CN110188711A - Method and apparatus for output information - Google Patents
Method and apparatus for output information Download PDFInfo
- Publication number
- CN110188711A CN110188711A CN201910477387.2A CN201910477387A CN110188711A CN 110188711 A CN110188711 A CN 110188711A CN 201910477387 A CN201910477387 A CN 201910477387A CN 110188711 A CN110188711 A CN 110188711A
- Authority
- CN
- China
- Prior art keywords
- side face
- image
- target
- face
- location information
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
-
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
Abstract
Embodiment of the invention discloses the method and apparatus for output information, and the method and apparatus for handling video.The specific embodiment for being used for the method for output information includes: acquisition target facial image；Based on side face location model trained in advance, generate the side face location information in the side face region in target facial image, wherein, the position in the side face region in image of the side face location model for determining input, side face region includes the corresponding facial pixel of cheekbone, and side face location information includes the location information of the corresponding facial pixel of cheekbone；Export side face location information generated.The embodiment can determine the position of the cheekbone object in face-image, facilitate the processing that the position based on cheekbone object more refines face-image, facilitate the processing mode of abundant face-image.
Description
Technical field
Embodiment of the disclosure is related to field of computer technology, and in particular to for the method and apparatus of output information, with
And the method and apparatus for handling video.
Background technique
In general, the electronic equipments such as computer need to realize by the semantic analysis of image to the identification of image.Image
Semanteme is divided into vision layer, object layer and conceptual level.The bottom that vision layer is generally understood, i.e. color, texture and shape etc.,
It is semantic that these features are all referred to as low-level image feature.Object layer typically includes attributive character etc., for example, indicating certain an object at certain
The state at one moment.Conceptual level is the thing closest to human intelligible that image expression goes out.For example, including someone on an image
Body object (such as face object and non-face object), computer needs to analyze each image-region, to determine the figure
As the position of the face object and non-face object that are included.In the prior art, exist to object (such as the cheekbone in face-image
Bone object) demand that is positioned.
In addition, existing method, is often based on the gesture and movement of user, thin face processing is carried out to facial image
's.
Summary of the invention
The present disclosure proposes the method and apparatus for output information, and the method and apparatus for handling video.
In a first aspect, embodiment of the disclosure provides a kind of method for output information, this method comprises: obtaining mesh
Mark face-image；Based on side face location model trained in advance, the side face position in the side face region in target facial image is generated
Information, wherein the position in the side face region in image of the side face location model for determining input, side face region includes cheekbone pair
The facial pixel answered, side face location information include the location information of the corresponding facial pixel of cheekbone；Export side generated
Face location information.
In some embodiments, this method further include: be based on side face location information generated, to target facial image into
The thin face processing of row, obtains thin face rear face image.
In some embodiments, this method further include: be in using thin face rear face image substitution target facial image
It is existing.
In some embodiments, side face region further includes at least one of following corresponding facial pixel: temple, lower jaw
3 Along ents between 3 Along ents between bone, cheekbone and temple and cheekbone and mandibular；And side face location information further includes side
The location information of the also included facial pixel in face region.
In some embodiments, it is based on side face location information generated, thin face processing is carried out to target facial image, is obtained
To thin face rear face image, comprising: each facial pixel for including by side face region in target facial image to in target
It axis perpendicular and is moved by the directions of close-target central axes, to carry out thin face processing, obtains thin face rear face image；Its
In, target central axes are the point for being used to indicate place between the eyebrows and the straight line being used to indicate where the point of Renzhong acupoint in face-image.
In some embodiments, in each facial pixel moved, about symmetrical two faces of target axis
What pixel was moved is equidistant.
In some embodiments, distance and facial pixel of each facial pixel moved to the movement of target central axes
The distance of point to target central axes is positively correlated.
Second aspect, embodiment of the disclosure provide a kind of method for handling video, work as this method comprises: obtaining
The video of preceding shooting and presentation is as target video；The video frame comprising face object is chosen from target video as target face
Portion's image, and execute following processing step: based on side face location model trained in advance, generate the side in target facial image
The side face location information in face region, wherein the position in the side face region in image of the side face location model for determining input, side
Face region includes the corresponding facial pixel of cheekbone, and side face location information includes the position letter of the corresponding facial pixel of cheekbone
Breath；Based on side face location information generated, thin face processing is carried out to target facial image, obtains thin face rear face image；It adopts
It is presented with thin face rear face image substitution target facial image.
In some embodiments, this method further include: in response in the current non-targeted video of target facial image most
A later frame, using the subsequent facial video frame of target facial image in target video, current as new target facial image,
Based on new target facial image, processing step is continued to execute.
The third aspect, embodiment of the disclosure provide a kind of device for output information, which includes: first to obtain
Unit is taken, is configured to obtain target facial image；Generation unit is configured to based on side face location model trained in advance,
Generate the side face location information in the side face region in target facial image, wherein side face location model is for determining the figure of input
The position in the side face region as in, side face region include the corresponding facial pixel of cheekbone, and side face location information includes cheekbone pair
The location information for the facial pixel answered；Output unit is configured to export side face location information generated.
In some embodiments, device further include: processing unit is configured to believe based on side face position generated
Breath carries out thin face processing to target facial image, obtains thin face rear face image.
In some embodiments, device further include: display unit is configured to substitute mesh using thin face rear face image
Mark face-image is presented.
In some embodiments, side face region further includes at least one of following corresponding facial pixel: temple, lower jaw
3 Along ents between 3 Along ents between bone, cheekbone and temple and cheekbone and mandibular；And side face location information further includes side
The location information of the also included facial pixel in face region.
In some embodiments, processing unit includes: mobile module, is configured to side face region in target facial image
Including each facial pixel moved to perpendicular with target central axes and by close-target central axes directions, to carry out
Thin face processing, obtains thin face rear face image；Wherein, target central axes are the point and use for being used to indicate place between the eyebrows in face-image
Straight line where the point of instruction Renzhong acupoint.
In some embodiments, in each facial pixel moved, about symmetrical two faces of target axis
What pixel was moved is equidistant.
In some embodiments, distance and facial pixel of each facial pixel moved to the movement of target central axes
The distance of point to target central axes is positively correlated.
Fourth aspect, embodiment of the disclosure provide a kind of for handling the device of video, which includes: second to obtain
Unit is taken, is configured to obtain the video of current shooting and presentation as target video；Execution unit is configured to regard from target
The video frame comprising face object is chosen in frequency as target facial image, and executes following processing step: based on instruction in advance
Experienced side face location model generates the side face location information in the side face region in target facial image, wherein side face location model
The position in the side face region in image for determining input, side face region include the corresponding facial pixel of cheekbone, side face position
Confidence breath includes the location information of the corresponding facial pixel of cheekbone；Based on side face location information generated, to target face
Image carries out thin face processing, obtains thin face rear face image；It is in using thin face rear face image substitution target facial image
It is existing.
In some embodiments, device further include: continue to execute unit, be configured in response to current target face
Last frame in the non-targeted video of image, by the subsequent facial video frame of target facial image in target video, current
Processing step is continued to execute based on new target facial image as new target facial image.
5th aspect, embodiment of the disclosure provide a kind of electronic equipment, comprising: one or more processors；Storage
Device is stored thereon with one or more programs, when said one or multiple programs are executed by said one or multiple processors,
So that the one or more processors realize the method as being used for output information in above-mentioned first aspect, alternatively, above-mentioned second party
The method of any embodiment in method in face for handling video.
6th aspect, embodiment of the disclosure provide a kind of computer-readable medium, are stored thereon with computer program,
The method as being used for output information in above-mentioned first aspect is realized when the program is executed by processor, alternatively, above-mentioned second aspect
In method for handling any embodiment in the method for video.
The method and apparatus for output information that embodiment of the disclosure provides, and method for handling video with
Then device, based on side face location model trained in advance, is generated in target facial image by obtaining target facial image
Side face region side face location information, wherein side face location model for determine input image in side face region position
It sets, side face region includes the corresponding facial pixel of cheekbone, and side face location information includes the position of the corresponding facial pixel of cheekbone
Confidence breath, finally, exporting side face location information generated, defines the position of the cheekbone object in face-image as a result,
Facilitate the processing that the position based on cheekbone object more refines face-image, facilitates the place of abundant face-image
Reason mode.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the disclosure is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that one embodiment of the disclosure can be applied to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the method for output information of the disclosure；
Fig. 3 is the schematic diagram according to an application scenarios of the method for output information of the disclosure；
Fig. 4 is the flow chart according to another embodiment of the method for output information of the disclosure；
Fig. 5 is the flow chart according to one embodiment of the method for handling video of the disclosure；
Fig. 6 is the structural schematic diagram according to one embodiment of the device for output information of the disclosure；
Fig. 7 is the structural schematic diagram according to one embodiment of the device for handling video of the disclosure；
Fig. 8 is adapted for the structural schematic diagram for the computer system for realizing the electronic equipment of embodiment of the disclosure.
Specific embodiment
The disclosure is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the disclosure can phase
Mutually combination.The disclosure is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can the method for output information using embodiment of the disclosure or the dress for output information
It sets, alternatively, the exemplary system architecture 100 for handling the method for video or the embodiment of the device for handling video.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
Send data (such as face-image) etc..Various client applications, such as video can be installed on terminal device 101,102,103
Playout software, the application of Domestic News class, image processing class application, web browser applications, shopping class application, searching class application,
Instant messaging tools, mailbox client, social platform software etc..
Terminal device 101,102,103 can be hardware, be also possible to software.When terminal device 101,102,103 is hard
When part, it can be various electronic equipments, including but not limited to smart phone, tablet computer, E-book reader, MP3 player
(Moving Picture Experts Group Audio Layer III, dynamic image expert's compression standard audio level 3),
MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image expert's compression standard audio level
4) player, pocket computer on knee and desktop computer etc..It, can be with when terminal device 101,102,103 is software
It is mounted in above-mentioned cited electronic equipment.Multiple softwares or software module may be implemented into (such as providing distribution in it
The software or software module of formula service), single software or software module also may be implemented into.It is not specifically limited herein.
Server 105 can be to provide the server of various services, such as to being obtained from terminal device 101,102,103
The background server that face-image is handled.Background server can be to face-image (such as the target face figure got
Picture) etc. data analyze etc. processing (such as the side face location information for determining the side face region in face-image), handled
As a result (such as side face location information) and output.As an example, server 105 can be cloud server, it is also possible to physics
Server.
It should be noted that server can be hardware, it is also possible to software.When server is hardware, may be implemented
At the distributed server cluster that multiple servers form, individual server also may be implemented into.It, can when server is software
To be implemented as multiple softwares or software module (such as providing the software of Distributed Services or software module), also may be implemented
At single software or software module.It is not specifically limited herein.
It should also be noted that, the method provided by embodiment of the disclosure for output information can be held by server
Row, can also be executed, can also be fitted to each other execution by server and terminal device by terminal device.Correspondingly, for exporting
The various pieces (such as each unit, subelement, module, submodule) that the device of information includes can all be set to server
In, it can also all be set in terminal device, can also be respectively arranged in server and terminal device.In addition, the disclosure
Embodiment provided by can be executed by server for the method that handles video, can also be executed by terminal device, may be used also
To be fitted to each other execution by server and terminal device.Various pieces that correspondingly, the device for exporting video includes (such as
Each unit, subelement, module, submodule) it can all be set in server, it can also all be set to terminal device
In, it can also be respectively arranged in server and terminal device.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.For example, when being used for the operation of output information method thereon
Electronic equipment during executing this method, when not needing to carry out data transmission with other electronic equipments, the system architecture
It can only include electronic equipment (such as server or terminal device) thereon for the operation of output information method.
With continued reference to Fig. 2, the process of one embodiment of the method for output information according to the disclosure is shown
200.This is used for the method for output information, comprising the following steps:
Step 201, target facial image is obtained.
In the present embodiment, for the executing subject of the method for output information, (such as server shown in FIG. 1 or terminal are set
It is standby) target facial image can be obtained from other electronic equipments or locally by wired connection mode or radio connection.
Wherein, target facial image can be any face figure of the side face location information in side face region therein to be determined
Picture.The target facial image can be facial image, be also possible to the image of the face of animal.
Herein, technical staff can carry out the specific location in sets itself side face region according to actual needs.For example, side
Face region can be light is irradiated at left and right sides of the face of people after, facial area that light is irradiated to.Example again
Such as, side face region is also possible to characterize temporal point, the point for characterizing cheekbone, the point for characterizing mandibular, characterization in face-image
The quadrilateral area that the point in Tinggong cave is constituted.
Side face location information can be the information for characterizing the position in side face region in face-image.
Step 202, based on side face location model trained in advance, the side face in the side face region in target facial image is generated
Location information.
In the present embodiment, based on side face location model trained in advance, target face is can be generated in above-mentioned executing subject
The side face location information in the side face region in image.Wherein, the side face area in image of the side face location model for determining input
The position in domain.Side face region includes the corresponding facial pixel of cheekbone, and side face location information includes the corresponding facial pixel of cheekbone
The location information of point.Side face location information can serve to indicate that the position in side face region in face-image.Here, cheekbone is corresponding
Facial pixel can be a facial pixel, be also possible to multiple facial pixels.
It should be noted that cheekbone object described in some embodiments of the present disclosure means the corresponding facial picture of cheekbone
Vegetarian refreshments.
Herein, above-mentioned side face location model can be the convolutional neural networks mould obtained using machine learning algorithm training
Type, being also possible to associated storage has the bivariate table or database of side face location information in side face region in image and image.Cheekbone
The corresponding facial pixel of bone can be the image of the cheekbone lateral cutaneous high spot in target facial image.It should be understood that cheekbone
The corresponding facial pixel of bone should be located on the target skin in face-image, and on the image of the cheekbone in non-skin.It is practical
On, due to blocking for target skin, the image of cheekbone is often sightless in face-image.It is right that target skin can be face
As the image of middle skin.In addition, facial pixel described in embodiment of the disclosure should all be located at the skin in face-image
On skin object.
As an example, above-mentioned executing subject can execute in the following way the step 202:
Target facial image is input in side face location model, the side face in the side face region in target facial image is obtained
Location information.Wherein, in this example, the position in the side face region in face-image of the side face location model for determining input
It sets.The side face location model can be using machine learning algorithm, based on including the side face region in face-image and image
The obtained convolutional neural networks model of training sample training of side face location information, be also possible to associated storage have face-image and
The bivariate table or database of the side face location information in the side face region in image.
As another example, above-mentioned executing subject can also execute in the following way the step 202:
Firstly, extracting in target facial image eyebrow object to the image-region between chin object.Wherein, eyebrow object
It can be the image of the eyebrow on face-image.Chin object can be the image of the chin on face-image.
Herein, above-mentioned executing subject can adopt in various manners to extract in face-image eyebrow object to chin object
Between image-region.For example, eyebrow object part below in face-image is determined as in face-image eyebrow object extremely
Image-region between chin object.For another example target facial image to be input to extraction model trained in advance, face is obtained
Eyebrow object is to the image-region between chin object in image.Here, extracting model can be used for extracting the face figure of input
Eyebrow object as in is to the image-region between chin object.Illustratively, extraction model can be is calculated using machine learning
The convolutional neural networks that method training obtains.
Then, extracted image-region is input in side face location model, is obtained in extracted image-region
The side face location information in side face region.Wherein, in this example, side face location model is for determining eyebrow object to chin object
Between image-region in side face region position.The side face location model can be using machine learning algorithm, based on packet
The training of the side face location information in side face region of the object containing eyebrow into the image-region and image-region between chin object
The convolutional neural networks model that sample training obtains, being also possible to associated storage has eyebrow object to the image between chin object
The bivariate table or database of the side face location information in the side face region in region and image-region.
Finally, the side face location information based on the side face region in extracted image-region, determines target facial image
In side face region side face location information.
It is appreciated that since extracted image-region extracts from target facial image, thus can be based on extracted
The side face location information in the side face region in image-region determines the side face position letter in the side face region in target facial image
Breath, details are not described herein.
It is appreciated that due to that may include more useless information (such as target facial image in target facial image
In other pixels in addition to side face region), thus, using it is in this example, first extracted from face-image including
The mode of the image-region in side face region, it is possible to reduce above-mentioned executing subject uses the calculating consumed during side face location model
Resource.
In some optional implementations of the present embodiment, side face region further includes at least one of following corresponding face
Pixel: 3 Along ents between 3 Along ents between temple, mandibular, cheekbone and temple and cheekbone and mandibular；And side
Face location information further includes the location information of the also included facial pixel in side face region.Here, above-mentioned each single item can correspond to
One facial pixel can also correspond to multiple facial pixels.
It is appreciated that the quantity of facial pixel included by usual side face location information is more, then may be implemented more
Accurately to the positioning in the side face region in face-image.The image procossing more refined is helped to realize as a result, (after such as
Continue thin face processing).
Step 203, side face location information generated is exported.
In the present embodiment, above-mentioned executing subject can export side face location information generated.
Herein, above-mentioned executing subject can send side face position generated to the electronic equipment for communicating with connection and believe
Breath can also be shown in local display using by side face location information generated to export the side face location information
Mode exports the side face location information.
In some optional implementations of the present embodiment, following steps are can also be performed in above-mentioned executing subject: being based on
Side face location information generated carries out thin face processing to target facial image, obtains thin face rear face image.
As an example, above-mentioned executing subject can be based on GPUImage, in the side face region of side face location information instruction
Each pixel carry out the variation of coordinate and color, the thin face of target facial image is handled to realize, after obtaining thin face
Face-image.Wherein, GPUImage is the processing frame of the image or video based on graphics processing unit of an open source.
In some optional implementations of the present embodiment, following steps are can also be performed in above-mentioned executing subject: being used
Thin face rear face image substitution target facial image is presented.
Herein, before thin face rear face image is presented in above-mentioned executing subject, which can present target
Face-image, can also be with not shown target facial image.The present embodiment is not construed as limiting this.
It should be understood that this optional implementation can be in using thin face rear face image substitution target facial image
It is existing, the presentation mode of image is enriched as a result,.
With continued reference to the signal that Fig. 3, Fig. 3 are according to the application scenarios of the method for output information of the present embodiment
Figure.In the application scenarios of Fig. 3, server 301 obtains target facial image 3011 first.Then, server 301 is based on preparatory
Trained side face location model 3012 generates the side face location information 3013 in the side face region in target facial image 3011.Its
In, the position in the side face region in image of the side face location model for determining input, side face region includes the corresponding face of cheekbone
Portion's pixel, side face location information include the location information of the corresponding facial pixel of cheekbone.Finally, server 301 exports institute
(in diagram, server 301 has sent generated the side face location information of generation to the terminal device 302 for communicating with connection
Side face location information.Wherein, side face location information includes the location information 3013,3014) of the corresponding facial pixel of cheekbone.
The method provided by the above embodiment for output information of the disclosure, by obtaining target facial image, then,
Based on side face location model trained in advance, the side face location information in the side face region in target facial image is generated, wherein side
The position in the side face region in image of the face location model for determining input, side face region include the corresponding facial pixel of cheekbone
Point, side face location information include the location information of the corresponding facial pixel of cheekbone, finally, exporting side face position letter generated
Breath, defines the position of the cheekbone object in face-image as a result, facilitates the position based on cheekbone object to face-image
The processing more refined facilitates the processing mode of abundant face-image.
With further reference to Fig. 4, it illustrates the processes 400 of another embodiment of the method for output information.The use
In the process 400 of the method for output information, comprising the following steps:
Step 401, target facial image is obtained.
In the present embodiment, step 401 and the step 201 in Fig. 2 corresponding embodiment are almost the same, and which is not described herein again.
Step 402, based on side face location model trained in advance, the side face in the side face region in target facial image is generated
Location information.
In the present embodiment, step 402 and the step 202 in Fig. 2 corresponding embodiment are almost the same, and which is not described herein again.
Step 403, side face location information generated is exported.
In the present embodiment, step 403 and the step 203 in Fig. 2 corresponding embodiment are almost the same, and which is not described herein again.
Step 404, each facial pixel for including by side face region in target facial image to target central axes phase
Vertical and by close-target central axes directions are moved, and to carry out thin face processing, obtain thin face rear face image.
In the present embodiment, for the executing subject of the method for output information, (such as server shown in FIG. 1 or terminal are set
It is standby) side face region includes in the target facial image that can will get in step 401 each facial pixel to target
The perpendicular and direction by close-target central axes in central axes is moved, and to carry out thin face processing, obtains thin face rear face image.
Wherein, target central axes are the point for being used to indicate place between the eyebrows in face-image and the straight line being used to indicate where the point of Renzhong acupoint.
It is appreciated that above-mentioned executing subject does not need to determine each facial pixel during executing the step 404
Mobile distance, and need to only pay close attention to the displacement of the movement of each facial pixel.As long as the moving displacement instruction of facial pixel
The face pixel to perpendicular with target central axes and moved by the directions of close-target central axes, no matter facial pixel
Movement routine be straight line, curve or broken line, should belong to the present embodiment it is claimed within the scope of.
It should be understood that during carrying out thin face processing, in addition to being moved to facial pixel, above-mentioned execution master
Body usually also needs to carry out liquefaction processing, to determine the position of the face contour in face-image；In addition, above-mentioned executing subject
Usually also need in face-image face object carry out anamorphose (such as protect similar image transformation and/or local scale
Adjustment transformation) processing, to avoid the excessive deformation of face object in face-image, and reduces image septum reset object after thin face
Including pixel quantity；In addition, above-mentioned executing subject usually also needs to carry out interpolation processing to face-image, moved with filling up
The position of missing pixel point after dynamic.In practice, above-mentioned treatment effect (including the movement of facial pixel, liquefaction processing, image become
Shape, interpolation processing), it can be used the image array of target facial image and predetermined one or more matrix multiples
Mode is realized.It should be understood that above-mentioned predetermined one or more matrixes can be used to implement target facial image to thin face
The mapping of rear face image.
As an example, the moving distance of each facial pixel moved can be predetermined distance value, it can also
With the numerical value in the predetermined distance range that is randomly generated.
In some optional implementations of the present embodiment, in each facial pixel for being moved, about in target
What the facial pixel of two of axisymmetrical was moved is equidistant.
It is appreciated that since face organ has symmetry, thus, in each facial pixel moved, about
Symmetrical two facial pixels of target axis moved when being equidistant, obtained thin face rear face image still has
There is symmetry.Thus, relative to the unequal side of distance moved about target axis symmetrical two facial pixels
Case, this optional implementation can carry out more accurate thin face to target facial image and handle.
In some optional implementations of the present embodiment, each facial pixel moved is moved to target central axes
Dynamic distance is positively correlated at a distance from pixel to target central axes.
It is appreciated that the remoter pixel in target central axes usually requires mobile bigger distance due in side face region,
Just be able to achieve better thin face effect, thus, when each facial pixel moved to the mobile distance in target central axes with
When the distance of facial pixel to target central axes is positively correlated, relative to each facial pixel moved to target central axes
Mobile distance non-positively related scheme at a distance from pixel to target central axes, this optional implementation can be to target
Face-image carries out more accurate thin face processing, reaches better thin face effect.
It should be noted that the present embodiment can also include embodiment corresponding with Fig. 2 in addition to documented content above
Same or similar feature, effect, details are not described herein.
Figure 4, it is seen that the method for output information compared with the corresponding embodiment of Fig. 2, in the present embodiment
Process 400 highlight to target facial image carry out thin face processing the step of.The scheme of the present embodiment description can be with base as a result,
The thin face processing of face-image is realized in side face location information generated, thus enriches the processing mode of image.
With continued reference to Fig. 5, the process of one embodiment of the method for handling video according to the disclosure is shown
500.The method for being used to handle video, comprising the following steps:
Step 501, the video of current shooting and presentation is obtained as target video.Later, step 502 is executed.
It in the present embodiment, can be with for handling the executing subject (such as terminal device shown in FIG. 1) of the method for video
The video of the image acquiring device current shooting, above-mentioned executing subject are obtained from local image acquiring device (such as camera)
The video of the image acquiring device current shooting can be presented using local picture production device (such as display screen).At this
In, above-mentioned target video is the shooting of present image acquisition device and the video that picture production device is presented.
Wherein, above-mentioned target video can be various videos.For example, target video can be the face to people or animal
Video obtained from being shot.
It is appreciated that when the video obtained from target video is shot to the face of people, it is complete in target video
Portion or partial video frame may include the face object of people.Herein, face object can be the people's presented in video frame
The image of face.
It should be understood that the video frame in video (including above-mentioned target video) is image.
Step 502, the video frame comprising face object is chosen from target video as target facial image.Later, it holds
Row step 503.
In the present embodiment, above-mentioned executing subject can be chosen from the target video that step 501 is got comprising face
The video frame of object is as target facial image.
Herein, above-mentioned executing subject can choose the video frame comprising face object in target video, currently presented
As target facial image, can also choose in target video, current video to be presented and not shown, comprising face object
Frame is as target facial image.
Step 503, based on side face location model trained in advance, the side face in the side face region in target facial image is generated
Location information.Later, step 504 is executed.
In the present embodiment, above-mentioned executing subject can generate target face based on side face location model trained in advance
The side face location information in the side face region in image.Wherein, the side face area in image of the side face location model for determining input
The position in domain, side face region include the corresponding facial pixel of cheekbone, and side face location information includes the corresponding facial pixel of cheekbone
The location information of point.
In the present embodiment, step 503 and the step 202 in Fig. 2 corresponding embodiment are almost the same, and which is not described herein again.
Step 504, it is based on side face location information generated, thin face processing is carried out to target facial image, obtains thin face
Rear face image.Later, step 505 is executed.
In the present embodiment, above-mentioned executing subject can be based on side face location information generated, to target facial image
Thin face processing is carried out, thin face rear face image is obtained.
As an example, above-mentioned executing subject can be based on GPUImage, in the side face region of side face location information instruction
Each pixel carry out the change of coordinate and color, the thin face of target facial image is handled to realize, after obtaining thin face
Face-image.Wherein, GPUImage is the processing frame of the image or video based on graphics processing unit of an open source.
In some optional implementations of the present embodiment, above-mentioned executing subject can also execute this in the following way
Step 504:
By each facial pixel that side face region in target facial image includes to perpendicular with target central axes and lean on
The direction of close-target central axes is moved, and to carry out thin face processing, obtains thin face rear face image.Wherein, target central axes
For in face-image the point for being used to indicate place between the eyebrows and the straight line that is used to indicate where the point of Renzhong acupoint.
Herein, above-mentioned object region can be the image-region including facial pixel.The object region
It can be the image-region obtained after liquefying to each facial pixel that side face region includes, be also possible to facial picture
Centered on vegetarian refreshments, based on the image-region that preset algorithm obtains, for example, being half with pre-determined distance using facial pixel as the center of circle
The circular image-region of diameter.
It should be understood that during mobile pixel, in the face contour of the face object in target facial image
Pixel is often both needed to be moved, hereby it is achieved that the thin face to target facial image is handled.
As an example, the moving distance of each facial pixel moved can be predetermined distance value, it can also
With the numerical value in the predetermined distance range that is randomly generated.
In some optional implementations of the present embodiment, in each facial pixel for being moved, about in target
What the facial pixel of two of axisymmetrical was moved is equidistant.
It is appreciated that since face organ has symmetry, thus, in each facial pixel moved, about
Symmetrical two facial pixels of target axis moved when being equidistant, obtained thin face rear face image still has
There is symmetry.Thus, relative to the unequal side of distance moved about target axis symmetrical two facial pixels
Case, this optional implementation can carry out more accurate thin face to target facial image and handle.
In some optional implementations of the present embodiment, each facial pixel moved is moved to target central axes
Dynamic distance is positively correlated at a distance from facial pixel to target central axes.
It is appreciated that the remoter pixel in target central axes usually requires mobile bigger distance due in side face region,
Just be able to achieve better thin face effect, thus, when each facial pixel moved to the mobile distance in target central axes with
When the distance of facial pixel to target central axes is positively correlated, relative to each facial pixel moved to target central axes
Mobile distance non-positively related scheme at a distance from facial pixel to target central axes, this optional implementation can be right
Target facial image carries out more accurate thin face processing, reaches better thin face effect.
Step 505, it is presented using thin face rear face image substitution target facial image.
In the present embodiment, above-mentioned executing subject can be in using thin face rear face image substitution target facial image
It is existing.
Herein, before thin face rear face image is presented in above-mentioned executing subject, which can present target
Face-image, can also be with not shown target facial image.The present embodiment is not construed as limiting this.
It should be understood that above-mentioned executing subject can shoot video by the video capture device being mounted thereon in real time
And it presents.Due to above-mentioned executing subject obtain video between presentation video there are the regular hour, also, above-mentioned execution
Main body obtains video, and to executing between the completion step 505, there is also the regular hours.Therefore, at above-mentioned executing subject presentation
After reason before image, which can present target facial image, can also be with not shown target facial image.In addition,
Technical staff or user can also carry out sets itself whether before thin face rear face image is presented according to actual needs, to mesh
Mark face-image is presented.
In some optional implementations of the present embodiment, after executing above-mentioned steps 505, above-mentioned executing subject is also
Following steps 506 can be executed: determining whether current target facial image is last frame in target video.If it is not, then
Execute following steps 507: using the subsequent facial video frame of target facial image in target video, current as new target
Face-image continues to execute above-mentioned steps 503- step 505 based on new target facial image.
Herein, the subsequent facial video frame of above-mentioned target facial image can be the next frame face of target facial image
Video frame is also possible to target facial image interval predetermined quantity (such as 1,2) pattern portion video frame and positioned at target face
Facial video frame after image.
The method provided by the above embodiment for handling video of the disclosure, by the view for obtaining current shooting and presentation
Frequency is used as target video, then, the video frame comprising face object is chosen from target video as target facial image, and
It executes following processing step: based on side face location model trained in advance, generating the side in the side face region in target facial image
Face location information, wherein the position in the side face region in image of the side face location model for determining input, side face region includes
The corresponding facial pixel of cheekbone, side face location information include the location information of the corresponding facial pixel of cheekbone；Based on giving birth to
At side face location information, thin face processing is carried out to target facial image, obtains thin face rear face image；Using thin face rear face
Image substitution target facial image is presented, hereby it is achieved that scheming to the face for including in the video of current shooting and presentation
The real-time thin face processing of picture, and presented using the face-image substitution target facial image after thin face to user, thus,
Enrich the mode of processing and the presentation of video.
With further reference to Fig. 6, as the realization to method shown in above-mentioned Fig. 2, present disclose provides one kind for exporting letter
One embodiment of the device of breath, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, except following documented special
Sign is outer, which can also include feature identical or corresponding with embodiment of the method shown in Fig. 2, and generates and scheme
Embodiment of the method shown in 2 is identical or corresponding effect.The device specifically can be applied in various electronic equipments.
As shown in fig. 6, the device 600 for output information of the present embodiment includes: first acquisition unit 601, it is configured
At acquisition target facial image；Generation unit 602 is configured to generate target face based on side face location model trained in advance
The side face location information in the side face region in portion's image, wherein the side face in image of the side face location model for determining input
The position in region, side face region include the corresponding facial pixel of cheekbone, and side face location information includes the corresponding facial picture of cheekbone
The location information of vegetarian refreshments；Output unit 603 is configured to export side face location information generated.
It in the present embodiment, can be by wired connection side for the first acquisition unit 601 of the device of output information 600
Formula or radio connection obtain target facial image from other electronic equipments or locally.Wherein, target facial image can be with
It is any face-image of the side face location information in side face region therein to be determined.The target facial image can be face figure
Picture is also possible to the face-image of animal.Side face location information can be the position for characterizing side face region in face-image
Information.
In the present embodiment, above-mentioned generation unit 602 can generate target face based on side face location model trained in advance
The side face location information in the side face region in portion's image.Wherein, the side face in image of the side face location model for determining input
The position in region.Side face region includes the corresponding facial pixel of cheekbone, and side face location information includes the corresponding facial picture of cheekbone
The location information of vegetarian refreshments.Side face location information can serve to indicate that the position in side face region in face-image.
In the present embodiment, above-mentioned output unit 603 can export side face location information generated.
In some optional implementations of the present embodiment, the device 600 further include: processing unit (not shown)
It is configured to based on side face location information generated, thin face processing is carried out to target facial image, obtains thin face rear face figure
Picture.
In some optional implementations of the present embodiment, the device 600 further include: display unit (not shown)
It is configured to be presented using thin face rear face image substitution target facial image.
In some optional implementations of the present embodiment, side face region further includes at least one of following corresponding face
Pixel: 3 Along ents between 3 Along ents between temple, mandibular, cheekbone and temple and cheekbone and mandibular；And side
Face location information further includes the location information of the also included facial pixel in side face region.
In some optional implementations of the present embodiment, processing unit includes: mobile module (not shown) quilt
The each facial pixel for being configured to include by side face region in target facial image is to perpendicular and close with target central axes
The direction of target central axes is moved, and to carry out thin face processing, obtains thin face rear face image.Wherein, target central axes are
The point for being used to indicate place between the eyebrows in face-image and the straight line being used to indicate where the point of Renzhong acupoint.
In some optional implementations of the present embodiment, in each facial pixel for being moved, about in target
What the facial pixel of two of axisymmetrical was moved is equidistant.
In some optional implementations of the present embodiment, each facial pixel moved is moved to target central axes
Dynamic distance is positively correlated at a distance from facial pixel to target central axes.
The device provided by the above embodiment for output information of the disclosure obtains mesh by first acquisition unit 601
Face-image is marked, then, generation unit 602 generates the side in target facial image based on side face location model trained in advance
The side face location information in face region, wherein the position in the side face region in image of the side face location model for determining input, side
Face region includes the corresponding facial pixel of cheekbone, and side face location information includes the position letter of the corresponding facial pixel of cheekbone
Breath, finally, output unit 603 exports side face location information generated, defines the cheekbone object in face-image as a result,
Position, facilitate the processing that the position based on cheekbone object more refines face-image, facilitate abundant face
The processing mode of image.
With further reference to Fig. 7, as the realization to method shown in above-mentioned Fig. 5, present disclose provides one kind for handling view
One embodiment of the device of frequency, the Installation practice is corresponding with embodiment of the method shown in fig. 5, except following documented special
Sign is outer, which can also include feature identical or corresponding with embodiment of the method shown in fig. 5, and generates and scheme
Embodiment of the method shown in 5 is identical or corresponding effect.The device specifically can be applied in various electronic equipments.
As shown in fig. 7, the present embodiment includes: second acquisition unit 701 for handling the device 700 of video, it is configured
At acquisition current shooting and the video of presentation as target video；Execution unit 702 is configured to choose packet from target video
Video frame containing face object is as target facial image, and executes following processing step: fixed based on side face trained in advance
Bit model generates the side face location information in the side face region in target facial image, wherein side face location model is defeated for determining
The position in the side face region in the image entered, side face region include the corresponding facial pixel of cheekbone, and side face location information includes
The location information of the corresponding facial pixel of cheekbone；Based on side face location information generated, target facial image is carried out thin
Face processing, obtains thin face rear face image；It is presented using thin face rear face image substitution target facial image.
It in the present embodiment, can be by wired connection side for the second acquisition unit 701 of the device of output information 700
Formula or radio connection obtain target facial image from other electronic equipments or locally.Wherein, target facial image can be with
It is any face-image of the side face location information in side face region therein to be determined.The target facial image can be face figure
Picture is also possible to the face-image of animal.
In the present embodiment, above-mentioned execution unit 702 can choose the video frame comprising face object from target video
As target facial image, and execute following processing step: firstly, generating mesh based on side face location model trained in advance
Mark the side face location information in the side face region in face-image, wherein in image of the side face location model for determining input
The position in side face region, side face region include the corresponding facial pixel of cheekbone, and side face location information includes the corresponding face of cheekbone
The location information of portion's pixel.Then, it is based on side face location information generated, thin face processing is carried out to target facial image,
Obtain thin face rear face image.Finally, being presented using thin face rear face image substitution target facial image.
In some optional implementations of the present embodiment, the device 700 further include: continue to execute unit (in figure not
Show) be configured in response to the last frame in the non-targeted video of current target facial image, by it is in target video, when
The subsequent facial video frame of preceding target facial image is as new target facial image, based on new target facial image, after
It is continuous to execute processing step.
The device provided by the above embodiment for being used to handle video of the disclosure, is worked as by the acquisition of second acquisition unit 701
The video of preceding shooting and presentation is as target video, and then, execution unit 702 is chosen from target video comprising face object
Video frame is as target facial image, and executes following processing step: based on side face location model trained in advance, generating mesh
Mark the side face location information in the side face region in face-image, wherein in image of the side face location model for determining input
The position in side face region, side face region include the corresponding facial pixel of cheekbone, and side face location information includes the corresponding face of cheekbone
The location information of portion's pixel；Based on side face location information generated, thin face processing is carried out to target facial image, is obtained thin
Face rear face image；It is presented using thin face rear face image substitution target facial image, hereby it is achieved that current shooting
And the real-time thin face processing for the face-image in the video presented including, and target face is substituted using the face-image after thin face
Portion's image is presented to user, thus, enrich the mode of processing and the presentation of video.
Below with reference to Fig. 8, it illustrates the electronic equipment that is suitable for being used to realize embodiment of the disclosure, (example is as shown in figure 1
Server or terminal device) 800 structural schematic diagram.Terminal device in embodiment of the disclosure can include but is not limited to all
As mobile phone, laptop, digit broadcasting receiver, PDA (personal digital assistant), PAD (tablet computer), PMP are (portable
Formula multimedia player), the mobile terminal and such as number TV, desk-top meter of car-mounted terminal (such as vehicle mounted guidance terminal) etc.
The fixed terminal of calculation machine etc..Terminal device/server shown in Fig. 8 is only an example, should not be to the implementation of the disclosure
The function and use scope of example bring any restrictions.
As shown in figure 8, electronic equipment 800 may include processing unit (such as central processing unit, graphics processor etc.)
801, random access can be loaded into according to the program being stored in read-only memory (ROM) 802 or from storage device 808
Program in memory (RAM) 803 and execute various movements appropriate and processing.In RAM 803, it is also stored with electronic equipment
Various programs and data needed for 800 operations.Processing unit 801, ROM 802 and RAM803 are connected with each other by bus 804.
Input/output (I/O) interface 805 is also connected to bus 804.
In general, following device can connect to I/O interface 805: including such as touch screen, touch tablet, keyboard, mouse, taking the photograph
As the input unit 806 of head, microphone, accelerometer, gyroscope etc.；Including such as liquid crystal display (LCD), loudspeaker, vibration
The output device 807 of dynamic device etc.；Storage device 808 including such as tape, hard disk etc.；And communication device 809.Communication device
809, which can permit electronic equipment 800, is wirelessly or non-wirelessly communicated with other equipment to exchange data.Although Fig. 8 shows tool
There is the electronic equipment 800 of various devices, it should be understood that being not required for implementing or having all devices shown.It can be with
Alternatively implement or have more or fewer devices.Each box shown in Fig. 8 can represent a device, can also root
According to needing to represent multiple devices.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communication device 809, or from storage device 808
It is mounted, or is mounted from ROM802.When the computer program is executed by processing unit 801, the implementation of the disclosure is executed
The above-mentioned function of being limited in the method for example.
It is situated between it should be noted that computer-readable medium described in embodiment of the disclosure can be computer-readable signal
Matter or computer readable storage medium either the two any combination.Computer readable storage medium for example can be with
System, device or the device of --- but being not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or it is any more than
Combination.The more specific example of computer readable storage medium can include but is not limited to: have one or more conducting wires
Electrical connection, portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type are programmable
Read-only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic are deposited
Memory device or above-mentioned any appropriate combination.In embodiment of the disclosure, computer readable storage medium, which can be, appoints
What include or the tangible medium of storage program that the program can be commanded execution system, device or device use or and its
It is used in combination.And in embodiment of the disclosure, computer-readable signal media may include in a base band or as carrier wave
The data-signal that a part is propagated, wherein carrying computer-readable program code.The data-signal of this propagation can be adopted
With diversified forms, including but not limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal is situated between
Matter can also be any computer-readable medium other than computer readable storage medium, which can be with
It sends, propagate or transmits for by the use of instruction execution system, device or device or program in connection.Meter
The program code for including on calculation machine readable medium can transmit with any suitable medium, including but not limited to: electric wire, optical cable,
RF (radio frequency) etc. or above-mentioned any appropriate combination.
Above-mentioned computer-readable medium can be included in above-mentioned electronic equipment；It is also possible to individualism, and not
It is fitted into the electronic equipment.Above-mentioned computer-readable medium carries one or more program, when said one or more
When a program is executed by the electronic equipment, so that the electronic equipment: obtaining target facial image；It is fixed based on side face trained in advance
Bit model generates the side face location information in the side face region in target facial image, wherein side face location model is defeated for determining
The position in the side face region in the image entered, side face region include the corresponding facial pixel of cheekbone, and side face location information includes
The location information of the corresponding facial pixel of cheekbone；Export side face location information generated.Alternatively, making the electronic equipment:
The video of current shooting and presentation is obtained as target video；The video frame conduct comprising face object is chosen from target video
Target facial image, and execute following processing step: based on side face location model trained in advance, generate target facial image
In side face region side face location information, wherein the side face region in image of the side face location model for determining input
Position, side face region include the corresponding facial pixel of cheekbone, and side face location information includes the corresponding facial pixel of cheekbone
Location information；Based on side face location information generated, thin face processing is carried out to target facial image, obtains thin face rear face figure
Picture；It is presented using thin face rear face image substitution target facial image.
The behaviour for executing embodiment of the disclosure can be write with one or more programming languages or combinations thereof
The computer program code of work, described program design language include object oriented program language-such as Java,
Smalltalk, C++ further include conventional procedural programming language-such as " C " language or similar program design language
Speech.Program code can be executed fully on the user computer, partly be executed on the user computer, as an independence
Software package execute, part on the user computer part execute on the remote computer or completely in remote computer or
It is executed on server.In situations involving remote computers, remote computer can pass through the network of any kind --- packet
It includes local area network (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as benefit
It is connected with ISP by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the disclosure, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in embodiment of the disclosure can be realized by way of software, can also be passed through
The mode of hardware is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor
Including first acquisition unit, generation unit and output unit.Alternatively, it is single including the second acquisition to be described as a kind of processor
Member and execution unit.Wherein, the title of these units does not constitute the restriction to the unit itself under certain conditions, for example,
First acquisition unit is also described as " obtaining the unit of target facial image ".
Above description is only the preferred embodiment of the disclosure and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the disclosure, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed in the disclosure
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (17)
1. a kind of method for output information, comprising:
Obtain target facial image；
Based on side face location model trained in advance, the side face position letter in the side face region in the target facial image is generated
Breath, wherein the position in the side face region in image of the side face location model for determining input, side face region includes cheekbone
Corresponding face pixel, side face location information include the location information of the corresponding facial pixel of cheekbone；
Export side face location information generated.
2. according to the method described in claim 1, wherein, the method also includes:
Based on side face location information generated, thin face processing is carried out to the target facial image, obtains thin face rear face figure
Picture.
3. according to the method described in claim 2, wherein, the method also includes:
The target facial image is substituted using the thin face rear face image to be presented.
4. according to the method described in claim 2, wherein, side face region further includes at least one of following corresponding facial pixel
Point: 3 Along ents between 3 Along ents between temple, mandibular, cheekbone and temple and cheekbone and mandibular；And
Side face location information further includes the location information of the also included facial pixel in side face region.
5. the method according to one of claim 2-4, wherein it is described to be based on side face location information generated, to described
Target facial image carries out thin face processing, obtains thin face rear face image, comprising:
By each facial pixel that side face region in the target facial image includes to perpendicular with target central axes and lean on
The direction of the nearly target central axes is moved, and to carry out thin face processing, obtains thin face rear face image；
Wherein, the target central axes are the point for being used to indicate place between the eyebrows in face-image and the point for being used to indicate Renzhong acupoint place
Straight line.
6. according to the method described in claim 5, wherein, in each facial pixel for being moved, about the target axis
What symmetrical two facial pixels were moved is equidistant.
7. according to the method described in claim 5, wherein, each facial pixel moved is mobile to the target central axes
Distance positive correlation at a distance from facial pixel to the target central axes.
8. a kind of method for handling video, comprising:
The video of current shooting and presentation is obtained as target video；
The video frame comprising face object is chosen from the target video as target facial image, and executes following processing
Step:
Based on side face location model trained in advance, the side face location information in the side face region in target facial image is generated,
In, the position in the side face region in image of the side face location model for determining input, side face region includes that cheekbone is corresponding
Facial pixel, side face location information includes the location information of the corresponding facial pixel of cheekbone；
Based on side face location information generated, thin face processing is carried out to target facial image, obtains thin face rear face image；
It is presented using thin face rear face image substitution target facial image.
9. according to the method described in claim 8, wherein, the method also includes:
In response to the last frame in the current non-target video of target facial image, by it is in the target video, when
The subsequent facial video frame of preceding target facial image is as new target facial image, based on new target facial image, after
It is continuous to execute the processing step.
10. a kind of device for output information, comprising:
First acquisition unit is configured to obtain target facial image；
Generation unit is configured to generate the side face in the target facial image based on side face location model trained in advance
The side face location information in region, wherein the position in the side face region in image of the side face location model for determining input,
Side face region includes the corresponding facial pixel of cheekbone, and side face location information includes the position letter of the corresponding facial pixel of cheekbone
Breath；
Output unit is configured to export side face location information generated.
11. device according to claim 10, wherein described device further include:
Processing unit, is configured to based on side face location information generated, carries out thin face processing to the target facial image,
Obtain thin face rear face image.
12. device according to claim 11, wherein described device further include:
Display unit is configured to be presented using the thin face rear face image substitution target facial image.
13. device according to claim 11, wherein side face region further includes at least one of following corresponding facial pixel
Point: 3 Along ents between 3 Along ents between temple, mandibular, cheekbone and temple and cheekbone and mandibular；And
Side face location information further includes the location information of the also included facial pixel in side face region.
14. device described in one of 1-13 according to claim 1, wherein the processing unit includes:
Mobile module, each facial pixel for being configured to include by side face region in the target facial image to target
The perpendicular and direction close to the target central axes in central axes is moved, and to carry out thin face processing, obtains thin face rear face
Image；
Wherein, the target central axes are the point for being used to indicate place between the eyebrows in face-image and the point for being used to indicate Renzhong acupoint place
Straight line.
15. a kind of for handling the device of video, comprising:
Second acquisition unit is configured to obtain the video of current shooting and presentation as target video；
Execution unit is configured to choose the video frame comprising face object from the target video as target face figure
Picture, and execute following processing step:
Based on side face location model trained in advance, the side face location information in the side face region in target facial image is generated,
In, the position in the side face region in image of the side face location model for determining input, side face region includes that cheekbone is corresponding
Facial pixel, side face location information includes the location information of the corresponding facial pixel of cheekbone；
Based on side face location information generated, thin face processing is carried out to target facial image, obtains thin face rear face image；
It is presented using thin face rear face image substitution target facial image.
16. a kind of electronic equipment, comprising:
One or more processors；
Storage device is stored thereon with one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1-9.
17. a kind of computer-readable medium, is stored thereon with computer program, wherein real when described program is executed by processor
The now method as described in any in claim 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910477387.2A CN110188711A (en) | 2019-06-03 | 2019-06-03 | Method and apparatus for output information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910477387.2A CN110188711A (en) | 2019-06-03 | 2019-06-03 | Method and apparatus for output information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110188711A true CN110188711A (en) | 2019-08-30 |
Family
ID=67719969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910477387.2A Pending CN110188711A (en) | 2019-06-03 | 2019-06-03 | Method and apparatus for output information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110188711A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145110A (en) * | 2019-12-13 | 2020-05-12 | 北京达佳互联信息技术有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104850847A (en) * | 2015-06-02 | 2015-08-19 | 上海斐讯数据通信技术有限公司 | Image optimization system and method with automatic face thinning function |
| CN105447823A (en) * | 2014-08-07 | 2016-03-30 | 联想(北京)有限公司 | Image processing method and electronic device |
| CN107705248A (en) * | 2017-10-31 | 2018-02-16 | 广东欧珀移动通信有限公司 | Image processing method, device, electronic equipment and computer-readable recording medium |
| CN108470322A (en) * | 2018-03-09 | 2018-08-31 | 北京小米移动软件有限公司 | Handle the method, apparatus and readable storage medium storing program for executing of facial image |
| CN108491780A (en) * | 2018-03-16 | 2018-09-04 | 广东欧珀移动通信有限公司 | Image landscaping treatment method, apparatus, storage medium and terminal device |
| CN109299714A (en) * | 2017-07-25 | 2019-02-01 | 上海中科顶信医学影像科技有限公司 | ROI template generation method, ROI extracting method and system, equipment, medium |
| CN109614902A (en) * | 2018-11-30 | 2019-04-12 | 深圳市脸萌科技有限公司 | Face image processing process, device, electronic equipment and computer storage medium |
-
2019
- 2019-06-03 CN CN201910477387.2A patent/CN110188711A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105447823A (en) * | 2014-08-07 | 2016-03-30 | 联想(北京)有限公司 | Image processing method and electronic device |
| CN104850847A (en) * | 2015-06-02 | 2015-08-19 | 上海斐讯数据通信技术有限公司 | Image optimization system and method with automatic face thinning function |
| CN109299714A (en) * | 2017-07-25 | 2019-02-01 | 上海中科顶信医学影像科技有限公司 | ROI template generation method, ROI extracting method and system, equipment, medium |
| CN107705248A (en) * | 2017-10-31 | 2018-02-16 | 广东欧珀移动通信有限公司 | Image processing method, device, electronic equipment and computer-readable recording medium |
| CN108470322A (en) * | 2018-03-09 | 2018-08-31 | 北京小米移动软件有限公司 | Handle the method, apparatus and readable storage medium storing program for executing of facial image |
| CN108491780A (en) * | 2018-03-16 | 2018-09-04 | 广东欧珀移动通信有限公司 | Image landscaping treatment method, apparatus, storage medium and terminal device |
| CN109614902A (en) * | 2018-11-30 | 2019-04-12 | 深圳市脸萌科技有限公司 | Face image processing process, device, electronic equipment and computer storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145110A (en) * | 2019-12-13 | 2020-05-12 | 北京达佳互联信息技术有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN111145110B (en) * | 2019-12-13 | 2021-02-19 | 北京达佳互联信息技术有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7104683B2 (en) | How and equipment to generate information | |
| CN108416310B (en) | Method and apparatus for generating information | |
| CN109858445A (en) | Method and apparatus for generating model | |
| CN108898185A (en) | Method and apparatus for generating image recognition model | |
| CN108509915A (en) | The generation method and device of human face recognition model | |
| CN111476871B (en) | Method and device for generating video | |
| CN111814985A (en) | Model training method under federated learning network and related equipment thereof | |
| CN108985257A (en) | Method and apparatus for generating information | |
| CN109086719A (en) | Method and apparatus for output data | |
| CN110503703A (en) | Method and apparatus for generating image | |
| CN110298319B (en) | Image synthesis method and device | |
| CN108492364A (en) | The method and apparatus for generating model for generating image | |
| CN109993150A (en) | The method and apparatus at age for identification | |
| CN108363995A (en) | Method and apparatus for generating data | |
| CN110188719A (en) | Method for tracking target and device | |
| CN110796089B (en) | Method and apparatus for training face model | |
| CN110288705B (en) | Method and device for generating three-dimensional model | |
| CN110009059A (en) | Method and apparatus for generating model | |
| CN109815365A (en) | Method and apparatus for handling video | |
| CN111275650B (en) | Beauty treatment method and device | |
| CN108491823A (en) | Method and apparatus for generating eye recognition model | |
| CN109977839A (en) | Information processing method and device | |
| CN108062544A (en) | For the method and apparatus of face In vivo detection | |
| CN109784304A (en) | Method and apparatus for marking dental imaging | |
| CN109754464A (en) | Method and apparatus for generating information |
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 |