CN117314794B - Live broadcast beautifying method and device, electronic equipment and storage medium - Google Patents
Live broadcast beautifying method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117314794B CN117314794B CN202311617817.9A CN202311617817A CN117314794B CN 117314794 B CN117314794 B CN 117314794B CN 202311617817 A CN202311617817 A CN 202311617817A CN 117314794 B CN117314794 B CN 117314794B
- Authority
- CN
- China
- Prior art keywords
- image
- standard
- beautified
- area
- parameters
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000001514 detection method Methods 0.000 claims description 36
- 230000003796 beauty Effects 0.000 claims description 34
- 238000012937 correction Methods 0.000 claims description 7
- 230000001815 facial effect Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 210000000056 organ Anatomy 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- 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
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/47815—Electronic shopping
Abstract
The application relates to the field of image processing, in particular to a live-broadcast beautifying method, a live-broadcast beautifying device, electronic equipment and a storage medium. The method and the device enable the live audience to know the accurate information of the goods and the goods more accurately.
Description
Technical Field
The present application relates to the field of image processing, and in particular, to a live-broadcast beautifying method, a live-broadcast beautifying device, an electronic device and a storage medium.
Background
Live broadcast is a way to share audio and video content in real time through the internet. The anchor is an creator of live content, and usually the anchor uses beauty in the live process for showing better forms and meters to live viewers. The beautifying technology can be used for beautifying the image of the anchor in the live video, such as modifying the color, shape and organ proportion of the human body.
The method of beautifying is usually to identify a human body target, and then to modify the whole area of the human body target in the image correspondingly, or even directly modify the whole image. However, if the live broadcast is in a scene with the live broadcast content, the live broadcast host starts to beautify the face during live broadcast, the beautification can often make the live broadcast show the live broadcast commodity to the audience to beautify the face together, and further, the information such as the color, the shape, the proportion and the like of the live broadcast commodity seen by the live broadcast audience during live broadcast has larger deviation with the actual color, the shape and the proportion information of the live broadcast commodity, so that the live broadcast audience cannot accurately know the accurate information of the live broadcast commodity.
Disclosure of Invention
In order to enable a live audience to more accurately know accurate information of goods, the application provides a live beautifying method, a live beautifying device, electronic equipment and a storage medium.
In a first aspect, the present application provides a live-broadcast beautifying method, which adopts the following technical scheme:
a live beautifying method, comprising:
acquiring an image to be beautified, and determining a first area and a second area in the image to be beautified, wherein the first area is an area of a human target in the image, and the second area is an area of a commodity with goods in the image;
determining a coincidence region of the first region and the second region;
determining a region to be beautified based on the first region and the superposition region, wherein the region to be beautified is other regions of the first region which do not comprise the superposition region;
and beautifying the region to be beautified to obtain the beautified image.
Through adopting above-mentioned technical scheme, can discern the first region of determining human target and the second region of commodity of taking, combine first region and second region, confirm the coincidence area that does not need the beauty in the first region to only treat the beauty area to the beauty that does not include the coincidence area in the first region, and then make the second region of commodity of taking not carry out the beauty, just also make live broadcast spectator can see more accurate information of commodity of taking.
In one possible implementation, the method further includes:
obtaining standard parameters of the commodity with goods, wherein the standard parameters comprise at least one of standard color parameters, standard texture parameters, standard proportion parameters and standard contour parameters;
and correcting the second area in the beautified image based on the standard parameters to obtain a corrected image, wherein the corrected image is used for generating a video stream transmitted to a live audience.
In one possible implementation, when the standard parameter includes a standard scale parameter, correcting the second region in the beautified image based on the standard parameter includes:
carrying out gray processing on the second area in the beautified image to obtain a gray image;
determining at least two characteristic areas based on pixel point gray value distribution in the gray image;
determining a lateral-longitudinal direction of the goods in the second region based on the at least two feature regions;
and correcting the second area in the beautified image based on the standard transverse-longitudinal ratio and the transverse-longitudinal direction.
In one possible implementation, before obtaining the standard parameters of the commodity, the method further includes:
acquiring a plurality of standard images acquired for the goods with goods, wherein the acquisition position and the acquisition angle of each standard image are different;
extracting the characteristics of each standard image, and determining standard parameters corresponding to each standard image;
and determining standard parameters of the goods with goods based on the standard parameters corresponding to each standard image.
In one possible implementation manner, the determining the second area in the image to be beautified includes:
determining detection characteristics of the goods with goods;
and determining a second area from the image to be beautified based on the detection characteristic.
In one possible implementation, the determining the detection feature of the commodity includes:
acquiring shooting parameters of the image to be beautified, wherein the shooting parameters comprise a lens type and an exposure type;
and determining detection characteristics of the commodity with goods based on the shooting parameters, wherein the detection characteristics comprise at least one of color characteristics, texture characteristics and contour characteristics.
In a second aspect, the present application provides a live-broadcast beautifying device, which adopts the following technical scheme:
a live beauty device, comprising:
the system comprises an image acquisition module to be beautified, a first image acquisition module and a second image acquisition module, wherein the image acquisition module is used for acquiring an image to be beautified, and determining a first area and a second area in the image to be beautified, the first area is an area of a human target in the image, and the second area is an area of a commodity with goods in the image;
the overlapping region determining module is used for determining an overlapping region of the first region and the second region;
the to-be-beautified area determining module is used for determining to-be-beautified areas based on the first area and the superposition area, wherein the to-be-beautified areas are other areas which do not comprise the superposition area in the first area;
and the beauty Yan Mokuai is used for beautifying the region to be beautified to obtain a beautified image.
Through adopting above-mentioned technical scheme, the device can discern the first region of determining human target and the second region of commodity of taking goods, combines first region and second region, determines the coincidence region that does not need the beauty in the first region to only treat the beauty in the first region including coincidence region and carry out the beauty, and then make the second region of commodity of taking goods not carry out the beauty, just also make live broadcast spectator can see more accurate information of commodity of taking goods.
In one possible implementation, the apparatus further includes:
the standard parameter determining module is used for obtaining standard parameters of the goods, wherein the standard parameters comprise at least one of standard color parameters, standard texture parameters, standard proportion parameters and standard contour parameters;
and the correction module is used for correcting the second area in the beautified image based on the standard parameters to obtain a corrected image, and the corrected image is used for generating a video stream transmitted to the live audience terminal.
In one possible implementation manner, if the standard parameter includes a standard scale parameter, the correction module is specifically configured to, when correcting the second area in the beautified image based on the standard parameter:
carrying out gray processing on the second area in the beautified image to obtain a gray image;
determining at least two characteristic areas based on pixel point gray value distribution in the gray image;
determining a lateral-longitudinal direction of the goods in the second region based on the at least two feature regions;
and correcting the second area in the beautified image based on the standard transverse-longitudinal ratio and the transverse-longitudinal direction.
In one possible implementation, the apparatus further includes:
the standard image acquisition module is used for acquiring a plurality of standard images acquired by the goods, wherein the acquisition position and the acquisition angle of each standard image are different;
the feature extraction module is used for extracting features of each standard image and determining standard parameters corresponding to each standard image;
and the standard parameter determining module is used for determining standard parameters of the goods on the basis of the standard parameters corresponding to each standard image.
In one possible implementation manner, when the to-be-beautified image acquisition module determines the second area in the to-be-beautified image, the to-be-beautified image acquisition module is specifically configured to:
determining detection characteristics of the goods with goods;
and determining a second area from the image to be beautified based on the detection characteristic.
In one possible implementation manner, when the to-be-beautified image acquisition module determines the detection feature of the commodity with goods, the to-be-beautified image acquisition module is specifically configured to:
acquiring shooting parameters of the image to be beautified, wherein the shooting parameters comprise a lens type and an exposure type;
and determining detection characteristics of the commodity with goods based on the shooting parameters, wherein the detection characteristics comprise at least one of color characteristics, texture characteristics and contour characteristics.
In a third aspect, the present application provides an electronic device, which adopts the following technical scheme:
an electronic device, the electronic device comprising:
at least one processor;
a memory;
at least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application configured to: the live beautifying method in the first aspect is performed.
In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical scheme:
a computer-readable storage medium, comprising: a computer program is stored that can be loaded by a processor and that performs the above-described method of live-beautifying.
In summary, the present application includes at least one of the following beneficial technical effects:
the method and the device can identify and determine the first area of the human body target and the second area of the commodity with goods, and combine the first area and the second area to determine the overlapping area which does not need to be beautified in the first area, and beautify the area to be beautified which does not comprise the overlapping area in the first area, so that the second area of the commodity with goods does not beautify, and a live broadcast audience can see more accurate information of the commodity with goods.
Drawings
Fig. 1 is a schematic flow chart of a method for direct-broadcasting beauty in an embodiment of the application;
fig. 2 is a schematic diagram of a first area and a second area in an image to be beautified in the embodiment of the application;
fig. 3 is a schematic structural diagram of a beauty live broadcast device in an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device in an embodiment of the present application.
Detailed Description
The present application is described in further detail below in conjunction with fig. 1-4.
Modifications of the embodiments which do not creatively contribute to the invention may be made by those skilled in the art after reading the present specification, but are protected by patent laws only within the scope of claims of the present application.
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
In addition, the term "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In this context, unless otherwise specified, the term "/" generally indicates that the associated object is an "or" relationship.
The embodiment of the application provides a live beautifying method which is executed by electronic equipment, wherein the electronic equipment comprises, but is not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, video cameras, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), car terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like, and servers and the like are also possible.
Referring to fig. 1, the live beautifying method includes steps S01 to S04, in which:
and S01, acquiring an image to be beautified, and determining a first area and a second area in the image to be beautified.
For the embodiment of the application, the image to be beautified is an image acquired in real time in a live scene. Typically, when the anchor is on the fly, the requirements for beauty include facial beauty, limb beauty, and filter beauty. Face beauty requires adjustment of face color, face shape and organ ratio; the limbs are beautified, and the height, the fat and the thin of the limbs and the proportion of the limbs are required to be adjusted; the filter beautifying requires modification of parameters such as exposure, saturation, contrast and the like for the whole image.
Specifically, referring to fig. 2, the first region is a region in the image to be beautified of the human target, where the human target may be a plurality of human targets or one human target. The second area is the area of the commodity to be beautified in the image to be beautified. In the embodiment of the present application, a person object and a commodity to be carried, that is, a first area and a second area, exist in each image to be beautified are taken as examples for explanation.
Step S02, determining a superposition area of the first area and the second area;
step S03, determining a region to be beautified based on the first region and the overlapping region, wherein the region to be beautified is other regions which do not include the overlapping region in the first region.
For the embodiment of the application, when the host is directly broadcast to carry out goods, the goods carried by the host need to be held by hand for demonstration explanation most of the time, and then the goods carried by the host are placed in front of the human body target, namely, the first area and the second area have overlapping areas.
And S04, carrying out beauty treatment on the region to be subjected to beauty treatment to obtain a beautiful image.
For the embodiment of the application, if the overlapping area exists, the overlapping area in the first area is not beautified, and only the area to be beautified, which does not include the overlapping area in the first area, is beautified. And if the overlapping area does not exist, beautifying the complete first area.
According to the scheme, the first area of the human body target and the second area of the commodity with goods can be identified and determined, the overlapping area which does not need to be beautified in the first area is determined by combining the first area with the second area, and the beautifying is carried out only on the area to be beautified which does not comprise the overlapping area in the first area, so that the second area of the commodity with goods does not beautify, and a live broadcast audience can see more accurate information of the commodity with goods.
Further, since the contour and the features of the human body target are relatively fixed, determining the first region in the image to be beautified includes determining the first region based on the facial features and further includes determining the first region based on the contour of the human body.
Further, since randomness of the commodity with goods is strong, and feature differences such as contours, colors and textures among different commodities with goods are large, and the expression form of the commodity with goods in the image to be beautified is greatly influenced by factors such as a mode and a style when the image is acquired, determining the second area in the image to be beautified specifically may include: the detection features of the goods in the belt are determined, and then a second area is determined from the image to be beautified based on the detection features.
Specifically, shooting parameters of an image to be beautified are obtained, and detection characteristics of the commodity with goods are determined based on the shooting parameters; wherein the photographing parameters include a lens type and an exposure type, and the detection feature includes at least one of a color feature, a texture feature, and a contour feature. The shooting parameters can be acquired based on information carried by the image or input by a user.
When the image capturing device is used for capturing live images, various shooting modes and shooting styles can be used. For example, a wide-angle lens is used for image acquisition, and different exposure types are used for image acquisition. The image collected by the wide-angle lens can change the shape of a target in the image, and when different exposure types are adopted for image collection, the overall brightness of the image is different due to different exposure, so that different deviations exist in the white balance of the target in the collected image under different exposure types, and color misalignment is caused.
Thus, when determining the second region in the image to be beautified, the detection feature of the second region is determined based on the acquired shooting parameters; specifically, if the photographing parameters characterize that the image to be beautified is photographed by the wide-angle lens, the detection features do not include contour features, but the second region is determined in the image to be beautified based on the color features and the texture features. If the shooting parameters represent that the image to be beautified is shot under the condition of overexposure or underexposure, the detection features do not comprise color features, and a second area is determined in the image to be beautified based on the contour features and the texture features. Furthermore, the second area can be accurately and rapidly determined by the mode.
In fact, when a live broadcast audience watches live broadcast, the live broadcast audience cannot accurately know the reason of the accurate information of the goods with goods, and the live broadcast audience not only comprises the reason that the beauty opened by a host broadcast is used for beautifying the goods with goods, but also comprises factors of live broadcast field environment and shooting modes, such as over-bright or over-dark live broadcast field lighting, or live broadcast by collecting images in a wide-angle shooting mode and the like, so that the deviation of parameters such as color, shape, proportion and the like of the target goods can be caused.
Therefore, further, after the region to be beautified is beautified, the method may further include: and acquiring standard parameters of the commodity with goods, and correcting a second area in the beautified image based on the standard parameters to obtain a corrected image, wherein the corrected image is used for generating a video stream transmitted to a live audience terminal.
Specifically, the standard parameters comprise at least one of standard color parameters, standard texture parameters, standard proportion parameters and standard contour parameters; and if the standard parameters comprise a plurality of items, correcting the second area in the beautified image based on each standard parameter. That is, after the previous standard parameters correct the second area, the subsequent standard parameters correct the previous standard parameters again on the basis of the corrected second area until all standard parameters are corrected, and a corrected image is obtained.
The process of obtaining the standard parameters specifically may include: and acquiring a plurality of standard images acquired for the goods with goods, extracting the characteristics of each standard image, determining the standard parameters corresponding to each standard image, and determining the standard parameters of the goods with goods based on the standard parameters corresponding to each standard image.
Specifically, the acquisition position and the acquisition angle of each standard image are different from each other, and the standard image is an image acquired under the shooting modes of automatic exposure balance, non-wide angle and the like under the natural light with preset intensity. The number of standard images is not particularly limited in the embodiment of the present application. And extracting parameters of each standard image to obtain color parameters, texture parameters and proportion parameters of each standard image. The standard color parameters can specifically comprise color type distribution of the target commodity and a corresponding RGB value range of each color in the RGB color gamut; the standard texture parameters comprise a plurality of texture features and a degree of density corresponding to each texture feature. The standard ratio parameters include the ratio of the lateral and longitudinal lengths of the respective side angles of the target article, i.e., the aspect ratio. Further, each side view angle corresponds to at least one key feature for reference, and the key feature represents a transverse and longitudinal direction, that is, one transverse and longitudinal direction corresponds to one transverse and longitudinal ratio, wherein the key feature selects a region with darker color and/or higher brightness.
Specifically, the standard features of the commodity with goods can be more accurately determined through a plurality of standard images.
Further, when the standard parameter includes a standard scale parameter, the process of correcting the second region in the image after the face-beautifying based on the standard parameter, that is, correcting the second region in the image after the face-beautifying based on the standard scale parameter, may specifically include:
carrying out gray processing on a second region in the beautified image to obtain a gray image, and determining at least two characteristic regions based on pixel point gray value distribution in the gray image; determining a transverse and longitudinal direction of the goods in the second area based on the at least two characteristic areas; and correcting the second area in the beautified image based on the standard transverse-longitudinal ratio and the transverse-longitudinal direction.
Specifically, the second region is subjected to gray scale processing to reduce the influence of color deviation on the correction process. After the gray image is obtained, the higher the gray value of the region in the gray image is, the darker the true color or the higher the brightness is. Two areas with gray values higher than a preset threshold value are selected from the gray image as characteristic areas, the two characteristic areas are compared with a plurality of key characteristics in standard proportion parameters, so that key characteristics matched with at least one characteristic area are determined, the transverse and longitudinal directions corresponding to the key characteristics are further determined, the transverse and longitudinal ratio corresponding to the transverse and longitudinal directions is further determined to be the standard transverse and longitudinal ratio, and the second area is further corrected based on the standard transverse and longitudinal ratio.
Through the method, the shooting view angle of the goods in the second area in the beautified image can be accurately determined, and further the goods in the second area are corrected based on the standard transverse-longitudinal comparison corresponding to the side shooting view angle, so that live broadcast audiences can see the goods in the second area with more true proportion.
The foregoing embodiment describes a live beautifying method from the perspective of a method flow, and the following embodiment describes a live beautifying device from the perspective of a virtual module or a virtual unit, specifically the following embodiment.
The embodiment of the application provides a live-broadcast beauty device, as shown in fig. 3, the live-broadcast beauty device may specifically include a to-be-beauty image acquisition module 301, a superposition area determination module 302, a to-be-beauty area determination module 303, and a beauty Yan Mokuai, where:
the to-be-beautified image acquisition module 301 is configured to acquire an to-be-beautified image, and determine a first area and a second area in the to-be-beautified image, where the first area is an area of a human target in the image, and the second area is an area of a commodity in the image;
a coincidence region determining module 302, configured to determine a coincidence region of the first region and the second region;
the to-be-beautified area determining module 303 is configured to determine an to-be-beautified area based on the first area and the overlapping area, where the to-be-beautified area is other areas of the first area that do not include the overlapping area;
and the beauty Yan Mokuai is used for beautifying the region to be beautified to obtain the beautified image.
Through adopting above-mentioned technical scheme, the device can discern the first region of determining human target and the second region of commodity of taking goods, combines first region and second region, determines the coincidence region that does not need the beauty in the first region to only treat the beauty in the first region including coincidence region and carry out the beauty, and then make the second region of commodity of taking goods not carry out the beauty, just also make live broadcast spectator can see more accurate information of commodity of taking goods.
In one possible implementation, the apparatus further includes:
the standard parameter determining module is used for obtaining standard parameters of the goods to be carried, wherein the standard parameters comprise at least one of standard color parameters, standard texture parameters, standard proportion parameters and standard contour parameters;
and the correction module is used for correcting the second area in the beautified image based on the standard parameters to obtain a corrected image, and the corrected image is used for generating a video stream transmitted to the live audience.
In one possible implementation, if the standard parameter includes a standard scale parameter, the correction module 304 corrects the second region in the beautified image based on the standard parameter, specifically for:
carrying out gray processing on a second area in the beautified image to obtain a gray image;
determining at least two characteristic areas based on pixel point gray value distribution in the gray image;
determining a transverse and longitudinal direction of the goods in the second area based on the at least two characteristic areas;
and correcting the second area in the beautified image based on the standard transverse-longitudinal ratio and the transverse-longitudinal direction.
In one possible implementation, the apparatus further includes:
the standard image acquisition module is used for acquiring a plurality of standard images acquired by the goods, wherein the acquisition position and the acquisition angle of each standard image are different;
the feature extraction module is used for extracting features of each standard image and determining standard parameters corresponding to each standard image;
and the standard parameter determining module is used for determining standard parameters of the goods with goods based on the standard parameters corresponding to each standard image.
In one possible implementation manner, when the image to be beautified acquiring module 301 determines the second area in the image to be beautified, the method is specifically used for:
determining detection characteristics of the goods with goods;
and determining a second area from the image to be beautified based on the detection characteristic.
In one possible implementation manner, when the to-be-beautified image acquisition module determines the detection feature of the commodity with goods, the to-be-beautified image acquisition module is specifically configured to:
acquiring shooting parameters of an image to be beautified, wherein the shooting parameters comprise a lens type and an exposure type;
a detection feature of the commodity is determined based on the shooting parameters, wherein the detection feature comprises at least one of a color feature, a texture feature and a contour feature.
In an embodiment of the present application, as shown in fig. 4, an electronic device 400 shown in fig. 4 includes: a processor 401 and a memory 403. Processor 401 is connected to memory 403, such as via bus 402. Optionally, the electronic device 400 may also include a transceiver 404. It should be noted that, in practical applications, the transceiver 404 is not limited to one, and the structure of the electronic device 400 is not limited to the embodiment of the present application.
The processor 401 may be a CPU (Central Processing Unit ), general purpose processor, DSP (Digital Signal Processor, data signal processor), ASIC (Application Specific Integrated Circuit ), FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules, and circuits described in connection with this disclosure. Processor 401 may also be a combination that implements computing functionality, such as a combination comprising one or more microprocessors, a combination of a DSP and a microprocessor, or the like.
Bus 402 may include a path to transfer information between the components. Bus 402 may be a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus or EISA (Extended Industry Standard Architecture ) bus, among others. Bus 402 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 4, but not only one bus or one type of bus.
The Memory 403 may be, but is not limited to, a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory ) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory ), a CD-ROM (Compact Disc Read Only Memory, compact disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The memory 403 is used for storing application program codes for executing the present application and is controlled to be executed by the processor 401. The processor 401 is arranged to execute application code stored in the memory 403 for implementing what is shown in the foregoing method embodiments.
The electronic device shown in fig. 4 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.
The present application provides a computer readable storage medium having a computer program stored thereon, which when run on a computer, causes the computer to perform the corresponding method embodiments described above.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
The foregoing is only a partial embodiment of the present application and it should be noted that, for a person skilled in the art, several improvements and modifications can be made without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.
Claims (4)
1. A live beautifying method, comprising:
acquiring an image to be beautified, and determining a first area and a second area in the image to be beautified, wherein the first area is an area of a human target in the image, and the determining of the first area in the image to be beautified comprises: in the image to be beautified, determining a first area based on facial features and human body contours, wherein the second area is an area of the commodity with goods in the image;
determining a coincidence region of the first region and the second region;
determining a region to be beautified based on the first region and the superposition region, wherein the region to be beautified is other regions of the first region which do not comprise the superposition region;
carrying out beauty treatment on the region to be subjected to beauty treatment to obtain a beautiful image;
obtaining standard parameters of the commodity with goods, wherein the standard parameters comprise at least one of standard color parameters, standard texture parameters, standard proportion parameters and standard contour parameters;
correcting the second area in the beautified image based on the standard parameters to obtain a corrected image, wherein the corrected image is used for generating a video stream transmitted to a live audience terminal;
if the standard parameters comprise a plurality of items, correcting the second area after correcting the previous standard parameters, and correcting the subsequent standard parameters again on the basis of the corrected second area of the previous standard parameters until all standard parameters are corrected to obtain a corrected image, wherein the previous standard parameters are any one of the plurality of standard parameters, and the subsequent standard parameters are any one of the rest standard parameters in the plurality of standard parameters;
the standard proportion parameter comprises the proportion of the transverse length and the longitudinal length of the angles of each side of the target commodity, namely the transverse-longitudinal ratio; each side view angle corresponds to at least one key feature serving as a reference, wherein the key feature represents the transverse and longitudinal directions, namely one transverse and longitudinal direction corresponds to one transverse and longitudinal ratio;
when the standard parameters include standard scale parameters, correcting the second region in the beautified image based on the standard parameters includes:
carrying out gray processing on the second area in the beautified image to obtain a gray image;
determining at least two characteristic areas based on pixel point gray value distribution in the gray image;
determining a lateral-longitudinal direction of the goods in the second region based on the at least two feature regions;
correcting the second region in the beautified image based on the standard transverse-longitudinal ratio and the transverse-longitudinal direction;
selecting two areas with gray values higher than a preset threshold value from a gray image as characteristic areas, comparing the two characteristic areas with a plurality of key characteristics in standard proportion parameters to determine key characteristics matched with at least one characteristic area, further determining the transverse and longitudinal directions corresponding to the key characteristics, further determining the transverse and longitudinal ratio corresponding to the transverse and longitudinal directions as standard transverse and longitudinal ratio, and further correcting the second area based on the standard transverse and longitudinal ratio;
before obtaining the standard parameters of the goods, the method further comprises the following steps:
acquiring a plurality of standard images acquired for the goods with goods, wherein the acquisition position and the acquisition angle of each standard image are different;
extracting the characteristics of each standard image, and determining standard parameters corresponding to each standard image;
determining standard parameters of the goods with goods based on the standard parameters corresponding to each standard image;
determining a second region in the image to be beautified comprises the following steps:
determining a detection characteristic of the commodity;
determining a second area from the image to be beautified based on the detection characteristic;
determining a detection characteristic of the commodity with the goods, comprising:
acquiring shooting parameters of the image to be beautified, wherein the shooting parameters comprise a lens type and an exposure type;
determining detection features of the goods based on the shooting parameters, wherein the detection features comprise at least one of color features, texture features and contour features;
if the shooting parameters represent that the image to be beautified is shot by the wide-angle lens, the detection features do not comprise outline features, and a second area is determined in the image to be beautified based on the color features and the texture features; if the shooting parameters represent that the image to be beautified is shot under the condition of overexposure or underexposure, the detection features do not comprise color features, and a second area is determined in the image to be beautified based on the contour features and the texture features.
2. A live beautifying device, comprising:
the image to be beautified is used for acquiring an image to be beautified, determining a first area and a second area in the image to be beautified, wherein the first area is an area of a human target in the image, and determining the first area in the image to be beautified comprises: in the image to be beautified, determining a first area based on facial features and human body contours, wherein the second area is an area of the commodity with goods in the image;
the overlapping region determining module is used for determining an overlapping region of the first region and the second region;
the to-be-beautified area determining module is used for determining to-be-beautified areas based on the first area and the superposition area, wherein the to-be-beautified areas are other areas which do not comprise the superposition area in the first area;
the beauty Yan Mokuai is used for beautifying the region to be beautified to obtain a beautified image;
the standard parameter determining module is used for obtaining standard parameters of the goods, wherein the standard parameters comprise at least one of standard color parameters, standard texture parameters, standard proportion parameters and standard contour parameters;
the correction module is used for correcting the second area in the beautified image based on the standard parameters to obtain a corrected image, and the corrected image is used for generating a video stream transmitted to a live audience terminal;
if the standard parameters comprise a plurality of items, correcting the second area after correcting the previous standard parameters, and correcting the subsequent standard parameters again on the basis of the corrected second area of the previous standard parameters until all standard parameters are corrected to obtain a corrected image, wherein the previous standard parameters are any one of the plurality of standard parameters, and the subsequent standard parameters are any one of the rest standard parameters in the plurality of standard parameters;
the standard proportion parameter comprises the proportion of the transverse length and the longitudinal length of the angles of each side of the target commodity, namely the transverse-longitudinal ratio; each side view angle corresponds to at least one key feature serving as a reference, wherein the key feature represents the transverse and longitudinal directions, namely one transverse and longitudinal direction corresponds to one transverse and longitudinal ratio;
if the standard parameters include standard proportion parameters, the correction module corrects the second region in the beautified image based on the standard parameters, specifically for:
carrying out gray processing on the second area in the beautified image to obtain a gray image;
determining at least two characteristic areas based on pixel point gray value distribution in the gray image;
determining a lateral-longitudinal direction of the goods in the second region based on the at least two feature regions;
correcting the second region in the beautified image based on the standard transverse-longitudinal ratio and the transverse-longitudinal direction;
selecting two areas with gray values higher than a preset threshold value from a gray image as characteristic areas, comparing the two characteristic areas with a plurality of key characteristics in standard proportion parameters to determine key characteristics matched with at least one characteristic area, further determining the transverse and longitudinal directions corresponding to the key characteristics, further determining the transverse and longitudinal ratio corresponding to the transverse and longitudinal directions as standard transverse and longitudinal ratio, and further correcting the second area based on the standard transverse and longitudinal ratio;
further comprises: the standard image acquisition module is used for acquiring a plurality of standard images acquired by the goods, wherein the acquisition position and the acquisition angle of each standard image are different;
the feature extraction module is used for extracting features of each standard image and determining standard parameters corresponding to each standard image;
the standard parameter determining module is used for determining standard parameters of the goods with goods based on the standard parameters corresponding to each standard image;
when the to-be-beautified image acquisition module determines the second area in the to-be-beautified image, the to-be-beautified image acquisition module is specifically configured to:
determining detection characteristics of the goods with goods;
determining a second area from the image to be beautified based on the detection characteristic;
determining a detection characteristic of the commodity with the goods, comprising:
acquiring shooting parameters of the image to be beautified, wherein the shooting parameters comprise a lens type and an exposure type;
determining detection features of the goods based on the shooting parameters, wherein the detection features comprise at least one of color features, texture features and contour features;
specifically, if the shooting parameters represent that the image to be beautified is shot by the wide-angle lens, the detection features do not comprise contour features, but a second region is determined in the image to be beautified based on the color features and the texture features; if the shooting parameters represent that the image to be beautified is shot under the condition of overexposure or underexposure, the detection features do not comprise color features, and a second area is determined in the image to be beautified based on the contour features and the texture features.
3. An electronic device, comprising:
at least one processor;
a memory;
at least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application configured to: performing the live beauty method of claim 1.
4. A computer-readable storage medium, comprising: a computer program is stored that can be loaded by a processor and that performs the live beauty method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311617817.9A CN117314794B (en) | 2023-11-30 | 2023-11-30 | Live broadcast beautifying method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311617817.9A CN117314794B (en) | 2023-11-30 | 2023-11-30 | Live broadcast beautifying method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117314794A CN117314794A (en) | 2023-12-29 |
| CN117314794B true CN117314794B (en) | 2024-03-01 |
Family
ID=89274178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311617817.9A Active CN117314794B (en) | 2023-11-30 | 2023-11-30 | Live broadcast beautifying method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117314794B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105320482A (en) * | 2014-07-25 | 2016-02-10 | 中兴通讯股份有限公司 | Object displaying method used for mobile terminal and mobile terminal |
| CN108629745A (en) * | 2018-04-12 | 2018-10-09 | Oppo广东移动通信有限公司 | Image processing method, device based on structure light and mobile terminal |
| WO2021047433A1 (en) * | 2019-09-10 | 2021-03-18 | 广州华多网络科技有限公司 | Image processing method and system in live streaming |
-
2023
- 2023-11-30 CN CN202311617817.9A patent/CN117314794B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105320482A (en) * | 2014-07-25 | 2016-02-10 | 中兴通讯股份有限公司 | Object displaying method used for mobile terminal and mobile terminal |
| CN108629745A (en) * | 2018-04-12 | 2018-10-09 | Oppo广东移动通信有限公司 | Image processing method, device based on structure light and mobile terminal |
| WO2021047433A1 (en) * | 2019-09-10 | 2021-03-18 | 广州华多网络科技有限公司 | Image processing method and system in live streaming |
Non-Patent Citations (2)
| Title |
|---|
| Jiang, B et al.Living Images: A Recursive Approach to Computing the Structural Beauty of Images or the Livingness of Space.《ANNALS OF THE AMERICAN ASSOCIATION OF GEOGRAPHERS》.2023,(第6期),第1329-1347页. * |
| 吴迎.基于SIFT和最邻近匹配的商品图像相似度算法.《计算机与现代化》.2020,(第10期),第66-72页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117314794A (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10559095B2 (en) | Image processing apparatus, image processing method, and medium | |
| RU2617557C1 (en) | Method of exposure to virtual objects of additional reality | |
| CN108537155B (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| CN107635098B (en) | High dynamic range images noise remove method, device and equipment | |
| US9390475B2 (en) | Backlight detection method and device | |
| CN108830892B (en) | Face image processing method and device, electronic equipment and computer readable storage medium | |
| US20170163953A1 (en) | Method and electronic device for processing image containing human face | |
| US10984538B2 (en) | Image-processing device, image-processing method, and recording medium | |
| CN108810406B (en) | Portrait light effect processing method, device, terminal and computer readable storage medium | |
| US20150109525A1 (en) | Image processing apparatus, image processing method, and storage medium | |
| KR20170002308A (en) | Apparatus for and method of processing image based on object region | |
| CN111667420B (en) | Image processing method and device | |
| CN103262126A (en) | Image processor, lighting processor and method therefor | |
| CN107564085B (en) | Image warping processing method and device, computing equipment and computer storage medium | |
| CN110677557B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN117314794B (en) | Live broadcast beautifying method and device, electronic equipment and storage medium | |
| JP6937603B2 (en) | Image processing equipment and its control methods, programs, and storage media | |
| JP7277158B2 (en) | Setting device and method, program, storage medium | |
| JP2020145594A (en) | Image processing apparatus, image processing method, and imaging apparatus | |
| CN116128707A (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN110008911B (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| CN112418153A (en) | Image processing method, image processing device, electronic equipment and computer storage medium | |
| CN108965859B (en) | Projection mode identification method, video playing method and device and electronic equipment | |
| CN110430424A (en) | Test method, device, storage medium and the electronic equipment of FOV | |
| JP2021089534A (en) | Image processing device, control method thereof, imaging device, program, 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |