CN109523461A - Method, apparatus, terminal and the storage medium of displaying target image - Google Patents
Method, apparatus, terminal and the storage medium of displaying target image Download PDFInfo
- Publication number
- CN109523461A CN109523461A CN201811334358.2A CN201811334358A CN109523461A CN 109523461 A CN109523461 A CN 109523461A CN 201811334358 A CN201811334358 A CN 201811334358A CN 109523461 A CN109523461 A CN 109523461A
- Authority
- CN
- China
- Prior art keywords
- image
- face
- facial
- target
- topological
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000001815 facial effect Effects 0.000 claims abstract description 228
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 14
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 21
- 238000002156 mixing Methods 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 33
- 230000000694 effects Effects 0.000 abstract description 9
- 238000004088 simulation Methods 0.000 abstract description 7
- 230000006870 function Effects 0.000 description 26
- 238000010586 diagram Methods 0.000 description 17
- 230000004927 fusion Effects 0.000 description 14
- 238000004891 communication Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 9
- 238000001514 detection method Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000000712 assembly Effects 0.000 description 2
- 238000000429 assembly Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 210000004209 hair Anatomy 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000012092 media component Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G06T3/18—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Abstract
The disclosure is directed to method, apparatus, terminal and the storage mediums of a kind of displaying target image, belong to field of image processing.The described method includes: obtaining first facial image and the second face-image；First facial topology image is generated according to the first facial image, according to the topological image of second face of the second Facial image synthesis；The first facial topology image is merged with the topological image of the second face, generates target image；The target image is shown in target interface.Using the disclosure, simulation effect can be made preferable.
Description
Technical field
This disclosure relates to field of image processing more particularly to a kind of method, apparatus, terminal and the storage of displaying target image
Medium.
Background technique
Currently, many users are very interested in the appearance for simulating the following baby, for example, being simulated by the image of two people
The image of the following baby, it is very interesting, it is a kind of relatively popular entertainment way.
In the related technology, when through image simulation baby's image of parent, user need first by the image of father and
The image of mother is uploaded to terminal, after terminal receives this two images, randomly selects an image in this two images, then
Obtain pre-stored baby's image in image library.The above-mentioned image selected is matched respectively with every baby's image,
The similarity of the image chosen and every baby's image, then terminal is using the maximum baby's image of similarity as simulating
To as a result, being shown on the display screen of terminal.
But the above-mentioned baby's image simulated, the only comparatively similarity with the image of parent in picture library
Maximum image, but in fact, the baby's image simulated is not necessarily really much like with the image of parent, that is to say, that root
The baby's appearance simulated according to the appearance of parent is possible to dissimilar with parent, in this way, the analog result and reason that actually obtain
By upper available analog result, there are difference, so that simulation effect is poor.
Summary of the invention
The disclosure provides method, apparatus, terminal and the storage medium of a kind of displaying target image, can solve simulation effect
Poor problem.
According to the first aspect of the embodiments of the present disclosure, a kind of method of displaying target image is provided, comprising:
Obtain first facial image and the second face-image；
First facial topology image is generated according to the first facial image, according to second Facial image synthesis second
Facial topology image；
The first facial topology image is merged with the topological image of the second face, generates target image；
The target image is shown in target interface.
Optionally, described to merge the first facial topology image with the topological image of the second face, it generates
Target image, comprising:
It will be in the multiple first area subgraphs and the topological image of the second face in the first facial topology image
Corresponding multiple second area subgraphs are merged respectively, generate target image.
Optionally, multiple first area subgraphs by the first facial topology image and second face
Corresponding multiple second area subgraphs are merged respectively in topological image, generate target image, comprising:
According to multiple first area subgraphs in the first facial topology image, to the topological image of the second face
In corresponding multiple second area subgraphs carry out the adjustment of shapes and size；
Multiple second area subgraphs adjusted are fitted on corresponding multiple first area subgraphs, according to prestoring
Pixel fusion algorithm, to the first area subgraph and the topological image of second face in the first facial topology image
In corresponding second area subgraph merged, generate target image.
Optionally, which is characterized in that the first area subgraph by the first facial topology image with it is described
Corresponding second area subgraph is merged in the topological image of second face, generates target image, comprising:
According to corresponding first weight of the first facial topology image, the first facial topology image is adjusted, is obtained
First facial topology image adjusted；
According to corresponding second weight of the topological image of the second face, the topological image of the second face is adjusted, is obtained
The topological image of second face adjusted；
By the first area subgraph in the first facial topology image adjusted, with second face adjusted
Corresponding second area subgraph is merged in portion's topology image, generates target image.
Optionally, first weight is random determining, and second weight is the difference of 1 with first weight.
Optionally, after the generation target image, further includes:
The first skin tone value is obtained in the predetermined position of the first facial topology image, in the described second facial topological diagram
The predetermined position of picture obtains the second skin tone value；
According to first skin tone value and second skin tone value, the target skin of the predeterminated position of the target image is determined
Color value；
According to the target skin tone value, the skin tone value of the predeterminated position in the target image is adjusted.
Optionally, described according to first skin tone value and second skin tone value, determine the default of the target image
The target skin tone value of position, comprising:
Obtain preset colour of skin adjusted value；
Obtain first skin tone value and second skin tone value and value, the colour of skin adjusted value is subtracted with value by described
Obtained difference is determined as the target skin tone value of the predeterminated position of the target face topology image.
Optionally, the acquisition first facial image and the second face-image, comprising:
When receiving target image generation instruction, video frame is acquired by camera, from the multi-frame video frame acquired
In, a frame video frame is randomly selected as source images；
First facial image and the second face-image are extracted in the source images；
After the acquisition first facial image and the second face-image, further includes:
In the target interface, the first facial image and the second face-image are shown.
Optionally, described that first facial topology image is generated according to the first facial image, according to second face
Image generates the topological image of the second face, comprising:
In the first facial image, first group of face feature point is determined；
According to pre-set concatenate rule, each face feature point in first group of face feature point is connected
It connects, generates first facial topology image；
In second face-image, second group of face feature point is determined；
According to pre-set concatenate rule, each face feature point in second group of face feature point is connected
It connects, generates the topological image of the second face.
Optionally, the method also includes:
It obtains and updates service packs, wherein is described to update the instruction for carrying in service packs and calling center processor cpu function
And the instruction of image processor GPU function is called, the cpu function includes using sensor, detection touch event, detection touching
Hair event determines face feature point function；
Load the update service packs.
According to the second aspect of an embodiment of the present disclosure, a kind of device of displaying target image is provided, comprising:
Acquiring unit is configured as obtaining first facial image and the second face-image；
Generation unit is configured as generating first facial topology image according to the first facial image, according to described the
The two topological images of the second face of Facial image synthesis；
The generation unit, be additionally configured to by the first facial topology image and the topological image of second face into
Row fusion, generates target image；
Display unit is configured as showing the target image in target interface.
Optionally, the generation unit, is configured as:
It will be in the multiple first area subgraphs and the topological image of the second face in the first facial topology image
Corresponding multiple second area subgraphs are merged respectively, generate target image.
Optionally, the generation unit, is configured as:
According to multiple first area subgraphs in the first facial topology image, to the topological image of the second face
In corresponding multiple second area subgraphs carry out the adjustment of shapes and size；
Multiple second area subgraphs adjusted are fitted on corresponding multiple first area subgraphs, according to prestoring
Pixel fusion algorithm, to the first area subgraph and the topological image of second face in the first facial topology image
In corresponding second area subgraph merged, generate target image.
Optionally, which is characterized in that the generation unit is configured as:
According to corresponding first weight of the first facial topology image, the first facial topology image is adjusted, is obtained
First facial topology image adjusted；
According to corresponding second weight of the topological image of the second face, the topological image of the second face is adjusted, is obtained
The topological image of second face adjusted；
By the first area subgraph in the first facial topology image adjusted, with second face adjusted
Corresponding second area subgraph is merged in portion's topology image, generates target image.
Optionally, first weight is random determining, and second weight is the difference of 1 with first weight.
Optionally, described device further include:
The acquiring unit is additionally configured to after generating target image, in the default of the first facial topology image
The first skin tone value is obtained at position, obtains the second skin tone value in the predetermined position of the topological image of the second face；
Determination unit is configured as determining the target image according to first skin tone value and second skin tone value
Predeterminated position target skin tone value；
Adjustment unit is configured as according to the target skin tone value, to the colour of skin of the predeterminated position in the target image
Value is adjusted.
Optionally, the determination unit, is configured as:
Obtain preset colour of skin adjusted value；
Obtain first skin tone value and second skin tone value and value, the colour of skin adjusted value is subtracted with value by described
Obtained difference is determined as the target skin tone value of the predeterminated position of the target face topology image.
Optionally, the acquiring unit, is configured as:
When receiving target image generation instruction, video frame is acquired by camera, from the multi-frame video frame acquired
In, a frame video frame is randomly selected as source images；
First facial image and the second face-image are extracted in the source images；
After the acquisition first facial image and the second face-image, further includes:
In the target interface, the first facial image and the second face-image are shown.
Optionally, the generation unit, is configured as:
In the first facial image, first group of face feature point is determined；
According to pre-set concatenate rule, each face feature point in first group of face feature point is connected
It connects, generates first facial topology image；
In second face-image, second group of face feature point is determined；
According to pre-set concatenate rule, each face feature point in second group of face feature point is connected
It connects, generates the topological image of the second face.
Optionally, the method also includes:
The acquiring unit is configured as obtaining update service packs, wherein carry in calling in the update service packs
The instruction of heart processor cpu function and the instruction for calling image processor GPU function, the cpu function include using sensing
Device detects touch event, detects trigger event, determines face feature point function；
Loading unit is configured as loading the update service packs.
According to the third aspect of an embodiment of the present disclosure, a kind of terminal is provided, comprising:
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to:
Obtain first facial image and the second face-image；
First facial topology image is generated according to the first facial image, according to second Facial image synthesis second
Facial topology image；
The first facial topology image is merged with the topological image of the second face, generates target image；
The target image is shown in target interface.
According to a fourth aspect of embodiments of the present disclosure, a kind of non-transitorycomputer readable storage medium is provided, when described
When instruction in storage medium is executed by the processor of server, the side for executing a kind of displaying target image is enabled the server to
Method, which comprises
Obtain first facial image and the second face-image；
First facial topology image is generated according to the first facial image, according to second Facial image synthesis second
Facial topology image；
The first facial topology image is merged with the topological image of the second face, generates target image；
The target image is shown in target interface.
According to a fifth aspect of the embodiments of the present disclosure, a kind of application program is provided, when application program terminal at runtime,
So that a kind of method that terminal executes displaying target image, which comprises
Obtain first facial image and the second face-image；
First facial topology image is generated according to the first facial image, according to second Facial image synthesis second
Facial topology image；
The first facial topology image is merged with the topological image of the second face, generates target image；
The target image is shown in target interface.
The technical scheme provided by this disclosed embodiment can include the following benefits:
Terminal obtains first facial image and the second face-image, then according to first facial image and the second face-image
Fusion, Lai Shengcheng target image.And in the related technology, it is chosen in pre-stored baby's image similar to the image of parent
Spend maximum baby's image as target image, the target image chosen by this method, only in limited baby's image
The maximum image of comparatively similarity of middle selection, but there is no the features of the image of fusion parent for the image chosen, therefore
The similarity of target image and the image of parent is lower, and simulation effect is poor.And in the disclosure, the target image of generation merges
The feature of first facial image and the second face-image, therefore, compared to the relevant technologies, target image that the disclosure generates with
The similarity of first facial image and the second face-image is bigger, therefore, so that simulation effect is more preferable.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.
Fig. 1 is a kind of method flow diagram of displaying target image shown according to an exemplary embodiment.
Fig. 2 is a kind of method flow diagram of displaying target image shown according to an exemplary embodiment.
Fig. 3 is a kind of interface schematic diagram of displaying target image shown according to an exemplary embodiment.
Fig. 4 is a kind of schematic diagram of a scenario of displaying target image shown according to an exemplary embodiment.
Fig. 5 is a kind of interface schematic diagram of displaying target image shown according to an exemplary embodiment.
Fig. 6 is a kind of device block diagram of displaying target image shown according to an exemplary embodiment.
Fig. 7 is a kind of block diagram of device 700 for displaying target image shown according to an exemplary embodiment.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
Fig. 1 is a kind of flow chart of the method for displaying target image shown according to an exemplary embodiment, such as Fig. 1 institute
Show, this method is for including the following steps in terminal.
In a step 101, first facial image and the second face-image are obtained.
In a step 102, first facial topology image is generated according to first facial image, according to the second Facial image synthesis
The topological image of second face.
In step 103, first facial topology image is merged with the topological image of the second face, generates target figure
Picture.
At step 104, the displaying target image in target interface.
Optionally, first facial topology image is merged with the topological image of the second face, generates target image, packet
It includes:
Multiple first area subgraphs in first facial topology image are corresponding more with the topological image of the second face
A second area subgraph is merged respectively, generates target image.
Optionally, by first facial topology image multiple first area subgraphs with it is right in the second topological image of face
The multiple second area subgraphs answered are merged respectively, generate target image, comprising:
According to multiple first area subgraphs in first facial topology image, to corresponding in the topological image of the second face
Multiple second area subgraphs carry out the adjustment of shape and size；
Multiple second area subgraphs adjusted are fitted on corresponding multiple first area subgraphs, according to prestoring
Pixel fusion algorithm, it is corresponding with the second topological image of face to the first area subgraph in first facial topology image
Second area subgraph is merged, and target image is generated.
Optionally, which is characterized in that by the first area subgraph and the second face topology in first facial topology image
Corresponding second area subgraph is merged in image, generates target image, comprising:
According to corresponding first weight of first facial topology image, first facial topology image is adjusted, after being adjusted
First facial topology image；
According to corresponding second weight of the topological image of the second face, the topological image of the second face of adjustment, after being adjusted
The topological image of second face；
By the first area subgraph in first facial topology image adjusted, with the adjusted second facial topological diagram
Corresponding second area subgraph is merged as in, generates target image.
Optionally, the first weight be it is random determine, the second weight be 1 and first weight difference.
Optionally, after generation target image, further includes:
The first skin tone value is obtained in the predetermined position of first facial topology image, in the default of the topological image of the second face
The second skin tone value is obtained at position；
According to the first skin tone value and the second skin tone value, the target skin tone value of the predeterminated position of target image is determined；
According to target skin tone value, the skin tone value of the predeterminated position in target image is adjusted.
Optionally, according to the first skin tone value and the second skin tone value, the target skin tone value of the predeterminated position of target image is determined,
Include:
Obtain preset colour of skin adjusted value；
Obtain the first skin tone value and the second skin tone value and value, the difference that colour of skin adjusted value obtains will be subtracted with value, determination
For the target skin tone value of the predeterminated position of target face topology image.
Optionally, first facial image and the second face-image are obtained, comprising:
When receiving target image generation instruction, video frame is acquired by camera, from the multi-frame video frame acquired
In, a frame video frame is randomly selected as source images；
First facial image and the second face-image are extracted in source images；
After acquisition first facial image and the second face-image, further includes:
In target interface, first facial image and the second face-image are shown.
Optionally, first facial topology image is generated according to first facial image, according to the second Facial image synthesis second
Facial topology image, comprising:
In first facial image, first group of face feature point is determined；
According to pre-set concatenate rule, each face feature point in first group of face feature point is attached, it is raw
At first facial topology image；
In the second face-image, second group of face feature point is determined；
According to pre-set concatenate rule, each face feature point in second group of face feature point is attached, it is raw
At the topological image of the second face.
Optionally, method further include:
Obtain update service packs, wherein update service packs in carry call center processor cpu function instruction and
Call image processor GPU function instruction, cpu function include using sensor, detection touch event, detection trigger event,
Determine face feature point function；
Load updates service packs.
The present embodiment will be introduced the method for displaying target image in conjunction with specific embodiment.This method can be with
It is realized by terminal, which can be the terminal for being equipped with the application program of displaying target picture.Terminal include at least video card with
And CPU (Central Processing Unit, central processing unit).The method flow of generation target image as shown in Figure 2
Figure, the present embodiment are the face-image of father and the face-image of mother respectively with first facial image and the second face-image,
For the target image of generation is baby's image, the method for generating target image is illustrated, the process flow of this method can
To comprise the following steps that
In step 201, when terminal, which receives target image, generates instruction, video frame is acquired by camera, from
In the multi-frame video frame of acquisition, a frame video frame is randomly selected as source images, then, first facial figure is extracted in source images
Then picture and the second face-image in the target interface of terminal, show first facial image and the second face-image.
Wherein, source images, which refer to, contains the image of at least two face-images to be fused.
When user wants to generate baby's image (i.e. target image), user can first open a terminal the application journey of upper installation
Sequence, then, user click the option for generating baby's image, and terminal receives the corresponding instruction of option of generation baby's image (i.e.
Target image generates instruction) when, terminal opens camera function, acquires video frame by camera.It is adopted when terminal receives video
When collecting halt instruction, or when the duration for acquiring video frame reaches preset duration, terminal stops acquisition video frame,
And in the multi-frame video frame acquired, an at least frame video frame is randomly selected as source images.
Then in source images, pre-stored face recognition algorithms are can be used in terminal, in the source images got
Identify two facial images (i.e. first facial image and the second face-image), then, terminal is shown in target interface
First facial image and the second face-image.Wherein, face recognition algorithms can be Local Features Analysis method, eigenface side
Method, the recognizer based on elastic model, neural network recognization algorithm, hidden Markov model algorithm etc., as long as being able to achieve
The algorithm of first facial image and the second face-image is extracted in source images, the disclosure does not limit this.
It should be noted that terminal can be cut if terminal identifies more than two face-images in source images
It takes the multiple face-images identified and is shown to user, allow user to manually select two of them face-image and make respectively
For first facial image and the second face-image, as shown in Figure 3.It is mentioned alternatively, terminal can also issue the user with image mistake
Show information, prompts user to upload source images again, the disclosure does not limit this.If terminal can not identify two in source images
A face-image then issues image miscue information, and user is prompted to upload source images again.Issue image miscue information
Mode can there are many, such as display reminding text, display reminding picture, the modes such as voice prompting are issued, as long as can play
Prompt user uploads the effects of source images again, and the disclosure is to issuing the method for image miscue information without limitation.
It should be noted that terminal determines the processing mode of source images, in addition to the processing mode provided in above-mentioned steps,
It can be other processing modes.For example, terminal can receive at least one image of user's upload as source images.This
In mode, user can choose the image for uploading and being stored in advance in the terminal, also can choose shooting image and then uploads shooting
Image.Then, user can upload at least one image, then terminal is using the image received as source images.For another example eventually
End can receive at least one image and video frame of user's upload, as source images.In this fashion, user can be both
At least one image is uploaded, and uploads one section of video, terminal is chosen an at least frame video frame in the video received, will be chosen
Video frame and the image that receives be used as source images together.Terminal determines that the processing mode of source images is varied, can be with
Corresponding processing mode is chosen according to actual needs, and the disclosure does not limit this.
In step 202, terminal generates first facial topology image according to first facial image, according to the second face-image
Generate the topological image of the second face.
In a kind of feasible embodiment, in above-mentioned steps 202 the step of image topological according to Facial image synthesis face
It can be such that in face-image, determine one group of face feature point；According to pre-set concatenate rule, by this group face
Each face feature point in characteristic point is attached, and generates the topological image of face, as shown in Figure 4.By taking first facial image as an example,
Then above-mentioned steps may is that in first facial image, determine first group of face feature point；It is advised according to pre-set connection
Then, each face feature point in first group of face feature point is attached, generates first facial topology image, correspondingly, on
It states step 202 and includes the following steps 2021 and step 2022.
In step 2022, after determining first facial image and the second face-image, terminal, which can be used, to be stored in advance
Face feature point recognizer, one group of face feature point (i.e. first group of facial characteristics is calibrated in first facial image
Point).Based on identical algorithm, second group of face feature point is calibrated in the second face-image.Wherein, face feature point identifies
Algorithm can be CLM (Constrained local model constrains partial model) algorithm, Cascaded Regression
A kind of (cascade returns, man face characteristic point positioning method) algorithm, CNN (Convolutional Neural Network, convolution mind
Through network) algorithm etc., as long as being able to achieve the algorithm for calibrating face feature point in face-image, the disclosure does not do this
It limits.
It should be noted that for any one face-image, using identical face feature point recognizer to face
When image is demarcated, the quantity of the face feature point calibrated is identical, and each face feature point has a mark, each
Identifying corresponding face feature point has fixed meaning, for example, the face feature point of mark 19 to mark 24 represents face figure
The top edge of the left side eyebrow of picture, identify 49 face feature point represent face-image left side eyes left eye angle.
In step 2022, terminal obtains preset concatenate rule, is attached to face feature point, generates first
The first facial topology image of face-image.Preset concatenate rule can be the mark concatenate rule of face feature point,
In this case, by preset mark concatenate rule, regulation in concatenate rule will be identified and need the facial characteristics connected
Point is attached, and first facial image is marked off multiple regions, each region is properly termed as a region subgraph, Suo Youqu
The case where will not overlapping between the subgraph of domain.Generally, it identifies and provides that certain three facial characteristics clicks through in concatenate rule
Row connection, that is, the region subgraph marked off is the image of triangle, it is of course also possible to which setting identification connects according to actual needs
Providing that the face feature point of other quantity is attached in rule, that is, the region subgraph marked off is other shapes of image,
The disclosure does not limit this.
Similarly, the processing mode for generating the topological image of the second face may is that in the second face-image, determine second group
Face feature point；According to pre-set concatenate rule, each face feature point in second group of face feature point is attached,
Generate the topological image of the second face.It generates the topological corresponding processing mode of image of the second face and is referred to above-mentioned the first face of generation
The processing mode of portion's topology image, is not repeated herein.
In step 203, terminal adjusts first facial topological diagram according to corresponding first weight of first facial topology image
Picture, the first facial topology image after being adjusted, and according to the second weight, the topological image of the second face of adjustment is adjusted
The topological image of the second face afterwards.
Terminal first obtains corresponding first weight of first facial topology image and the second topological image of face corresponding the
Two weights, wherein the first weight can be the weight of entire first facial topology image, and in this case, the second weight is
The weight of the entire topological image of second face.In addition, the first weight is also possible to some region in first facial topology image
The weight of subgraph, in this case, the second weight are then regions corresponding with the first weight in the topological image of the second face
The weight of the corresponding region subgraph of subgraph, the first weight and the second weight may each comprise multiple and different weighted values.It removes
Except this, the first weight can also be the power for the face image that certain multiple regions subgraph in first facial topology image is constituted
Weight, the second weight are then the weight of corresponding face image in the topological image of the second face, the first weight and the second weight
To include multiple and different weighted values, if the first weight is the weight of eyes in first facial topology image, then the second weight is
The weight of eyes in the topological image of second face.For aforesaid way, the disclosure is not specifically limited in this embodiment.
Obtain the first weight and the second weight mode can there are many kinds of, several ways are set forth below.
Mode one, technical staff can preset the numerical value of the first weight and the numerical value of the second weight, when terminal pair
When first facial topology image and the second topological image of face are merged, in the first weight and the second weight is corresponding deposits
Storage area directly reads the numerical value of the first weight and the numerical value of the second weight.
The numerical value of mode two, the numerical value that the first weight can be determined by user and the second weight, as terminal is mentioned to user
For generation baby's image respectively with the adjustment option of the similarity degree of two pictures, user can manually adjust similarity degree,
Terminal converts similarity degree to the numerical value of the first weight and the numerical value of the second weight.
Mode three, terminal can set the numerical value of the first weight at random, then the second weight is 1 difference for subtracting the first weight
Value,.In this way, user does not know that baby's image of generation can be more like with which face-image, baby's figure of generation is increased
The uncertainty of picture, also increases interest.
After getting the first weight and the second weight by above-mentioned processing step, terminal is according to the first weight, adjustment the
One facial topological diagram picture, the first facial topology image after being adjusted, and according to the second weight, adjustment the second face topology
Image, the topological image of the second face after being adjusted.
If the first weight is the weight of entire first facial topology image, the second weight is the entire second facial topological diagram
The case where weight of picture, for mode one, mode two and the mode three in above-mentioned steps 2031, the processing of this step are as follows: really
RGB (Red-Green-Blue, RGB) value for determining each pixel of first facial topology image, by the rgb value of each pixel
With the first multiplied by weight, obtained product is the rgb value of first facial topology image adjusted.According to adjusted first
The rgb value of facial topology image, adjusts the rgb value of first facial topology image.Similarly, according to the second weight, the second face is adjusted
Portion's topology image, the processing step of the topological image of the second face after being adjusted is referring to above-mentioned generation first facial adjusted
Topological image, is not repeated herein.
If the first weight is the weight of some region subgraph in first facial topology image, the second weight is second
In facial topology image the case where the weight of the corresponding region subgraph of region corresponding with the first weight subgraph, for above-mentioned
Mode one, mode two and mode three in step 2031, the processing mode of this step are as follows: in first facial topology image
For some region subgraph, the rgb value of each pixel in the region subgraph is determined, by each rgb value and the first weight
It is multiplied, obtained product is the rgb value adjusted of the region subgraph, is carried out according to the rgb value to the region subgraph
Adjustment.It is adjusted after being adjusted to each region subgraph in first facial topology image based on identical processing mode
First facial topology image after whole.Similarly, according to the second weight, the topological image of the second face of adjustment, the after being adjusted
The processing step of the topological image of two faces is not repeated herein referring to above-mentioned generation first facial topology image adjusted.
If the first weight is the power for the face image that certain multiple regions subgraph in first facial topology image is constituted
The case where weight, the second weight is the weight of corresponding face image in the topological image of the second face, in above-mentioned steps 2031
Mode one, mode two and mode three, the processing mode of this step are as follows: in first facial topology image by multiple regions son
For some face image of image construction, the rgb value of each pixel in the face image is determined, by each rgb value and
One multiplied by weight, obtained product is the rgb value adjusted of the region subgraph, according to the rgb value to the face image
It is adjusted.It is obtained after being adjusted to each face image in first facial topology image based on identical processing mode
First facial topology image adjusted.Similarly, according to the second weight, the topological image of the second face of adjustment, after being adjusted
The processing step of the topological image of second face is not repeated herein referring to above-mentioned generation first facial topology image adjusted.
In step 204, terminal is by the first area subgraph in first facial topology image adjusted, after adjustment
The second topological image of face in corresponding second area subgraph merged, generate target image.
Wherein, first area subgraph is connected according to preset face feature point, in first facial topology image
A part of image marked off, similarly, second area subgraph are connected according to preset face feature point, in the second face
A part of image marked off in topological image.First area subgraph is corresponding with second area subgraph, refers to the firstth area
The mark of corresponding face feature point is identical with second area subgraph for the mark of the corresponding face feature point of domain subgraph.
Through the above steps according to the first weight and the second weight respectively to first facial topology image and the second face
After portion's topology image is adjusted, terminal is according to preset Image Fusion, by first facial topological diagram adjusted
First area subgraph as in is melted with corresponding second area subgraph in the topological image of the second face adjusted
It closes, generates target image.Wherein, Image Fusion can there are many, such as pixel-level image fusion algorithm, graph cut algorithm
Or MVC (Mean Value Coordinates, HCCI combustion) Image Fusion etc., first facial is opened up as long as being able to achieve
The algorithm of image and the topological image co-registration of the second face is flutterred, the disclosure does not limit this.
It is illustrated below by pixel-level image fusion algorithm of Image Fusion, above-mentioned steps 204 can wrap
Include subordinate's step 2041-2042.
In step 2041, terminal is according to multiple first area subgraphs in first facial topology image, to the second face
Corresponding multiple second area subgraphs carry out the adjustment of shape and size in portion's topology image.
It is base map that terminal, which presets the topological image of one of face, and the topological image of another face is false as material
If first facial topology image is determined as base map by terminal, by taking a second area subgraph as an example, terminal is first in first facial
First area subgraph corresponding with the second area subgraph in the topological image of the second face is determined in topological image, then,
According to the shapes and sizes for the first area subgraph determined, the tune of shape and size is carried out to the second area subgraph
It is whole, so that second area subgraph is identical as the shapes and sizes of corresponding first area subgraph.
In step 2042, multiple second area subgraphs adjusted are fitted into corresponding multiple first area subgraphs
As upper, according to the pixel fusion algorithm prestored, the first area subgraph in first facial topology image is opened up with the second face
It flutters corresponding second area subgraph in image to be merged, generates target image.
It should be noted that above-mentioned steps 203-204 is adjustment first facial topology image and the second facial topological diagram
Then the weight of picture is merged, Lai Shengcheng according to first facial topology image adjusted and the topological image of the second face
Target image, it is of course also possible to the weight of first facial topology image and the topological image of the second face is not adjusted, but in step
After rapid 202, first facial topology image is merged with the topological image of the second face directly, generates target image, this public affairs
It opens and does not limit this.
Optionally, in order to enable generate baby's image it is more attractive, more meet the image of baby, can to target image into
The corresponding landscaping treatment of row, such as can carry out liquefaction processing to by the face contour in target face topology image, so that facial
Profile becomes more round, and processing is amplified to the eye contour in target face topology image, so that eye contour becomes much larger
More round etc. or target image skin tone value is adjusted.
In step 205, the first skin tone value is obtained in the predetermined position of first facial topology image, is opened up in the second face
The predetermined position for flutterring image obtains the second skin tone value.
Wherein, predeterminated position is the position of preset region subgraph, and skin tone value is some pixel in the topological image of face
Rgb value.
It, can be according to parent in order to further embody being associated between baby's image of generation and the face-image of parent
The skin tone value of face-image determine the skin tone value of baby's image, i.e., go out to extract the in the predeterminated position of first facial topology image
One skin tone value goes out to extract the second skin tone value in the predeterminated position of the topological image of the second face.
In step 206, according to the first skin tone value and the second skin tone value, the target skin of the predeterminated position of target image is determined
Color value.
After determining the first skin tone value and the second skin tone value, terminal can calculate the first skin tone value and the second skin tone value
Average value determines it as the target skin tone value of the predeterminated position of target image.
Furthermore, it is contemplated that the skin tone value of baby's image generally can be whiter, therefore, in the skin according to the face-image of parent
When color value determines the target skin tone value of predeterminated position, adjustment appropriate, phase can be carried out to the skin tone value of the face-image of parent
The processing mode answered, which can be such that, obtains preset colour of skin adjusted value；Obtain the first skin tone value and the second skin tone value and
Value, will subtract the difference that colour of skin adjusted value obtains with value, is determined as the target colour of skin of the predeterminated position of target face topology image
Value.
In addition to this, the target skin tone value storage that technical staff can also preset predeterminated position in the terminal, works as end
When end obtains the target skin tone value of predeterminated position, target skin tone value is directly read in the corresponding memory block of target skin tone value.
In step 207, according to target skin tone value, terminal adjusts the skin tone value of the predeterminated position in target image
It is whole.
When terminal is adjusted according to skin tone value of the target skin tone value to the predeterminated position in target image, by default position
The rgb value every pixel set is adjusted to target skin tone value.
In a step 208, terminal shows the target image after adjustment skin tone value in target interface.
After being adjusted to the skin tone value of the predeterminated position of target image, terminal displaying target image, as shown in Figure 5.Separately
Outside, terminal is in displaying target image, in order to increase aesthetics and interest, can first play pre-stored audio, animation
Then effect etc. shows target image, or carrys out displaying target image according to preset special display effect, according to actual needs may be used
To carry out corresponding display setting, the disclosure is not limited this.
In the related technology, it when application program needs to increase function, may need that new version is installed in terminal when being updated
Installation kit, new function is increased with this.But Internet resources are wasted in this way, and technical staff needs to make new edition when updating
This installation kit, wasting manpower and material resources can not accomplish quickly to update.Iteration is quickly updated in order to realize, technical staff is compiling
When writing the update service packs for stating function, the video driver script of terminal can be allow to carry out server by character string forms
To issuing for terminal.When user obtains above-mentioned function by more newly arriving, terminal, which obtains, updates service packs, wherein updates patch
The instruction for calling center processor cpu function is carried in packet and calls the instruction of image processor GPU function, cpu function
Including using sensor, detecting touch event, detect trigger event, determine face feature point function.Technical staff by using
Dynamic script language carries out the encapsulation of high latitude cpu logic, i.e., the relevant primitive of Opengl ES is all encapsulated as dynamic script can be with
The instruction of calling, and the relevant high level such as client's end sensor, touch event, trigger event, face's key point identification function
Logic is all encapsulated into script driver.Then, terminal loads update service packs, that is, realize do not have to hair new version can be into
Row updates, and accelerates iteration efficiency.
The method that the embodiment of the present disclosure provides, terminal obtain first facial image and the second face-image, then according to the
One face-image and the second face-image generate first facial topology image and the topological image of the second face, then, root respectively
First facial topology image and the topological image of the second face are adjusted separately according to the first weight and the second weight, it then will adjustment
First facial topology image merged with the topological image of the second face adjusted, generate target image.In this way, generate
Target image has merged the feature of first facial image and the second face-image, therefore, the target image of generation and the first face
The similarity of portion's image and the second face-image is larger, so that simulation effect is more preferable.Furthermore, it is possible to according to target skin tone value pair
The target image of generation is adjusted, so that the colour of skin of the target image generated more meets the feature of baby, so that the mesh generated
Logo image is more attractive.
Fig. 6 is a kind of device block diagram of displaying target image shown according to an exemplary embodiment.Referring to Fig. 6, the dress
It sets including acquiring unit 610, generation unit 620 and display unit 630.
The acquiring unit 610 is configured as obtaining first facial image and the second face-image；
The generation unit 620 is configured as generating first facial topology image according to first facial image, according to the second face
Portion's image generates the topological image of the second face；
The generation unit 620 is additionally configured to merge first facial topology image with the topological image of the second face,
Generate target image；
The display unit 630, is configured as the displaying target image in target interface.
Optionally, the generation unit 620, is configured as:
Multiple first area subgraphs in first facial topology image are corresponding more with the topological image of the second face
A second area subgraph is merged respectively, generates target image.
Optionally, the generation unit 620, is configured as:
According to multiple first area subgraphs in first facial topology image, to corresponding in the topological image of the second face
Multiple second area subgraphs carry out the adjustment of shape and size；
Multiple second area subgraphs adjusted are fitted on corresponding multiple first area subgraphs, according to prestoring
Pixel fusion algorithm, it is corresponding with the second topological image of face to the first area subgraph in first facial topology image
Second area subgraph is merged, and target image is generated.
Optionally, which is configured as:
According to corresponding first weight of first facial topology image, first facial topology image is adjusted, after being adjusted
First facial topology image；
According to corresponding second weight of the topological image of the second face, the topological image of the second face of adjustment, after being adjusted
The topological image of second face；
By the first area subgraph in first facial topology image adjusted, with the adjusted second facial topological diagram
Corresponding second area subgraph is merged as in, generates target image.
Optionally, the first weight be it is random determine, the second weight be 1 and first weight difference.
Optionally, the acquiring unit 610 is additionally configured to after generating target image, in first facial topology image
Predetermined position obtains the first skin tone value, obtains the second skin tone value in the predetermined position of the topological image of the second face；
Device further include:
Determination unit is configured as determining the predeterminated position of target image according to the first skin tone value and the second skin tone value
Target skin tone value；
Adjustment unit is configured as adjusting the skin tone value of the predeterminated position in target image according to target skin tone value
It is whole.
Optionally, the determination unit, is configured as:
Obtain preset colour of skin adjusted value；
Obtain the first skin tone value and the second skin tone value and value, the difference that colour of skin adjusted value obtains will be subtracted with value, determination
For the target skin tone value of the predeterminated position of target face topology image.
Optionally, the acquiring unit 610, is configured as:
When receiving target image generation instruction, video frame is acquired by camera, from the multi-frame video frame acquired
In, a frame video frame is randomly selected as source images；
First facial image and the second face-image are extracted in source images；
After acquisition first facial image and the second face-image, further includes:
In target interface, first facial image and the second face-image are shown.
Optionally, the generation unit 620, is configured as:
In first facial image, first group of face feature point is determined；
According to pre-set concatenate rule, each face feature point in first group of face feature point is attached, it is raw
At first facial topology image；
In the second face-image, second group of face feature point is determined；
According to pre-set concatenate rule, each face feature point in second group of face feature point is attached, it is raw
At the topological image of the second face.
Optionally, the acquiring unit 610 is configured as obtaining update service packs, wherein carry in the update service packs
It calls the instruction of center processor cpu function and calls the instruction of image processor GPU function, cpu function includes using biography
Sensor detects touch event, detects trigger event, determines face feature point function；
Device further include:
Loading unit is configured as loading the update service packs.
About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
Fig. 7 is a kind of block diagram of device 700 for displaying target image shown according to an exemplary embodiment.Example
Such as, device 700 can be mobile phone, computer, messaging devices, game console, the terminals such as tablet device.
Referring to Fig. 7, device 700 may include following one or more components: processing component 702, memory 704, electric power
Component 706, multimedia component 708, audio component 710, the interface 712 of input/output (I/O), sensor module 714, and
Communication component 716.
The integrated operation of the usual control device 700 of processing component 702, such as with display, telephone call, data communication, phase
Machine operation and record operate associated operation.Processing component 702 may include that one or more processors 720 refer to execute
It enables, to perform all or part of the steps of the methods described above.In addition, processing component 702 may include one or more modules, just
Interaction between processing component 702 and other assemblies.For example, processing component 702 may include multi-media module, it is more to facilitate
Interaction between media component 708 and processing component 702.
Memory 704 is configured as storing various types of data to support the operation in equipment 700.These data are shown
Example includes the instruction of any application or method for operating on device 700, contact data, and telephone book data disappears
Breath, picture, video etc..Memory 704 can be by any kind of volatibility or non-volatile memory device or their group
It closes and realizes, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable to compile
Journey read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash
Device, disk or CD.
Power supply module 706 provides electric power for the various assemblies of device 700.Power supply module 706 may include power management system
System, one or more power supplys and other with for device 700 generate, manage, and distribute the associated component of electric power.
Multimedia component 708 includes the screen of one output interface of offer between described device 700 and user.One
In a little embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen
Curtain may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touch sensings
Device is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding action
Boundary, but also detect duration and pressure associated with the touch or slide operation.In some embodiments, more matchmakers
Body component 708 includes a front camera and/or rear camera.When equipment 700 is in operation mode, such as screening-mode or
When video mode, front camera and/or rear camera can receive external multi-medium data.Each front camera and
Rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 710 is configured as output and/or input audio signal.For example, audio component 710 includes a Mike
Wind (MIC), when device 700 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone is matched
It is set to reception external audio signal.The received audio signal can be further stored in memory 704 or via communication set
Part 716 is sent.In some embodiments, audio component 710 further includes a loudspeaker, is used for output audio signal.
I/O interface 712 provides interface between processing component 702 and peripheral interface module, and above-mentioned peripheral interface module can
To be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and lock
Determine button.
Sensor module 714 includes one or more sensors, and the state for providing various aspects for device 700 is commented
Estimate.For example, sensor module 714 can detecte the state that opens/closes of equipment 700, and the relative positioning of component, for example, it is described
Component is the display and keypad of device 700, and sensor module 714 can be with 700 1 components of detection device 700 or device
Position change, the existence or non-existence that user contacts with device 700,700 orientation of device or acceleration/deceleration and device 700
Temperature change.Sensor module 714 may include proximity sensor, be configured to detect without any physical contact
Presence of nearby objects.Sensor module 714 can also include optical sensor, such as CMOS or ccd image sensor, at
As being used in application.In some embodiments, which can also include acceleration transducer, gyro sensors
Device, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 716 is configured to facilitate the communication of wired or wireless way between device 700 and other equipment.Device
700 can access the wireless network based on communication standard, such as WiFi, carrier network (such as 2G, 3G, 4G or 5G) or them
Combination.In one exemplary embodiment, communication component 716 is received via broadcast channel from the wide of external broadcasting management system
Broadcast signal or broadcast related information.In one exemplary embodiment, the communication component 716 further includes near-field communication (NFC)
Module, to promote short range communication.For example, radio frequency identification (RFID) technology, Infrared Data Association (IrDA) can be based in NFC module
Technology, ultra wide band (UWB) technology, bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 700 can be believed by one or more application specific integrated circuit (ASIC), number
Number processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory 704 of instruction, above-metioned instruction can be executed by the processor 720 of device 700 to complete above-mentioned displaying target figure
The method of picture, this method comprises: obtaining first facial image and the second face-image；First is generated according to first facial image
Facial topology image, according to the second topological image of the second face of Facial image synthesis；By first facial topology image and the second face
Portion's topology image is merged, and target image is generated；The displaying target image in target interface.For example, the non-transitory meter
Calculation machine readable storage medium storing program for executing can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk and optical data storage and set
It is standby etc..
In the exemplary embodiment, a kind of application program, including one or more instruction are additionally provided, this one or more
Instruction can be executed by the processor 720 of electronic equipment 700, the method to complete above-mentioned displaying target image, this method comprises:
Obtain first facial image and the second face-image；First facial topology image is generated according to the first facial image, according to
The topological image of the second face of second Facial image synthesis；First facial topology image and the topological image of the second face are melted
It closes, generates target image；The target image is shown in target interface.Optionally, above-metioned instruction can also be by electronic equipment 700
Processor 720 execute to complete other steps involved in the above exemplary embodiments.
Those skilled in the art will readily occur to its of the disclosure after considering specification and practicing disclosure disclosed herein
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following
Claim is pointed out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.
Claims (10)
1. a kind of method of displaying target image characterized by comprising
Obtain first facial image and the second face-image；
First facial topology image is generated according to the first facial image, according to second face of the second Facial image synthesis
Topological image；
The first facial topology image is merged with the topological image of the second face, generates target image；
The target image is shown in target interface.
2. the method for displaying target image according to claim 1, which is characterized in that described by the first facial topology
Image is merged with the topological image of the second face, generates target image, comprising:
Multiple first area subgraphs in the first facial topology image are corresponding with the topological image of the second face
Multiple second area subgraphs merged respectively, generate target image.
3. the method for displaying target image according to claim 2, which is characterized in that described by the first facial topology
Multiple first area subgraphs in image divide with corresponding multiple second area subgraphs in the topological image of the second face
It is not merged, generates target image, comprising:
According to multiple first area subgraphs in the first facial topology image, to right in the topological image of the second face
The multiple second area subgraphs answered carry out the adjustment of shape and size；
Multiple second area subgraphs adjusted are fitted on corresponding multiple first area subgraphs, according to the picture prestored
Plain blending algorithm, in the first facial topology image first area subgraph with it is right in the topological image of second face
The second area subgraph answered is merged, and target image is generated.
4. the method for displaying target image according to claim 2 or 3, which is characterized in that described by the first facial
First area subgraph in topological image is melted with corresponding second area subgraph in the topological image of the second face
It closes, generates target image, comprising:
According to corresponding first weight of the first facial topology image, the first facial topology image is adjusted, is adjusted
First facial topology image afterwards；
According to corresponding second weight of the topological image of the second face, the topological image of the second face is adjusted, is adjusted
The topological image of the second face afterwards；
By the first area subgraph in the first facial topology image adjusted, opened up with second face adjusted
It flutters corresponding second area subgraph in image to be merged, generates target image.
5. the method for displaying target image according to claim 4, which is characterized in that first weight is random true
Fixed, second weight is the difference of 1 with first weight.
6. the method for displaying target image according to claim 1, which is characterized in that after the generation target image,
Further include:
The first skin tone value is obtained in the predetermined position of the first facial topology image, in the topological image of the second face
Predetermined position obtains the second skin tone value；
According to first skin tone value and second skin tone value, the target colour of skin of the predeterminated position of the target image is determined
Value；
According to the target skin tone value, the skin tone value of the predeterminated position in the target image is adjusted.
7. the method for displaying target image according to claim 6, which is characterized in that described according to first skin tone value
With second skin tone value, the target skin tone value of the predeterminated position of the target image is determined, comprising:
Obtain preset colour of skin adjusted value；
Obtain first skin tone value and second skin tone value and value, by described the colour of skin adjusted value is subtracted with value obtain
Difference, be determined as the target skin tone value of the predeterminated position of the target face topology image.
8. a kind of device of displaying target image characterized by comprising
Acquiring unit is configured as obtaining first facial image and the second face-image；
Generation unit is configured as generating first facial topology image according to the first facial image, according to second face
Portion's image generates the topological image of the second face；
The generation unit is additionally configured to melt the first facial topology image and the topological image of the second face
It closes, generates target image；
Display unit is configured as showing the target image in target interface.
9. a kind of terminal characterized by comprising
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to:
Obtain first facial image and the second face-image；
First facial topology image is generated according to the first facial image, according to second face of the second Facial image synthesis
Topological image；
The first facial topology image is merged with the topological image of the second face, generates target image；
The target image is shown in target interface.
10. a kind of non-transitorycomputer readable storage medium, which is characterized in that when the instruction in the storage medium is by servicing
When the processor of device executes, a kind of enable the server to execute displaying target image method, which comprises
Obtain first facial image and the second face-image；
First facial topology image is generated according to the first facial image, according to second face of the second Facial image synthesis
Topological image；
The first facial topology image is merged with the topological image of the second face, generates target image；
The target image is shown in target interface.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811334358.2A CN109523461A (en) | 2018-11-09 | 2018-11-09 | Method, apparatus, terminal and the storage medium of displaying target image |
| PCT/CN2019/107085 WO2020093798A1 (en) | 2018-11-09 | 2019-09-20 | Method and apparatus for displaying target image, terminal, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811334358.2A CN109523461A (en) | 2018-11-09 | 2018-11-09 | Method, apparatus, terminal and the storage medium of displaying target image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109523461A true CN109523461A (en) | 2019-03-26 |
Family
ID=65773650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811334358.2A Pending CN109523461A (en) | 2018-11-09 | 2018-11-09 | Method, apparatus, terminal and the storage medium of displaying target image |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109523461A (en) |
| WO (1) | WO2020093798A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020093798A1 (en) * | 2018-11-09 | 2020-05-14 | 北京达佳互联信息技术有限公司 | Method and apparatus for displaying target image, terminal, and storage medium |
| CN111339833A (en) * | 2020-02-03 | 2020-06-26 | 重庆特斯联智慧科技股份有限公司 | Identity verification method, system and equipment based on face edge calculation |
| CN111784604A (en) * | 2020-06-29 | 2020-10-16 | 北京字节跳动网络技术有限公司 | Image processing method, device, equipment and computer readable storage medium |
| CN112991248A (en) * | 2021-03-10 | 2021-06-18 | 维沃移动通信有限公司 | Image processing method and device |
| WO2021189927A1 (en) * | 2020-03-23 | 2021-09-30 | 北京达佳互联信息技术有限公司 | Image processing method and apparatus, electronic device, and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1368418A1 (en) * | 2001-01-18 | 2003-12-10 | Polymerat Pty Ltd | Polymers having co-continuous architecture |
| CN1490764A (en) * | 2002-05-31 | 2004-04-21 | 欧姆龙株式会社 | Method, device, system, program and computer readable media for image synthesis |
| US20080034292A1 (en) * | 2006-08-04 | 2008-02-07 | Apple Computer, Inc. | Framework for graphics animation and compositing operations |
| CN103489011A (en) * | 2013-09-16 | 2014-01-01 | 广东工业大学 | Three-dimensional face identification method with topology robustness |
| CN103927531A (en) * | 2014-05-13 | 2014-07-16 | 江苏科技大学 | Human face recognition method based on local binary value and PSO BP neural network |
| CN105447864A (en) * | 2015-11-20 | 2016-03-30 | 小米科技有限责任公司 | Image processing method, device and terminal |
| CN107767335A (en) * | 2017-11-14 | 2018-03-06 | 上海易络客网络技术有限公司 | A kind of image interfusion method and system based on face recognition features' point location |
| CN107852443A (en) * | 2015-07-21 | 2018-03-27 | 索尼公司 | Message processing device, information processing method and program |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5564384B2 (en) * | 2010-09-28 | 2014-07-30 | 任天堂株式会社 | Image generation program, imaging apparatus, imaging system, and image generation method |
| CN103295210B (en) * | 2012-03-01 | 2016-08-10 | 汉王科技股份有限公司 | Infant image composition method and device |
| CN107609506B (en) * | 2017-09-08 | 2020-04-21 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating image |
| CN108229330A (en) * | 2017-12-07 | 2018-06-29 | 深圳市商汤科技有限公司 | Face fusion recognition methods and device, electronic equipment and storage medium |
| CN109523461A (en) * | 2018-11-09 | 2019-03-26 | 北京达佳互联信息技术有限公司 | Method, apparatus, terminal and the storage medium of displaying target image |
-
2018
- 2018-11-09 CN CN201811334358.2A patent/CN109523461A/en active Pending
-
2019
- 2019-09-20 WO PCT/CN2019/107085 patent/WO2020093798A1/en active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1368418A1 (en) * | 2001-01-18 | 2003-12-10 | Polymerat Pty Ltd | Polymers having co-continuous architecture |
| CN1490764A (en) * | 2002-05-31 | 2004-04-21 | 欧姆龙株式会社 | Method, device, system, program and computer readable media for image synthesis |
| US20080034292A1 (en) * | 2006-08-04 | 2008-02-07 | Apple Computer, Inc. | Framework for graphics animation and compositing operations |
| CN103489011A (en) * | 2013-09-16 | 2014-01-01 | 广东工业大学 | Three-dimensional face identification method with topology robustness |
| CN103927531A (en) * | 2014-05-13 | 2014-07-16 | 江苏科技大学 | Human face recognition method based on local binary value and PSO BP neural network |
| CN107852443A (en) * | 2015-07-21 | 2018-03-27 | 索尼公司 | Message processing device, information processing method and program |
| CN105447864A (en) * | 2015-11-20 | 2016-03-30 | 小米科技有限责任公司 | Image processing method, device and terminal |
| CN107767335A (en) * | 2017-11-14 | 2018-03-06 | 上海易络客网络技术有限公司 | A kind of image interfusion method and system based on face recognition features' point location |
Non-Patent Citations (1)
| Title |
|---|
| 张丽君: "改进snake模型的人脸拓扑轮廓提取", 《电脑知识与技术》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020093798A1 (en) * | 2018-11-09 | 2020-05-14 | 北京达佳互联信息技术有限公司 | Method and apparatus for displaying target image, terminal, and storage medium |
| CN111339833A (en) * | 2020-02-03 | 2020-06-26 | 重庆特斯联智慧科技股份有限公司 | Identity verification method, system and equipment based on face edge calculation |
| CN111339833B (en) * | 2020-02-03 | 2022-10-28 | 重庆特斯联智慧科技股份有限公司 | Identity verification method, system and equipment based on face edge calculation |
| WO2021189927A1 (en) * | 2020-03-23 | 2021-09-30 | 北京达佳互联信息技术有限公司 | Image processing method and apparatus, electronic device, and storage medium |
| CN111784604A (en) * | 2020-06-29 | 2020-10-16 | 北京字节跳动网络技术有限公司 | Image processing method, device, equipment and computer readable storage medium |
| CN112991248A (en) * | 2021-03-10 | 2021-06-18 | 维沃移动通信有限公司 | Image processing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020093798A1 (en) | 2020-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110929651B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN109523461A (en) | Method, apparatus, terminal and the storage medium of displaying target image | |
| KR101649596B1 (en) | Method, apparatus, program, and recording medium for skin color adjustment | |
| WO2021164587A1 (en) | Live streaming interface processing method and apparatus | |
| US20090251484A1 (en) | Avatar for a portable device | |
| CN110691279A (en) | Virtual live broadcast method and device, electronic equipment and storage medium | |
| WO2022037111A1 (en) | Image processing method and apparatus, interactive display apparatus, and electronic device | |
| CN108876732A (en) | Face U.S. face method and device | |
| WO2021063096A1 (en) | Video synthesis method, apparatus, electronic device, and storage medium | |
| CN105138962A (en) | Image display method and image display device | |
| WO2022227393A1 (en) | Image photographing method and apparatus, electronic device, and computer readable storage medium | |
| CN107016163B (en) | Plant species recommendation method and device | |
| WO2022198934A1 (en) | Method and apparatus for generating video synchronized to beat of music | |
| CN112052897B (en) | Multimedia data shooting method, device, terminal, server and storage medium | |
| US20210029304A1 (en) | Methods for generating video, electronic device and storage medium | |
| CN107705245A (en) | Image processing method and device | |
| CN108132983A (en) | The recommendation method and device of clothing matching, readable storage medium storing program for executing, electronic equipment | |
| KR20160127606A (en) | Mobile terminal and the control method thereof | |
| CN111339938A (en) | Information interaction method, device, equipment and storage medium | |
| CN104853223B (en) | The inserting method and terminal device of video flowing | |
| CN104902318B (en) | Control method for playing back and terminal device | |
| CN108933891A (en) | Photographic method, terminal and system | |
| CN104883603B (en) | Control method for playing back, system and terminal device | |
| CN112669233A (en) | Image processing method, image processing apparatus, electronic device, storage medium, and program product | |
| CN113609358A (en) | Content sharing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190326 |