CN104469253A - Face beautification method in real-time video and electronic equipment - Google Patents
Face beautification method in real-time video and electronic equipment Download PDFInfo
- Publication number
- CN104469253A CN104469253A CN201510003501.XA CN201510003501A CN104469253A CN 104469253 A CN104469253 A CN 104469253A CN 201510003501 A CN201510003501 A CN 201510003501A CN 104469253 A CN104469253 A CN 104469253A
- Authority
- CN
- China
- Prior art keywords
- instant video
- video frame
- current instant
- filtering
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a face beautification method in a real-time video and electronic equipment, and belongs to the field of images. The method comprises the steps that a detailed picture corresponding to a current real-time video frame is obtained by predicting at least one detail macro block in the face in the current real-time video frame; the real face in the current real-time video frame is filtered, and a filter picture corresponding to the current real-time video frame is obtained; the detailed picture and the filter picture are fused to form a beautified current real-time video, wherein the beautified current real-time video at least comprises the beautified face. In this way, the detail macro block in the current real-time video frame is predicted, the filter picture and the detailed picture generated after prediction are fused to generate the beautified current real-time video, the face beautifying efficiency in the real-time video is improved, and the user experience effect is improved.
Description
Technical field
The present invention relates to image domains, the method for beautifying faces particularly in a kind of instant video and electronic equipment.
Background technology
Along with instant video application on mobile terminals universal, make increasing user should be used for realizing and mutual between other people by instant video, but, due to the limitation of mobile terminal device and the impact of interaction scenarios imaging environment, cause the second-rate of instant video, especially the face image quality in instant video is poor, so need to provide the method for beautifying faces in a kind of instant video.
Prior art provides the method for beautifying faces in a kind of instant video, the method specifically comprises: obtain the present frame in instant video, face in present frame is beautified, and utilize the present frame after beautifying to replace original present frame, continue to perform above-mentioned steps to the next frame image of present frame, thus realize the beautifying faces in instant video.
The hardware requirement of method to equipment provided due to prior art is higher, and the hardware as the mobile terminal such as smart mobile phone and panel computer cannot meet the hardware requirement of the method, the method making mobile terminal that prior art cannot be used to provide carries out the beautifying faces in instant video, or, when the method that mobile terminal uses prior art to provide, take process resource and the storage resources of equipment in a large number, affect the use of equipment, thus reduce Consumer's Experience effect.
Summary of the invention
In order to improve the efficiency of beautifying faces in instant video, adding users experience effect, embodiments provides the method for beautifying faces in a kind of instant video and electronic equipment.Described technical scheme is as follows:
First aspect, provides the method for beautifying faces in a kind of instant video, and described method comprises:
By predicting at least one details macro block of face in current instant video frame, obtain the detail view that described current instant video frame is corresponding;
Filtering is carried out to real human face in described current instant video frame, obtains the filtering figure that described current instant video frame is corresponding;
Described detail view and described filtering figure are merged, generate beautify after current instant video, described in beautify after current instant video at least comprise the face after beautifying.
In conjunction with first aspect, in the implementation that the first is possible, described by before in current instant video frame, at least one details macro block of face is predicted, described method also comprises:
Described current instant video frame is split, obtains multiple macro block;
At least one details macro block described is obtained from described multiple macro block.
In conjunction with the first possible implementation of first aspect or first aspect, in the implementation that the second is possible, described by predicting at least one details macro block of face in instant video frame, the detail view obtaining described current instant video frame corresponding comprises:
According to described current instant video frame, at least one details macro block of face in described current instant video frame is predicted.
In conjunction with the first possible implementation of first aspect or first aspect, in the implementation that the third is possible, described by predicting at least one details macro block of face in instant video frame, the detail view obtaining described current instant video frame corresponding also comprises:
According to a upper instant video frame of described current instant video frame, at least one details macro block of face in described current instant video frame is predicted.
In conjunction with first aspect to the third arbitrary possible implementation of first aspect, in the 4th kind of possible implementation, describedly carry out filtering to real human face in described current instant video frame, the filtering figure obtaining described current instant video frame corresponding comprises:
High frequency filter parameter is set;
High frequency filter is carried out to real human face in described current instant video frame, obtains the filtering figure that described current instant video frame is corresponding.
In conjunction with first aspect to the 4th kind of arbitrary possible implementation of first aspect, in the 5th kind of possible implementation, describedly described detail view and described filtering figure to be merged, the current instant video generated after beautifying comprises:
Described detail view and described filtering figure are merged, generates the current instant video frame after merging;
Adjust the luminance parameter of the current instant video frame after described fusion, the current instant video after beautifying described in generation.
In conjunction with first aspect to the 5th kind of arbitrary possible implementation of first aspect, in the 6th kind of possible implementation, describedly described detail view and described filtering figure to be merged, the current instant video generated after beautifying comprises:
Described detail view and described filtering figure are merged, generates the current instant video frame after merging;
Adjust at least one in the red channel parameter of the current instant video frame after described fusion, yellow channels parameter and blue channel parameter, the current instant video after beautifying described in generation.
Second aspect, provides a kind of electronic equipment, it is characterized in that, described equipment comprises:
Prediction module, for by predicting at least one details macro block of face in current instant video frame, obtains the detail view that described current instant video frame is corresponding;
Filtration module, for carrying out filtering to real human face in described current instant video frame, obtains the filtering figure that described current instant video frame is corresponding;
Fusion Module, for described detail view and described filtering figure are merged, generate beautify after current instant video, described in beautify after current instant video at least comprise the face after beautifying.
In conjunction with second aspect, in the implementation that the first is possible, described equipment also comprises:
Segmentation module, for being split by described current instant video frame, obtains multiple macro block;
Described filtration module specifically for obtaining at least one details macro block described from described multiple macro block.
In conjunction with the first possible implementation of second aspect or second aspect, in the implementation that the second is possible, described prediction module specifically for:
According to described current instant video frame, at least one details macro block of face in described current instant video frame is predicted.
In conjunction with the first possible implementation of second aspect or second aspect, in the implementation that the third is possible, described prediction module also specifically for:
According to a upper instant video frame of described current instant video frame, at least one details macro block of face in described current instant video frame is predicted.
In conjunction with second aspect to the third arbitrary possible implementation of second aspect, in the 4th kind of possible implementation, described equipment also comprises:
Module is set, for arranging High frequency filter parameter;
Described filtration module also for carrying out High frequency filter to real human face in described current instant video frame, obtains the filtering figure that described current instant video frame is corresponding.
In conjunction with second aspect to the 4th kind of arbitrary possible implementation of second aspect, in the 5th kind of possible implementation, described Fusion Module specifically for:
Described detail view and described filtering figure are merged, generates the current instant video frame after merging;
Adjust the luminance parameter of the current instant video frame after described fusion, the current instant video after beautifying described in generation.
In conjunction with second aspect to the 5th kind of arbitrary possible implementation of second aspect, in the 6th kind of possible implementation, described Fusion Module also for:
Described detail view and described filtering figure are merged, generates the current instant video frame after merging;
Adjust at least one in the red channel parameter of the current instant video frame after described fusion, yellow channels parameter and blue channel parameter, the current instant video after beautifying described in generation.
The third aspect, provide a kind of electronic equipment, the processor comprising display screen, sending module, receiver module, memory and be connected with described display screen, described sending module, described receiver module, described memory respectively, wherein, batch processing code is stored in described memory, described processor, for calling the program code stored in described memory, performs following operation:
By predicting at least one details macro block of face in current instant video frame, obtain the detail view that described current instant video frame is corresponding;
Filtering is carried out to real human face in described current instant video frame, obtains the filtering figure that described current instant video frame is corresponding;
Described detail view and described filtering figure are merged, generate beautify after current instant video, described in beautify after current instant video at least comprise the face after beautifying.
In conjunction with the third aspect, in the implementation that the first is possible, described processor, for calling the program code stored in described memory, performs following operation:
Described current instant video frame is split, obtains multiple macro block;
At least one details macro block described is obtained from described multiple macro block.
In conjunction with the first possible implementation of the third aspect or the third aspect, in the implementation that the second is possible, described processor, for calling the program code stored in described memory, performs following operation:
According to described current instant video frame, at least one details macro block of face in described current instant video frame is predicted.
In conjunction with the first possible implementation of the third aspect or the third aspect, in the implementation that the third is possible, described processor, for calling the program code stored in described memory, performs following operation:
According to a upper instant video frame of described current instant video frame, at least one details macro block of face in described current instant video frame is predicted.
In conjunction with the third aspect to the third arbitrary possible implementation of the third aspect, in the 4th kind of possible implementation, described processor, for calling the program code stored in described memory, performs following operation:
High frequency filter parameter is set;
High frequency filter is carried out to real human face in described current instant video frame, obtains the filtering figure that described current instant video frame is corresponding.
In conjunction with the third aspect to the 4th kind of arbitrary possible implementation of the third aspect, in the 5th kind of possible implementation, described processor, for calling the program code stored in described memory, performs following operation:
Described detail view and described filtering figure are merged, generates the current instant video frame after merging;
Adjust the luminance parameter of the current instant video frame after described fusion, the current instant video after beautifying described in generation.
In conjunction with the third aspect to the 5th kind of arbitrary possible implementation of the third aspect, in the 6th kind of possible implementation, described processor, for calling the program code stored in described memory, performs following operation:
Described detail view and described filtering figure are merged, generates the current instant video frame after merging;
Adjust at least one in the red channel parameter of the current instant video frame after described fusion, yellow channels parameter and blue channel parameter, the current instant video after beautifying described in generation.
Embodiments providing the method for beautifying faces in a kind of instant video and electronic equipment, comprising: by predicting at least one details macro block of face in current instant video frame, obtaining the detail view that current instant video frame is corresponding; In current instant video frame, real human face carries out filtering, obtains the filtering figure that current instant video frame is corresponding; Detail view and filtering figure are merged, generate the current instant video after beautifying, the current instant video after beautifying at least comprises the face after beautifying.Thus by predicting the details macro block in current instant video frame, and the detail view filtering figure generated after prediction is merged, generate the current instant video after beautifying, improve the efficiency of beautifying faces in instant video, add Consumer's Experience effect.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, below the accompanying drawing used required in describing embodiment is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of interactive system schematic diagram that the embodiment of the present invention provides;
Fig. 2 is a kind of interactive system schematic diagram that the embodiment of the present invention provides;
Fig. 3 is the method for beautifying faces flow chart in a kind of instant video of providing of the embodiment of the present invention;
Fig. 4 is the method for beautifying faces flow chart in a kind of instant video of providing of the embodiment of the present invention;
Fig. 5 is a kind of electronic devices structure schematic diagram that the embodiment of the present invention provides;
Fig. 6 is a kind of electronic devices structure schematic diagram that the embodiment of the present invention provides.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with accompanying drawing, embodiment of the present invention is described further in detail.
Embodiments provide the method for beautifying faces in a kind of instant video, the method is applied to and a kind ofly comprises in the interactive system of at least two mobile terminals and server, this interactive system can with reference to shown in Fig. 1, wherein, mobile terminal 1 is instant video transmit leg, mobile terminal 2 is instant video recipient, and the instant video that mobile terminal 1 sends is forwarded to mobile terminal 2 via server; Wherein, this mobile terminal can be smart mobile phone (Smart Phone), can be panel computer (Tablet Personal Computer), can also be other mobile terminals, the embodiment of the present invention be limited concrete mobile terminal.Mobile terminal at least comprises video input module and video display module, video input module can comprise camera, video display module can comprise display screen, and at least can run an instant video program in mobile terminal, video input module and the video display module of this instant video program control mobile terminal carry out instant video.
Especially, the executive agent of the method that the embodiment of the present invention provides, i.e. electronic equipment, can be any one in mobile terminal 1, mobile terminal 2 and server, if the executive agent of the method is mobile terminal 1, then the face in this instant video is beautified, then the instant video after beautifying is sent to server, be sent to mobile terminal 2 by server again, by the video display module in mobile terminal 2 show this beautify after instant video; If the executive agent of the method is server, then mobile terminal 1 is after the video input module input instant video by self, this instant video is sent to server, by server, the face in instant video is beautified, face after this being beautified again is sent to mobile terminal 2, by the video display module in mobile terminal 2 show this beautify after instant video; If the executive agent of the method is mobile terminal 2, mobile terminal 1 is after the video input module input instant video by self, this instant video is sent to server, this instant video is sent to mobile terminal 2 by server, face in mobile terminal 2 pairs of instant videos beautifies, then by the video display module of self show this beautify after instant video.The concrete executive agent of the embodiment of the present invention to the method in this interactive system is not limited.
In addition, the method that the embodiment of the present invention provides can also be applied to and a kind ofly only include in the interactive system of mobile terminal 1 and mobile terminal 2, this interactive system can with reference to shown in Fig. 2, wherein, mobile terminal 1 is instant video transmit leg, mobile terminal 2 is instant video recipient, and mobile terminal at least comprises video input module and video display module, video input module can comprise camera, video display module can comprise display screen, and at least can run an instant video program in mobile terminal, video input module and the video display module of this instant video program control mobile terminal carry out instant video.
Especially, the executive agent of the method that the embodiment of the present invention provides, i.e. electronic equipment, can be any one in mobile terminal 1 and mobile terminal 2, if the executive agent of the method is mobile terminal 1, then this mobile terminal 1 is after the video input module input instant video by self, beautifies the face in this instant video, then the instant video after beautifying is sent to mobile terminal 2, by the video display module in mobile terminal 2 show this beautify after instant video; If the executive agent of the method is mobile terminal 2, mobile terminal 1 is after the video input module input instant video by self, this instant video is sent to mobile terminal 2, face in mobile terminal 2 pairs of instant videos beautifies, then by the video display module of self show this beautify after instant video.The concrete executive agent of the embodiment of the present invention to the method in this interactive system is not limited.
Embodiment one
Embodiments provide the method for beautifying faces in a kind of instant video, with reference to shown in Fig. 3, the method comprises:
301, by predicting at least one details macro block of face in current instant video frame, the detail view that current instant video frame is corresponding is obtained.
Concrete, according to current instant video frame, at least one details macro block of face in current instant video frame is predicted.
Optionally, according to a upper instant video frame of current instant video frame, at least one details macro block of face in current instant video frame is predicted.
Optionally, before step 301, also comprise:
Current instant video frame is split, obtains multiple macro block;
At least one details macro block is obtained from multiple macro block.
302, filtering is carried out to real human face in current instant video frame, obtain the filtering figure that current instant video frame is corresponding.
Concrete, High frequency filter parameter is set;
High frequency filter is carried out to real human face in current instant video frame, obtains the filtering figure that current instant video frame is corresponding.
303, detail view and filtering figure are merged, generate the current instant video after beautifying, the current instant video after beautifying at least comprises the face after beautifying.
Concrete, detail view and filtering figure are merged, generates the current instant video frame after merging;
The luminance parameter of the current instant video frame after adjustment fusion, generates the current instant video after beautifying.
Optionally,
Detail view and filtering figure are merged, generates the current instant video frame after merging;
Adjust at least one in the red channel parameter of the current instant video frame after merging, yellow channels parameter and blue channel parameter, generate the current instant video after beautifying.
Embodiments provide the method for beautifying faces in a kind of instant video, by predicting the details macro block in current instant video frame, and the detail view filtering figure generated after prediction is merged, generate the current instant video after beautifying, improve the efficiency of beautifying faces in instant video, add Consumer's Experience effect.
Embodiment two
Embodiments provide the method for beautifying faces in a kind of instant video, with reference to shown in Fig. 4, the method comprises:
401, current instant video frame is split, obtain multiple macro block.
Concrete, according to the size of current instant video frame, the size of macro block can be set;
Suppose that current instant video frame is of a size of width*height, then macro block can be set and be of a size of m*n; Wherein, width comprises i m, i is positive integer; It is positive integer that height comprises j n, j;
After completing segmentation, calculate first variance and the second variance of each macro block respectively, wherein, whether first variance is used to indicate macro block is flat site, and whether second variance is used to indicate macro block is details macro block, specifically comprises:
If stdDef
1< δ
1, then indicate macro block to be flat site, otherwise be non-planar regions, wherein stdDef
1represent first variance, δ
1represent the first predetermined threshold value;
If stdDef
2> δ
2, then indicate macro block to be details macro block, otherwise be non-details macro block, wherein, stdDef
2represent second variance, δ
2represent the second predetermined threshold value;
402, carry out filtering from multiple macro block, obtain at least one details macro block.
Concrete, can filter condition be set, according to this filter condition, from multiple macro block, obtains at least one details macro block.Exemplary, this filter condition can be:
r＞δ
3&r-b＞δ
4
Wherein, r and b is respectively parameter preset, δ
3and δ
4for the third party's difference respectively corresponding to macro block and the 4th variance, this third party differs from identical with the acquisition process of second variance with first variance in the acquisition process of the 4th variance and step 401, or else repeated herein, and in actual applications, this third party's difference can be any one in first variance and second variance, also can be other variances; 4th variance also can be any one in first variance and second variance, and can be also other variances, the embodiment of the present invention be limited.
According to this filter condition, the process obtaining at least one details macro block from multiple macro block can be:
Judge whether third party's difference that any one macro block is corresponding and the 4th variance meet this filter condition, be then defined as details macro block respectively, if do not meet, then continue to repeat said process to next macro block.
In addition, can also by other means, from multiple macro block, obtain at least one details macro block, the embodiment of the present invention is not limited.
403, according to current instant video frame, at least one details macro block of face in current instant video frame is predicted, obtains the detail view that current instant video frame is corresponding.
Concrete, the embodiment of the present invention is not limited concrete prediction mode, and after prediction completes, can also judge that whether prediction is successful, this deterministic process can be:
Obtain any one the predict pixel summit in macro block, and around this predict pixel summit, search for other meet pre-conditioned pixel, this is pre-conditioned can be:
| r-r
i| < δ
5, wherein, δ
5be the 5th variance that macro block is corresponding, in actual applications, the 5th variance can be any one in first variance, second variance, third party's difference and the 4th variance, and can be also other variances, the embodiment of the present invention be limited.
If any one pixel of the surrounding on this predict pixel summit meets, this is pre-conditioned, then judge to predict successfully.
Especially, step 403 is by predicting at least one details macro block of face in current instant video frame, obtaining the process of detail view corresponding to current instant video frame, except said process, can also be:
According to a upper instant video frame of current instant video frame, at least one details macro block of face in current instant video frame is predicted.
Concrete, the embodiment of the present invention is not limited concrete prediction mode, and after prediction completes, can also judge that whether prediction is successful, this deterministic process can be:
Obtain any one the predict pixel summit in macro block, and in the frame of video at previous frame place, search for other on this predict pixel summit and meet pre-conditioned pixel, this is pre-conditioned can be:
R-r
i| < δ
6, wherein, δ
6be the 6th variance that macro block is corresponding, in actual applications, the 5th variance can be any one in first variance, second variance, third party's difference and the 4th variance, and can be also other variances, the embodiment of the present invention be limited.
If this predict pixel summit any one pixel in the frame of video at previous frame place meets, this is pre-conditioned, then judge to predict successfully.
After judgement prediction success prediction, the pixel summit before utilizing predict pixel summit to replace it, its process is specially:
Determine that the Hong Qu at this place, survey pixel summit is non-details macro block and non-planar regions, then after judgement is predicted successfully, the pixel summit before replacing it with predict pixel summit
Unsuccessful in judgement prediction, then any one in linear filtering or bilateral filtering is performed to each pixel summit in this frame of video.
By predicting successfully, pixel summit before utilizing predict pixel point to replace it, after prediction is unsuccessful, any one in linear filtering or bilateral filtering is performed to each pixel in this frame of video, the beautifying faces efficiency in instant video can be improved.
404, High frequency filter parameter is set.
Concrete, the embodiment of the present invention is not limited concrete setting up procedure.
405, High frequency filter is carried out to real human face in current instant video frame, obtain the filtering figure that current instant video frame is corresponding.
Concrete, can on the basis of High frequency filter parameter, carry out High frequency filter by arranging filtering condition to real human face in current instant video frame, the embodiment of the present invention is not limited concrete mode.
Especially, step 404 to step 405 carries out filtering to real human face in current instant video frame, obtain the process of filtering figure corresponding to current instant video frame, because the high-frequency signal in vision signal is noise signal, so can by filtering this vision signal high frequency signal, making in the process that the face in instant video is beautified, without the need to processing this high-frequency signal, thus improve the beautifying faces efficiency in instant video.
406, detail view and filtering figure are merged, generate the current instant video frame after merging.
Concrete, by details mask, detail view and filtering figure are merged, this process can be:
According to detail view, generate details mask;
Obtain the average of the variance of each details macro block, then according on the basis of this average, by default details mask formation condition, make details mask, this default details mask formation condition can be:
if|x-mean|＜δ
7；
y＝x-mean
else y＝0
Wherein, mean is the average of this variance, and x is the variance of each details macro block, and y is the variance of each details after process, δ
7the 7th variance that variance for details macro block is corresponding.
Detail view can be superposed with filtering figure, realize the fusion of detail view and filtering figure, in addition, by the fusion formula preset, the fusion of detail view and filtering figure can also be realized, wherein, the embodiment of the present invention is not limited concrete fusion formula, in addition, and can also be by other means, realize the fusion of detail view and filtering figure, the embodiment of the present invention is not limited concrete mode.
The luminance parameter of the current instant video frame 407, after adjustment fusion, generates the current instant video after beautifying.
Concrete, can adjust the luminance parameter of the current instant video frame after fusion according to the ambient brightness in instant video frame, the embodiment of the present invention is not limited concrete process.
The luminance parameter of current instant video frame after being merged by adjustment, reduce face surrounding environment in current instant video frame darker or brighter time, on the impact of face display effect in the current instant video after beautifying, improve Consumer's Experience.
Especially, step 406 to step 407 is merged detail view and filtering figure, and generate the current instant video after beautifying, the current instant video after beautifying at least comprises the process of the face after beautifying, and except said process, can also be:
Detail view and filtering figure are merged, generates the current instant video frame after merging;
Adjust at least one in the red channel parameter of the current instant video frame after merging, yellow channels parameter and blue channel parameter, generate the current instant video after beautifying.
Concrete, can adjust the red channel parameter of the current instant video frame after fusion, yellow channels parameter and blue channel parameter according at least one in the red channel parameter of the environment in instant video frame, yellow channels parameter and blue channel parameter, the embodiment of the present invention is not limited concrete process.
The luminance parameter of current instant video frame after being merged by adjustment, reduce face surrounding environment in current instant video frame darker or brighter time, on the impact of face display effect in the current instant video after beautifying, improve Consumer's Experience.
In actual applications, the luminance parameter of the current instant video frame after fusion, red channel parameter, yellow channels parameter and blue channel parameter can be adjusted simultaneously.
Embodiments provide the method for beautifying faces in a kind of instant video, by predicting the details macro block in current instant video frame, and the detail view filtering figure generated after prediction is merged, generate the current instant video after beautifying, improve the efficiency of beautifying faces in instant video, add Consumer's Experience effect.
Embodiment four
Embodiments provide a kind of electronic equipment 5, with reference to shown in Fig. 5, equipment 5 comprises:
Prediction module 51, for by predicting at least one details macro block of face in current instant video frame, obtains the detail view that current instant video frame is corresponding;
Filtration module 52, for carrying out filtering to real human face in current instant video frame, obtains the filtering figure that current instant video frame is corresponding;
Fusion Module 53, for detail view and filtering figure being merged, generate the current instant video after beautifying, the current instant video after beautifying at least comprises the face after beautifying.
Optionally, equipment also comprises:
Segmentation module, for being split by current instant video frame, obtains multiple macro block;
Filtration module 52 specifically for obtaining at least one details macro block from multiple macro block.
Optionally, prediction module 51 specifically for:
According to current instant video frame, at least one details macro block of face in current instant video frame is predicted.
Optionally, prediction module 51 also specifically for:
According to a upper instant video frame of current instant video frame, at least one details macro block of face in current instant video frame is predicted.
Optionally, equipment also comprises:
Module is set, for arranging High frequency filter parameter;
Filtration module 52 also for carrying out High frequency filter to real human face in current instant video frame, obtains the filtering figure that current instant video frame is corresponding.
Optionally, Fusion Module 53 specifically for:
Detail view and filtering figure are merged, generates the current instant video frame after merging;
The luminance parameter of the current instant video frame after adjustment fusion, generates the current instant video after beautifying.
Optionally, Fusion Module 53 also for:
Detail view and filtering figure are merged, generates the current instant video frame after merging;
Adjust at least one in the red channel parameter of the current instant video frame after merging, yellow channels parameter and blue channel parameter, generate the current instant video after beautifying.
Embodiments provide a kind of electronic equipment, by predicting the details macro block in current instant video frame, and the detail view filtering figure generated after prediction is merged, generate the current instant video after beautifying, improve the efficiency of beautifying faces in instant video, add Consumer's Experience effect.
Embodiment five
Embodiments provide a kind of electronic equipment 6, with reference to shown in Fig. 6, the processor 65 comprising display screen 61, sending module 62, receiver module 63, memory 64 and be connected with display screen 61, sending module 62, receiver module 63, memory 64 respectively, wherein, batch processing code is stored in memory 64, processor 65, for calling the program code stored in memory 64, performs following operation:
By predicting at least one details macro block of face in current instant video frame, obtain the detail view that current instant video frame is corresponding;
Filtering is carried out to real human face in current instant video frame, obtains the filtering figure that current instant video frame is corresponding;
Detail view and filtering figure are merged, generate the current instant video after beautifying, the current instant video after beautifying at least comprises the face after beautifying.
Optionally, processor 65, for calling the program code stored in memory 64, performs following operation:
Current instant video frame is split, obtains multiple macro block;
At least one details macro block is obtained from multiple macro block.
Optionally, processor 65, for calling the program code stored in memory 64, performs following operation:
According to current instant video frame, at least one details macro block of face in current instant video frame is predicted.
Optionally, processor 65, for calling the program code stored in memory 64, performs following operation:
According to a upper instant video frame of current instant video frame, at least one details macro block of face in current instant video frame is predicted.
Optionally, processor 65, for calling the program code stored in memory 64, performs following operation:
High frequency filter parameter is set;
High frequency filter is carried out to real human face in current instant video frame, obtains the filtering figure that current instant video frame is corresponding
Optionally, processor 65, for calling the program code stored in memory 64, performs following operation:
Detail view and filtering figure are merged, generates the current instant video frame after merging;
The luminance parameter of the current instant video frame after adjustment fusion, generates the current instant video after beautifying.
Optionally, processor 65, for calling the program code stored in memory 64, performs following operation:
Detail view and filtering figure are merged, generates the current instant video frame after merging;
Adjust at least one in the red channel parameter of the current instant video frame after merging, yellow channels parameter and blue channel parameter, generate the current instant video after beautifying.
Embodiments provide a kind of electronic equipment, by predicting the details macro block in current instant video frame, and the detail view filtering figure generated after prediction is merged, generate the current instant video after beautifying, improve the efficiency of beautifying faces in instant video, add Consumer's Experience effect.
Embodiment six
Embodiments provide the beautifying faces system in a kind of instant video, this system comprises
Predict device, for by predicting at least one details macro block of face in current instant video frame, obtains the detail view that current instant video frame is corresponding;
Filter apparatus, for carrying out filtering to real human face in current instant video frame, obtains the filtering figure that current instant video frame is corresponding;
Fusion device, for detail view and filtering figure being merged, generate the current instant video after beautifying, the current instant video after beautifying at least comprises the face after beautifying.
Embodiments provide the beautifying faces system in a kind of instant video, by predicting the details macro block in current instant video frame, and the detail view filtering figure generated after prediction is merged, generate the current instant video after beautifying, improve the efficiency of beautifying faces in instant video, add Consumer's Experience effect
It should be noted that: the electronic equipment that above-described embodiment provides is performing the method for beautifying faces in instant video, only be illustrated with the division of above-mentioned each functional module, in practical application, can distribute as required and by above-mentioned functions and be completed by different functional modules, internal structure by device and equipment is divided into different functional modules, to complete all or part of function described above.In addition, the method and apparatus that above-described embodiment provides is executed example and is belonged to same design, and its specific implementation process refers to embodiment of the method, repeats no more here.
The invention described above embodiment sequence number, just to describing, does not represent the quality of embodiment.
One of ordinary skill in the art will appreciate that all or part of step realizing above-described embodiment can have been come by hardware, the hardware that also can carry out instruction relevant by program completes, described program can be stored in a kind of computer-readable recording medium, the above-mentioned storage medium mentioned can be read-only memory, disk or CD etc.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (15)
1. the method for beautifying faces in instant video, is characterized in that, described method comprises:
By predicting at least one details macro block of face in current instant video frame, obtain the detail view that described current instant video frame is corresponding;
Filtering is carried out to real human face in described current instant video frame, obtains the filtering figure that described current instant video frame is corresponding;
Described detail view and described filtering figure are merged, generate beautify after current instant video, described in beautify after current instant video at least comprise the face after beautifying.
2. method according to claim 1, is characterized in that, described by predicting at least one details macro block of face in instant video frame, the detail view obtaining described current instant video frame corresponding comprises:
According to described current instant video frame, at least one details macro block of face in described current instant video frame is predicted.
3. method according to claim 1, is characterized in that, described by predicting at least one details macro block of face in instant video frame, the detail view obtaining described current instant video frame corresponding also comprises:
According to a upper instant video frame of described current instant video frame, at least one details macro block of face in described current instant video frame is predicted.
4. according to the arbitrary described method of claims 1 to 3, it is characterized in that, describedly carry out filtering to real human face in described current instant video frame, the filtering figure obtaining described current instant video frame corresponding comprises:
High frequency filter parameter is set;
High frequency filter is carried out to real human face in described current instant video frame, obtains the filtering figure that described current instant video frame is corresponding.
5. according to the arbitrary described method of Claims 1-4, it is characterized in that, describedly described detail view and described filtering figure are merged, the current instant video after generation beautifies comprises:
Described detail view and described filtering figure are merged, generates the current instant video frame after merging;
Adjust the luminance parameter of the current instant video frame after described fusion, the current instant video after beautifying described in generation.
6. an electronic equipment, is characterized in that, described equipment comprises:
Prediction module, for by predicting at least one details macro block of face in current instant video frame, obtains the detail view that described current instant video frame is corresponding;
Filtration module, for carrying out filtering to real human face in described current instant video frame, obtains the filtering figure that described current instant video frame is corresponding;
Fusion Module, for described detail view and described filtering figure are merged, generate beautify after current instant video, described in beautify after current instant video at least comprise the face after beautifying.
7. equipment according to claim 6, is characterized in that, described prediction module specifically for:
According to described current instant video frame, at least one details macro block of face in described current instant video frame is predicted.
8. equipment according to claim 6, is characterized in that, described prediction module also specifically for:
According to a upper instant video frame of described current instant video frame, at least one details macro block of face in described current instant video frame is predicted.
9., according to the arbitrary described equipment of claim 6 to 8, it is characterized in that, described equipment also comprises:
Module is set, for arranging High frequency filter parameter;
Described filtration module also for carrying out High frequency filter to real human face in described current instant video frame, obtains the filtering figure that described current instant video frame is corresponding.
10., according to the arbitrary described equipment of claim 6 to 9, it is characterized in that, described Fusion Module specifically for:
Described detail view and described filtering figure are merged, generates the current instant video frame after merging;
Adjust the luminance parameter of the current instant video frame after described fusion, the current instant video after beautifying described in generation.
11. 1 kinds of electronic equipments, it is characterized in that, the processor comprising display screen, sending module, receiver module, memory and be connected with described display screen, described sending module, described receiver module, described memory respectively, wherein, batch processing code is stored in described memory, described processor, for calling the program code stored in described memory, performs following operation:
By predicting at least one details macro block of face in current instant video frame, obtain the detail view that described current instant video frame is corresponding;
Filtering is carried out to real human face in described current instant video frame, obtains the filtering figure that described current instant video frame is corresponding;
Described detail view and described filtering figure are merged, generate beautify after current instant video, described in beautify after current instant video at least comprise the face after beautifying.
12. electronic equipments according to right 11, is characterized in that, described processor, for calling the program code stored in described memory, performs following operation:
According to described current instant video frame, at least one details macro block of face in described current instant video frame is predicted.
13. electronic equipments according to right 11, is characterized in that, described processor, for calling the program code stored in described memory, performs following operation:
According to a upper instant video frame of described current instant video frame, at least one details macro block of face in described current instant video frame is predicted.
14., according to the arbitrary described electronic equipment of right 11 to 13, is characterized in that, described processor, for calling the program code stored in described memory, performs following operation:
High frequency filter parameter is set;
High frequency filter is carried out to real human face in described current instant video frame, obtains the filtering figure that described current instant video frame is corresponding.
15., according to the arbitrary described electronic equipment of right 11 to 14, is characterized in that, described processor, for calling the program code stored in described memory, performs following operation:
Described detail view and described filtering figure are merged, generates the current instant video frame after merging;
Adjust the luminance parameter of the current instant video frame after described fusion, the current instant video after beautifying described in generation.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510003501.XA CN104469253A (en) | 2015-01-05 | 2015-01-05 | Face beautification method in real-time video and electronic equipment |
| PCT/CN2015/098357 WO2016110188A1 (en) | 2015-01-05 | 2015-12-23 | Method and electronic device for aesthetic enhancements of face in real-time video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510003501.XA CN104469253A (en) | 2015-01-05 | 2015-01-05 | Face beautification method in real-time video and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104469253A true CN104469253A (en) | 2015-03-25 |
Family
ID=52914532
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510003501.XA Pending CN104469253A (en) | 2015-01-05 | 2015-01-05 | Face beautification method in real-time video and electronic equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN104469253A (en) |
| WO (1) | WO2016110188A1 (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104952036A (en) * | 2015-06-18 | 2015-09-30 | 福州瑞芯微电子有限公司 | Facial beautification method and electronic equipment in real-time video |
| CN104967867A (en) * | 2015-06-19 | 2015-10-07 | 美国掌赢信息科技有限公司 | Instant video coding method and electronic device |
| CN105005441A (en) * | 2015-06-18 | 2015-10-28 | 美国掌赢信息科技有限公司 | Instant video display method and electronic equipment |
| CN105163199A (en) * | 2015-06-19 | 2015-12-16 | 美国掌赢信息科技有限公司 | Real-time video coding method and electronic equipment |
| CN105163198A (en) * | 2015-06-19 | 2015-12-16 | 美国掌赢信息科技有限公司 | Real-time video coding method and electronic equipment |
| CN105611216A (en) * | 2015-12-31 | 2016-05-25 | 北京奇艺世纪科技有限公司 | Facial beautification video call method and device |
| WO2016110188A1 (en) * | 2015-01-05 | 2016-07-14 | 掌赢信息科技（上海）有限公司 | Method and electronic device for aesthetic enhancements of face in real-time video |
| CN105979195A (en) * | 2016-05-26 | 2016-09-28 | 努比亚技术有限公司 | Video image processing apparatus and method |
| WO2016202286A1 (en) * | 2015-06-19 | 2016-12-22 | 美国掌赢信息科技有限公司 | Real-time video transmission method and electronic apparatus |
| CN106358004A (en) * | 2015-07-14 | 2017-01-25 | 腾讯科技（深圳）有限公司 | Video call method and video call device |
| CN108762829A (en) * | 2018-05-03 | 2018-11-06 | 北京奇虎科技有限公司 | A kind of method, client and terminal for image beautification |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112150393B (en) * | 2020-10-12 | 2024-08-13 | 深圳数联天下智能科技有限公司 | Face image peeling method and device, computer equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101778188A (en) * | 2009-01-14 | 2010-07-14 | 华晶科技股份有限公司 | Method for beautifying faces in digital image |
| CN101916370A (en) * | 2010-08-31 | 2010-12-15 | 上海交通大学 | Method for processing non-feature regional images in face detection |
| CN103268475A (en) * | 2013-05-10 | 2013-08-28 | 中科创达软件股份有限公司 | Skin beautifying method based on face and skin color detection |
| US20140369554A1 (en) * | 2013-06-18 | 2014-12-18 | Nvidia Corporation | Face beautification system and method of use thereof |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103607554B (en) * | 2013-10-21 | 2017-10-20 | 易视腾科技股份有限公司 | It is a kind of based on full-automatic face without the image synthesizing method being stitched into |
| CN104574306A (en) * | 2014-12-24 | 2015-04-29 | 掌赢信息科技（上海）有限公司 | Face beautifying method for real-time video and electronic equipment |
| CN104469253A (en) * | 2015-01-05 | 2015-03-25 | 掌赢信息科技（上海）有限公司 | Face beautification method in real-time video and electronic equipment |
-
2015
- 2015-01-05 CN CN201510003501.XA patent/CN104469253A/en active Pending
- 2015-12-23 WO PCT/CN2015/098357 patent/WO2016110188A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101778188A (en) * | 2009-01-14 | 2010-07-14 | 华晶科技股份有限公司 | Method for beautifying faces in digital image |
| CN101916370A (en) * | 2010-08-31 | 2010-12-15 | 上海交通大学 | Method for processing non-feature regional images in face detection |
| CN103268475A (en) * | 2013-05-10 | 2013-08-28 | 中科创达软件股份有限公司 | Skin beautifying method based on face and skin color detection |
| US20140369554A1 (en) * | 2013-06-18 | 2014-12-18 | Nvidia Corporation | Face beautification system and method of use thereof |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016110188A1 (en) * | 2015-01-05 | 2016-07-14 | 掌赢信息科技（上海）有限公司 | Method and electronic device for aesthetic enhancements of face in real-time video |
| CN104952036A (en) * | 2015-06-18 | 2015-09-30 | 福州瑞芯微电子有限公司 | Facial beautification method and electronic equipment in real-time video |
| WO2016202288A1 (en) * | 2015-06-18 | 2016-12-22 | 美国掌赢信息科技有限公司 | Method for displaying real-time video and electronic device |
| CN105005441A (en) * | 2015-06-18 | 2015-10-28 | 美国掌赢信息科技有限公司 | Instant video display method and electronic equipment |
| CN105163198A (en) * | 2015-06-19 | 2015-12-16 | 美国掌赢信息科技有限公司 | Real-time video coding method and electronic equipment |
| CN105163199A (en) * | 2015-06-19 | 2015-12-16 | 美国掌赢信息科技有限公司 | Real-time video coding method and electronic equipment |
| CN104967867A (en) * | 2015-06-19 | 2015-10-07 | 美国掌赢信息科技有限公司 | Instant video coding method and electronic device |
| WO2016202286A1 (en) * | 2015-06-19 | 2016-12-22 | 美国掌赢信息科技有限公司 | Real-time video transmission method and electronic apparatus |
| CN105163198B (en) * | 2015-06-19 | 2019-03-19 | 美国掌赢信息科技有限公司 | A kind of coding method of instant video and electronic equipment |
| CN106358004A (en) * | 2015-07-14 | 2017-01-25 | 腾讯科技（深圳）有限公司 | Video call method and video call device |
| CN105611216A (en) * | 2015-12-31 | 2016-05-25 | 北京奇艺世纪科技有限公司 | Facial beautification video call method and device |
| CN105611216B (en) * | 2015-12-31 | 2018-09-11 | 北京奇艺世纪科技有限公司 | A kind of skin makeup video call method and equipment |
| CN105979195A (en) * | 2016-05-26 | 2016-09-28 | 努比亚技术有限公司 | Video image processing apparatus and method |
| CN105979195B (en) * | 2016-05-26 | 2019-04-19 | 努比亚技术有限公司 | A kind of video image processing device and method |
| CN108762829A (en) * | 2018-05-03 | 2018-11-06 | 北京奇虎科技有限公司 | A kind of method, client and terminal for image beautification |
| CN108762829B (en) * | 2018-05-03 | 2021-07-09 | 北京奇虎科技有限公司 | Method, client and terminal for beautifying image |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2016110188A1 (en) | 2016-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104469253A (en) | Face beautification method in real-time video and electronic equipment | |
| CN104574306A (en) | Face beautifying method for real-time video and electronic equipment | |
| KR101644868B1 (en) | Inter-terminal image sharing method, terminal device, and communications system | |
| CN105005426A (en) | Screenshot method and system for touch screen terminal, and data sharing method and system for touch screen terminal | |
| CN108198146B (en) | Noise reduction method, equipment and computer readable storage medium | |
| CN105049949A (en) | Coding method of instant video and electronic equipment | |
| CN106878631B (en) | Image display method and device | |
| CN103078924A (en) | Visual field sharing method and equipment | |
| CN107623833B (en) | Control method, device and system for video conference | |
| RU2596062C1 (en) | Method for correction of eye image using machine learning and method of machine learning | |
| CN104754221B (en) | A kind of photographic method and mobile terminal | |
| CN109658427A (en) | Image processing method and device | |
| CN105227873B (en) | A kind of test method and device of on-screen display data | |
| CN112037160B (en) | Image processing method, device and equipment | |
| CN105139340A (en) | Method and device for splicing panoramic photos | |
| CN104967917A (en) | Instant video coding method and electronic device | |
| CN105407313A (en) | Video calling method, equipment and system | |
| EP2890124B1 (en) | Coding method and device applied to hevc-based 3dvc | |
| CN104994405A (en) | Instant-video transmission method and electronic equipment | |
| US10791307B2 (en) | Image details processing method, apparatus, terminal, and storage medium | |
| CN112738398B (en) | Image anti-shake method and device and electronic equipment | |
| CN104967867A (en) | Instant video coding method and electronic device | |
| CN105163125A (en) | Real-time video coding method and electronic equipment | |
| CN110941413B (en) | Display screen generation method and related device | |
| JP2016167258A (en) | Method, device and computer program product of reducing chromatic aberration in deconvolution images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150325 |
|
| WD01 | Invention patent application deemed withdrawn after publication |