exemplary structural block diagram of the beauty device provided by the present application.
In the figure: 100-an electronic device; 101-a memory; 102-a processor; 103-a communication interface; 400-beauty parameter maintenance means; 401-a first processing module; 402-a save module; 500-a beauty device; 501-a transceiver module; 502-second processing module.
Detailed Description
To make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described below with reference to the accompanying drawings in some embodiments of the present application, and it is obvious that the described embodiments are some, but not all embodiments of the present application. The components of the present application, as generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, as presented in the figures, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments obtained by a person of ordinary skill in the art based on a part of the embodiments in the present application without any creative effort belong to the protection scope of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic view illustrating an interactive scene of a live broadcast system provided in the present application, which may be a live broadcast platform for live broadcast such as internet in some embodiments. The live broadcast system can comprise a server, a live broadcast initiating terminal and a live broadcast receiving terminal, wherein the server can be communicated with the live broadcast receiving terminal and the live broadcast initiating terminal respectively, and the server can provide live broadcast service for the live broadcast receiving terminal and the live broadcast initiating terminal. For example, the anchor may provide a live stream online in real time to the viewer through the live initiator and transmit the live stream to the server, and the live receiver may pull the live stream from the server for online viewing or playback.
In some implementations, the live receiver and the live initiator may be used interchangeably. For example, a anchor of a live originator may use the live originator to provide live video services to viewers, or as viewers to view live video provided by other anchors. For another example, a viewer at a live receiver may also use the live receiver to watch live video provided by a concerned anchor, or serve as the anchor to provide live video services to other viewers.
In some embodiments, the live receiver and the live initiator may include, but are not limited to, a mobile device, a tablet computer, a laptop computer, or any combination of two or more thereof. In some embodiments, the mobile device may include, but is not limited to, a wearable device, a smart mobile device, an augmented reality device, and the like, or any combination thereof. In some embodiments, the smart mobile device may include, but is not limited to, a smartphone, a Personal Digital Assistant (PDA), a gaming device, a navigation device, or a point of sale (POS) device, or the like, or any combination thereof.
In addition, in some possible implementations, there may be zero, one, or more live receivers and live initiators, only one of which is shown in fig. 1, accessing the server. The live broadcast receiving end and the live broadcast initiating end can be provided with internet products for providing internet live broadcast services, for example, the internet products can be application programs APP, Web webpages, applets and the like used in a computer or a smart phone and related to the internet live broadcast services.
In some embodiments, the server may be a single physical server or a server group consisting of a plurality of physical servers for performing different data processing functions. The set of servers can be centralized or distributed (e.g., the servers can be a distributed system). In some possible embodiments, such as where the server employs a single physical server, the physical server may be assigned different logical server components based on different live service functions.
It will be appreciated that the live system shown in fig. 1 is only one possible example, and that in other possible embodiments of the present application, the live system may also include only some of the components shown in fig. 1 or may also include other components.
In the above-mentioned live webcasting scene, for example, with the beauty effects of three dimensions, namely, a thin face, a large eye, and a peeling, as shown in fig. 2, the live webcasting platform may maintain a three-dimensional space variable table as shown in fig. 2 as a beauty strategy; wherein, R parameter in this three-dimensional space variable table can be used for the thin face degree of representation, and G parameter can be used for the big eye degree of representation, and B parameter can be used for the buffing degree of representation.
In addition, for example, the parameter of the central point of the three-dimensional space variable table may be (0,0,0), and the beauty effect corresponding to the central point may be 0 face thinning, 0 eye enlarging, 0 skin polishing; the corresponding beauty degree is characterized to be larger as the corresponding parameter is larger; for example, the larger the R parameter is, the larger the corresponding face thinning degree is.
In some scenes, the same anchor may be live on a plurality of live broadcast platforms, in order to make the difference of live broadcast pictures watched by audiences of different live broadcast platforms smaller, the anchor can perform adaptive adjustment on beauty parameters used during live broadcast under each live broadcast platform, so that the beauty effect in the presented live broadcast pictures is closer when the anchor is live broadcast under different live broadcast platforms.
However, in some scenarios, different beauty strategies are generally adopted due to different live platforms, namely: for the same beauty effect, different beauty parameters adopted by different live broadcast platforms may have differences, for example, the beauty effect of the big eye 0.6 of the live broadcast platform A is closer to that of the big eye 0.4 of the live broadcast platform B; therefore, when the anchor starts the live broadcast on different live broadcast platforms, in order to enable the live broadcast effect of the anchor on each live broadcast platform to be relatively close, the anchor needs to spend more time to adjust the beauty parameters of each live broadcast platform, and the live broadcast efficiency is lower.
Based on this, in order to solve at least some of the above-mentioned defects, the present application provides one possible implementation manner as follows: by acquiring the corresponding relation between each beauty parameter in the first space variable table and each beauty parameter in the second space variable table and recording the acquired corresponding relation in the space variable maintenance strategy, the beauty parameters aiming at the first space variable table and the beauty parameters aiming at the second space variable table can be mutually converted based on the acquired space variable maintenance strategy; therefore, when the anchor starts live broadcast on different live broadcast platforms, the same beauty parameters can be used for realizing the same live broadcast effect on different live broadcast platforms without adjusting the beauty parameters of each live broadcast platform, and the live broadcast efficiency is improved.
Referring to fig. 3, fig. 3 is a schematic block diagram of an electronic device 100 provided in the present application, and in some embodiments, the electronic device 100 may be an apparatus for performing the beautifying method provided in the present application, such as the server described above; the electronic device 100 may also be a device for executing the beauty parameter maintenance method provided by the present application, for example, the electronic device 100 may obtain a space variable maintenance policy by executing the beauty parameter maintenance method provided by the present application, and send the space variable maintenance policy to the server in fig. 1, so that the server executes the beauty method provided by the present application based on the obtained space variable maintenance policy.
It is understood that, in some embodiments of the present application, the electronic device 100 may not only perform the beauty parameter maintenance method provided by the present application, but also perform the beauty method provided by the present application based on the obtained space variable maintenance policy as a server.
In some embodiments, the electronic device 100 may include a memory 101, a processor 102, and a communication interface 103, the memory 101, the processor 102, and the communication interface 103 being electrically connected to one another, directly or indirectly, to enable the transfer or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines.
The memory 101 may be configured to store software programs and modules, such as program instructions/modules corresponding to the beauty parameter maintaining apparatus or the beauty apparatus provided in the present application, and the processor 102 executes various functional applications and data processing by executing the software programs and modules stored in the memory 101, so as to execute the steps of the beauty parameter maintaining method or the beauty method provided in the present application. The communication interface 103 may be used for communicating signaling or data with other node devices.
The Memory 101 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Programmable Read-Only Memory (EEPROM), and the like.
The processor 102 may be an integrated circuit chip having signal processing capabilities. The Processor 102 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
It will be appreciated that the configuration shown in fig. 3 is merely illustrative and that electronic device 100 may include more or fewer components than shown in fig. 3 or have a different configuration than shown in fig. 3. The components shown in fig. 3 may be implemented in hardware, software, or a combination thereof.
The following takes the electronic device 100 shown in fig. 3 as an exemplary execution subject to exemplarily explain the beauty parameter maintenance method provided by the present application.
Referring to fig. 4, fig. 4 shows an exemplary flowchart of a beauty parameter maintaining method provided by the present application, which may include the following steps:
In some embodiments, taking a beauty parameter maintenance scheme for two live broadcast platforms as an example, the electronic device may obtain a first space variable table and a second space variable table used by each of the two live broadcast platforms; the first space variable table and the second space variable table may both be the space variable tables shown in fig. 2, and the dimensionality of the first space variable table is the same as that of the second space variable table, for example, the first space variable table and the second space variable table may both be N-dimensional space variable tables, for example, both may be three-dimensional space variable tables shown in fig. 2, and N is a positive integer.
In addition, in some embodiments, the first and second spatial variable tables may include a plurality of sets of beauty parameters, respectively; for example, referring to the three-dimensional space variable table shown in fig. 2, each point of the three-dimensional space variable table may represent a set of beauty parameters, and each set of beauty parameters may correspond to a beauty effect.
Of course, it can be understood that different groups of beauty parameters in the same space variable table may correspond to different beauty effects, and the same beauty parameters in the first space variable table and the second space variable table may also correspond to different beauty effects.
Next, the electronic device may determine, for the first beauty parameter in the first space variable table, a second beauty parameter corresponding to the same beauty effect as the first beauty parameter in the second space variable table, with the beauty effect corresponding to each of the beauty parameters as a comparison object.
When the electronic device determines a second beauty parameter of the first beauty parameter in the first space variable table in the second space variable table, the electronic device may store a corresponding relationship between the first beauty parameter and the second beauty parameter, and record the corresponding relationship between the first beauty parameter and the second beauty parameter in a space variable maintenance policy, where the space variable maintenance policy may record a corresponding relationship between the beauty parameter in the first space variable table and the beauty parameter in the second space variable table.
In this way, according to the above scheme provided by the application, the electronic device may obtain respective corresponding relationships between the plurality of beauty parameters in the first space variable table and the plurality of beauty parameters in the second space variable table, and record the obtained respective corresponding relationships in the space variable maintenance policy.
For example, in the example where the big eye 0.6 of the live platform a and the big eye 0.4 of the live platform B have the same beauty effect, the spatial variable maintenance policy may record the following:
| live broadcast platform A | Live broadcast platform B |
| …… | …… |
| 0.6 big eye | 0.4 of large eye |
| …… | …… |
In some embodiments, in the process of executing step 203, the electronic device may use the beauty effect corresponding to the first beauty parameter as a comparison standard, and compare the beauty effect corresponding to each of the beauty parameters included in the second spatial variable table with the beauty effect corresponding to the first beauty parameter, so as to determine, in the second spatial variable table, a second beauty parameter having the same beauty effect as the first beauty parameter.
For example, when the electronic device executes the beauty parameter maintenance method provided by the present application, the electronic device may obtain a beauty image corresponding to each beauty image, for example, obtain a first beauty image obtained after performing beauty processing according to a first beauty parameter, and obtain a plurality of second beauty images obtained after performing beauty processing according to a plurality of beauty parameters in a second space variable table.
Based on this, in the process of executing step 203, the electronic device may use the first beauty image corresponding to the first beauty parameter as a reference, use the pixel difference between the first beauty image and each second beauty image as a judgment basis, and when the pixel difference between one of the second beauty images and the first beauty image is smaller than the set threshold, the electronic device may determine the second beauty image at this time as a target beauty image having the same beauty effect as the first beauty image, and determine the beauty parameter corresponding to the target beauty image as the second beauty parameter.
In some scenarios, in order to promote the electronic device to obtain the corresponding relationship between the plurality of beauty parameters in the first space variable table and the plurality of beauty parameters in the second space variable table, the electronic device may obtain the target beauty image having the same beauty effect as the first beauty image based on a pre-constructed machine learning model.
For example, the electronic device may pre-construct a DQN (Deep Q-Network) model as shown in fig. 5, and train the DQN model based on Reinforcement Learning (Reinforcement Learning).
For example, in the process of performing reinforcement learning on the DQN model, the electronic device may perform reinforcement learning on the DQN model shown in fig. 5 by using the respective beauty effects of the first beauty image and each second beauty image as response values, and using the difference value between the beauty effects of the first beauty image and each second beauty image as a feedback value, so as to obtain a target beauty image output by the DQN model and having the same beauty effect as the first beauty image.
In this way, the electronic device outputs a target beauty image having the same beauty effect as the first beauty image by using the machine learning model based on a reinforcement learning mode, and meanwhile, the machine learning model learns more corresponding relations between beauty parameters in the first space variable table and beauty parameters in the second space variable table, so as to improve the generation speed of the space variable maintenance strategy; and the corresponding relation between the beauty parameters in the first space variable table and the beauty parameters in the second space variable table does not need to be calculated, so that the calculation amount can be reduced, and the calculation resources are saved.
In some possible application scenarios, based on the obtained space variable maintenance policy, the space variable maintenance policy may be stored in a server as shown in fig. 1, the server may establish communication with a live broadcast initiating terminal, and a anchor may generate a live broadcast code stream by using the live broadcast initiating terminal and send the live broadcast code stream to the server; when the server receives the live broadcast code stream, the server can execute the following beautifying method based on the stored space variable maintenance strategy, perform beautifying processing on the live broadcast image in the live broadcast code stream, and send out the live broadcast image after the beautifying processing.
It is to be understood that, in some possible scenarios, the electronic device and the server may be different devices, and when the electronic device obtains the space variable maintenance policy by executing the beauty parameter maintenance method, the electronic device may send the space variable maintenance policy to the server, and then the server executes the beauty method provided in the present application based on the space variable maintenance policy; in addition, in some other possible scenarios of the present application, the electronic device and the server may also be the same device, for example, the electronic device is a server, and when the server obtains the space variable maintenance policy by executing the beauty parameter maintenance method, the server further executes the beauty method provided by the present application based on the space variable maintenance policy.
Referring to fig. 6, fig. 6 shows an exemplary flowchart of a beautifying method provided by the present application, which may include the following steps:
And 305, performing beauty treatment on the live broadcast image to be treated by using the target beauty parameter, and sending out the live broadcast image after the beauty treatment.
In some embodiments, taking the server default usage being the second space variable table for performing the beauty treatment as an example, when the anchor operation live broadcast initiating end indicates to use the beauty policy in the second space variable table to request the server to perform the beauty treatment, the anchor may input the initial beauty parameter at the live broadcast initiating end; the live broadcast initiating terminal can send the received initial beauty parameters and the recorded live broadcast images to be processed to the server, so that the server performs beauty processing on the live broadcast images to be processed by using the second space variable table and combining the initial beauty parameters.
In addition, when the anchor operation live broadcast initiating end indicates to use the beauty strategy request server in the first space variable table request to perform beauty processing, the anchor can input a parameter conversion request and an initial beauty parameter at the live broadcast initiating end; the live broadcast initiating terminal can send the received initial beauty parameters, the parameter conversion request and the recorded live broadcast image to be processed to a server.
In some embodiments, the display interface of the live broadcast initiator may include a conversion request control, and when the anchor of the live broadcast initiator clicks the conversion request control, the live broadcast initiator determines to receive a parameter conversion request input by the anchor.
Thus, when the server receives a live image to be processed sent by a live initiating end and a parameter conversion request aiming at an initial beauty parameter, the server determines that the initial beauty parameter is the beauty parameter aiming at the first space variable table, and can search a target beauty parameter corresponding to the initial beauty parameter in a space variable maintenance strategy in response to the parameter conversion request, wherein the target beauty parameter is the beauty parameter aiming at the second space variable table; namely: the server can respond to a parameter conversion request sent by the live broadcast initiating terminal, and convert the initial beauty parameters aiming at the first space variable table into the target beauty parameters aiming at the second space variable table.
Then, the server may perform the beauty processing on the live broadcast image to be processed by using the target beauty parameter obtained by the conversion, and send out the live broadcast image after the beauty processing, such as feeding back to a live broadcast initiating terminal, or sending to a live broadcast receiving terminal, and the like.
Therefore, based on the above scheme provided by the application, the corresponding relation between each beauty parameter in the first space variable table and each beauty parameter in the second space variable table is obtained, and the obtained corresponding relation is recorded in the space variable maintenance strategy, so that the beauty parameters for the first space variable table and the second space variable table can be mutually converted based on the obtained space variable maintenance strategy; therefore, when the anchor starts live broadcast on different live broadcast platforms, the same beauty parameters can be used for realizing the same live broadcast effect on different live broadcast platforms without adjusting the beauty parameters of each live broadcast platform, and the live broadcast efficiency is improved.
Of course, it is understood that the above is only an example, and the beauty parameter for the first space variable table is converted into the beauty parameter for the second space variable table to exemplify the beauty method provided by the present application; in some other possible embodiments of the present application, the beauty parameter for the second space variable table may also be converted into the beauty parameter for the first space variable table, and the present application does not limit the conversion direction of the beauty parameter.
In addition, based on the same inventive concept as the beauty parameter maintaining method provided in the present application, please refer to fig. 7, fig. 7 shows an exemplary structural block diagram of the beauty parameter maintaining apparatus 400 provided in the present application, and the beauty parameter maintaining apparatus 400 may include a first processing module 401 and a saving module 402.
The first processing module 401 is configured to obtain a first space variable table and a second space variable table; the first space variable table and the second space variable table respectively comprise a plurality of groups of beauty parameters, and each beauty parameter corresponds to a beauty effect;
the first processing module 401 is further configured to, for a first beauty parameter in the first space variable table, determine a second beauty parameter with the same beauty effect as the first beauty parameter in the second space variable table;
a storing module 402, configured to store a corresponding relationship between the first beauty parameter and the second beauty parameter, and record the corresponding relationship in a space variable maintenance policy; the space variable maintenance strategy records the corresponding relation between the beauty parameters in the first space variable table and the beauty parameters in the second space variable table.
Optionally, as a possible implementation manner, when determining, in the second space variable table, a second beauty parameter corresponding to the same beauty effect as the first beauty parameter for the first beauty parameter in the first space variable table, the first processing module 401 is specifically configured to:
and with the first beauty image corresponding to the first beauty parameter as a reference, searching a target beauty image with the same beauty effect as the first beauty image from a plurality of second beauty images subjected to beauty treatment according to the second space variable table, and determining the beauty parameter corresponding to the target beauty image as the second beauty parameter.
Optionally, as a possible implementation manner, when the first beauty image corresponding to the first beauty parameter is taken as a reference, and a target beauty image having the same beauty effect as the first beauty image is found from a plurality of second beauty images subjected to beauty processing according to the second space variable table, the first processing module 401 is specifically configured to:
and taking the corresponding beautifying effect of the first beautifying image and each second beautifying image as a response value, taking the beautifying effect difference value between the first beautifying image and each second beautifying image as a feedback value, performing reinforcement learning on the pre-constructed machine learning model, and obtaining a target beautifying image which is output by the machine learning model and has the same beautifying effect as the first beautifying image.
With respect to fig. 8, based on the same inventive concept as the above-mentioned beautifying method provided in the present application, fig. 8 shows an exemplary structural block diagram of a beautifying apparatus 500 provided in the present application, where the beautifying apparatus 500 may include a transceiver module 501 and a second processing module 502.
A transceiver module 501, configured to receive a live broadcast image to be processed sent by a live broadcast initiator, and a parameter conversion request for an initial beauty parameter; wherein the initial beauty parameter is a beauty parameter for the first space variable table;
a second processing module 502, configured to search, in response to the parameter conversion request, a target beauty parameter corresponding to the initial beauty parameter in the space variable maintenance policy; wherein the target beauty parameter is a beauty parameter for the second space variable table;
the second processing module 502 is further configured to perform a beauty treatment on the live broadcast image to be processed by using the target beauty parameter;
the transceiver module 501 is further configured to send out the live broadcast image after the beauty processing.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to some embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s).
It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in some embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to some embodiments of the present application. And the aforementioned storage medium includes: u disk, removable hard disk, read only memory, random access memory, magnetic or optical disk, etc. for storing program codes.
The above description is only a few examples of the present application and is not intended to limit the present application, and those skilled in the art will appreciate that various modifications and variations can be made in the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (10)
1. A beauty parameter maintenance method, the method comprising:
acquiring a first space variable table and a second space variable table; the first space variable table and the second space variable table respectively comprise a plurality of groups of beautifying parameters, and each beautifying parameter corresponds to a beautifying effect;
for a first beauty parameter in the first space variable table, determining a second beauty parameter with the same beauty effect corresponding to the first beauty parameter in the second space variable table;
storing the corresponding relation between the first beauty parameter and the second beauty parameter, and recording the corresponding relation in a space variable maintenance strategy; the space variable maintenance strategy records the corresponding relation between the beauty parameters in the first space variable table and the beauty parameters in the second space variable table.
2. The method of claim 1, wherein the determining, for a first beauty parameter in the first space variable table, a second beauty parameter in the second space variable table that corresponds to the same beauty effect as the first beauty parameter comprises:
and with the first beauty image corresponding to the first beauty parameter as a reference, searching a target beauty image with the same beauty effect as the first beauty image from a plurality of second beauty images subjected to beauty treatment according to the second space variable table, and determining the beauty parameter corresponding to the target beauty image as the second beauty parameter.
3. The method of claim 2, wherein the finding of the target beauty image having the same beauty effect as the first beauty image from among a plurality of second beauty images subjected to beauty processing according to the second space variable table with reference to the first beauty image corresponding to the first beauty parameter comprises:
and taking the corresponding beautifying effect of the first beautifying image and each second beautifying image as a response value, and taking the beautifying effect difference value between the first beautifying image and each second beautifying image as a feedback value, performing reinforcement learning on a pre-constructed machine learning model, and obtaining a target beautifying image which is output by the machine learning model and has the same beautifying effect as the first beautifying image.
4. The beautifying method is applied to a server, and the server establishes communication with a live broadcast initiating terminal; the server stores a space variable maintenance strategy obtained by the beauty parameter maintenance method according to any one of claims 1-3;
the method comprises the following steps:
receiving a to-be-processed live broadcast image sent by the live broadcast initiating terminal and a parameter conversion request aiming at an initial beauty parameter; wherein the initial beauty parameter is a beauty parameter for the first space variable table;
in response to the parameter conversion request, finding out a target beauty parameter corresponding to the initial beauty parameter in the space variable maintenance strategy; wherein the target beauty parameter is a beauty parameter for the second space variable table;
and performing beauty treatment on the live broadcast image to be treated by using the target beauty parameter, and sending out the live broadcast image after the beauty treatment.
5. A beauty parameter maintenance apparatus, characterized in that the apparatus comprises:
the first processing module is used for acquiring a first space variable table and a second space variable table; the first space variable table and the second space variable table respectively comprise a plurality of groups of beautifying parameters, and each beautifying parameter corresponds to a beautifying effect;
the first processing module is further configured to determine, in the second space variable table, a second beauty parameter corresponding to the same beauty effect as the first beauty parameter for the first beauty parameter in the first space variable table;
the storage module is used for storing the corresponding relation between the first beauty parameter and the second beauty parameter and recording the corresponding relation in a space variable maintenance strategy; the space variable maintenance strategy records the corresponding relation between the beauty parameters in the first space variable table and the beauty parameters in the second space variable table.
6. The apparatus of claim 5, wherein the first processing module, when determining, in the second spatial variable table, a second beauty parameter corresponding to the same beauty effect as the first beauty parameter for the first beauty parameter in the first spatial variable table, is specifically configured to:
and with the first beauty image corresponding to the first beauty parameter as a reference, searching a target beauty image with the same beauty effect as the first beauty image from a plurality of second beauty images subjected to beauty treatment according to the second space variable table, and determining the beauty parameter corresponding to the target beauty image as the second beauty parameter.
7. The apparatus of claim 6, wherein the first processing module, when finding a target beauty image having a same beauty effect as the first beauty image from a plurality of second beauty images that are subjected to beauty processing according to the second spatial variable table with reference to the first beauty image corresponding to the first beauty parameter, is specifically configured to:
and taking the corresponding beautifying effect of the first beautifying image and each second beautifying image as a response value, and taking the beautifying effect difference value between the first beautifying image and each second beautifying image as a feedback value, performing reinforcement learning on a pre-constructed machine learning model, and obtaining a target beautifying image which is output by the machine learning model and has the same beautifying effect as the first beautifying image.
8. The beautifying device is applied to a server, and the server establishes communication with a live broadcast initiating terminal; the server stores a space variable maintenance strategy obtained by the beauty parameter maintenance method according to any one of claims 1-3;
the device comprises:
the receiving and sending module is used for receiving the live broadcast image to be processed sent by the live broadcast initiating terminal and a parameter conversion request aiming at the initial beauty parameter; wherein the initial beauty parameter is a beauty parameter for the first space variable table;
the second processing module is used for responding to the parameter conversion request, and finding out a target beauty parameter corresponding to the initial beauty parameter in the space variable maintenance strategy; wherein the target beauty parameter is a beauty parameter for the second space variable table;
the second processing module is further configured to perform beauty treatment on the live broadcast image to be processed by using the target beauty parameter;
the receiving and sending module is further used for sending out the live broadcast image after the beautifying processing.
9. An electronic device, comprising:
a memory for storing one or more programs;
a processor;
the one or more programs, when executed by the processor, implement the method of any of claims 1-4.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010975503.6A CN112102195A (en) | 2020-09-16 | 2020-09-16 | Beautifying method, parameter maintenance method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010975503.6A CN112102195A (en) | 2020-09-16 | 2020-09-16 | Beautifying method, parameter maintenance method, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112102195A true CN112102195A (en) | 2020-12-18 |
Family
ID=73759284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010975503.6A Pending CN112102195A (en) | 2020-09-16 | 2020-09-16 | Beautifying method, parameter maintenance method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112102195A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113573092A (en) * | 2021-07-30 | 2021-10-29 | 北京达佳互联信息技术有限公司 | Live broadcast data processing method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106231207A (en) * | 2016-07-21 | 2016-12-14 | 北京小米移动软件有限公司 | Image processing method and device |
| CN106341696A (en) * | 2016-09-28 | 2017-01-18 | 北京奇虎科技有限公司 | Live video stream processing method and device |
| CN108718385A (en) * | 2018-07-31 | 2018-10-30 | 北京会播科技有限公司 | Image processing apparatus and method |
-
2020
- 2020-09-16 CN CN202010975503.6A patent/CN112102195A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106231207A (en) * | 2016-07-21 | 2016-12-14 | 北京小米移动软件有限公司 | Image processing method and device |
| CN106341696A (en) * | 2016-09-28 | 2017-01-18 | 北京奇虎科技有限公司 | Live video stream processing method and device |
| CN108718385A (en) * | 2018-07-31 | 2018-10-30 | 北京会播科技有限公司 | Image processing apparatus and method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113573092A (en) * | 2021-07-30 | 2021-10-29 | 北京达佳互联信息技术有限公司 | Live broadcast data processing method and device, electronic equipment and storage medium |
| CN113573092B (en) * | 2021-07-30 | 2022-09-30 | 北京达佳互联信息技术有限公司 | Live broadcast data processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10796685B2 (en) | Method and device for image recognition | |
| CN108563670B (en) | Video recommendation method and device, server and computer-readable storage medium | |
| CN112929678B (en) | Live broadcast method, live broadcast device, server side and computer readable storage medium | |
| US10200268B2 (en) | Methods and systems for congestion-based content delivery | |
| CN108184170B (en) | Data processing method and device | |
| CN110856008B (en) | Live broadcast interaction method, device and system, electronic equipment and storage medium | |
| CN110677267B (en) | Information processing method and device | |
| CN112218108B (en) | Live broadcast rendering method and device, electronic equipment and storage medium | |
| JP6026680B1 (en) | Method and system for performing image identification | |
| CN108600780B (en) | Method for pushing information, electronic device and computer readable medium | |
| CN115022679B (en) | Video processing method, device, electronic equipment and medium | |
| CN112118472A (en) | Method and apparatus for playing multimedia | |
| CN111027301A (en) | Information processing method, device, terminal equipment and storage medium | |
| CN112929728A (en) | Video rendering method, device and system, electronic equipment and storage medium | |
| CN111259245B (en) | Work pushing method, device and storage medium | |
| CN112102195A (en) | Beautifying method, parameter maintenance method, device, electronic equipment and storage medium | |
| CN113051481B (en) | Content recommendation method, device, electronic equipment and medium | |
| CN107733874B (en) | Information processing method, information processing device, computer equipment and storage medium | |
| CN111049735B (en) | Group head portrait display method, device, equipment and storage medium | |
| US11750876B2 (en) | Method and apparatus for determining object adding mode, electronic device and medium | |
| US20240236395A9 (en) | Video definition grade determining method and apparatus, server, storage medium and system | |
| WO2016138698A1 (en) | Friend adding method and device therefor | |
| CN110413817B (en) | Method and device for clustering pictures | |
| CN111314627B (en) | Method and apparatus for processing video frames | |
| CN115525780A (en) | Template recommendation method, device, equipment and storage medium |
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 |