CN107832751A - Mask method, device and the computing device of human face characteristic point - Google Patents
Mask method, device and the computing device of human face characteristic point Download PDFInfo
- Publication number
- CN107832751A CN107832751A CN201711351407.9A CN201711351407A CN107832751A CN 107832751 A CN107832751 A CN 107832751A CN 201711351407 A CN201711351407 A CN 201711351407A CN 107832751 A CN107832751 A CN 107832751A
- Authority
- CN
- China
- Prior art keywords
- faceforms
- face
- feature point
- contour feature
- face picture
- 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
- 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
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of mask method of human face characteristic point, device and computing device, wherein, method includes：Obtain the first face picture and its labeling position information of facial contour feature point；3D reconstructions are carried out to the first face picture, obtain the first 3D faceforms；First 3D faceforms are rotated into predetermined angle, obtain the 2nd 3D faceforms；Determine the 3D positional informations of the facial contour feature point in the 2nd 3D faceforms；2nd 3D faceforms are projected into 2D spaces, obtain the second face picture, and the 3D positional informations of the facial contour feature point in the 2nd 3D faceforms determine the positional information of the facial contour feature point in the second face picture.As can be seen here, using the present invention program, the labeling position information of the facial contour feature point of the second face picture after rotated predetermined angle can be obtained based on the first face picture of the labeling position information of existing facial contour feature point, mark difficulty thus is reduced, reduces the cost of mark.
Description
Technical field
The present invention relates to field of computer technology, and in particular to a kind of mask method of human face characteristic point, device and calculating
Equipment.
Background technology
Facial modeling technology is a committed step in the man-machine interaction based on face, human face characteristic point information
It can be used for the application scenarios such as Expression Recognition, Attitude estimation, recognition of face.At the same time, facial modeling algorithm is steady
Qualitative and accuracy extremely relies on human face characteristic point labeled data.
In the prior art, the human face characteristic point of different angle face is marked, is the people by gathering a large amount of respective angles
Face, and the face is manually marked, and then obtain the human face characteristic point labeled data of different angle.Utilize existing mark
When note mode carries out human face characteristic point mark, for different angle face, it is necessary to resurvey substantial amounts of face, and needs pair
These faces are manually marked, thus the difficulty marked is big, and mark cost is high, and takes time and effort.
The content of the invention
In view of the above problems, it is proposed that the present invention so as to provide one kind overcome above mentioned problem or at least in part solve on
State the mask method, device and computing device of the human face characteristic point of problem.
According to an aspect of the invention, there is provided a kind of mask method of human face characteristic point, including：
Obtain the labeling position information of the facial contour feature point in the first face picture and first face picture；
The labeling position information of facial contour feature point in first face picture is to the first face figure
Piece carries out 3D reconstructions, obtains the first 3D faceforms；
The first 3D faceforms are rotated into predetermined angle, obtain the 2nd 3D faceforms；
Determined according to the positional information of each pixel in the 2nd 3D faceforms in the 2nd 3D faceforms
Facial contour feature point 3D positional informations；
The 2nd 3D faceforms are projected into 2D spaces, obtain the second face picture, and according to the 2nd 3D people
The 3D positional informations of facial contour feature point in face model determine the facial contour feature point in second face picture
Positional information.
Further, the face in first face picture and the first 3D faceforms is to be in first angle
It is existing；Face in second face picture and the 2nd 3D faceforms is presented with second angle；The first angle
Difference with the second angle is the predetermined angle.
Further, it is described that the first 3D faceforms are rotated into predetermined angle, it is specific to obtain the 2nd 3D faceforms
For：The first 3D faceforms are rotated into predetermined angle by pivot of default center point, obtain the 2nd 3D faceforms.
Further, the 2nd 3D is being determined according to the positional information of each pixel in the 2nd 3D faceforms
Before the 3D positional informations of facial contour feature point in faceform, methods described also includes：According to the position of default center point
Confidence breath and predetermined angle determine the positional information of each pixel in the 2nd 3D faceforms.
Further, the positional information according to each pixel in the 2nd 3D faceforms determines described second
The 3D positional informations of facial contour feature point in 3D faceforms further comprise：
According to the positional information of each pixel in the 2nd 3D faceforms, determine in the 2nd 3D faceforms
The 3D positional informations of face contour feature point；Wherein, face contour feature point and the first face in the 2nd 3D faceforms
Face contour feature point in picture corresponds；
And the positional information according to each pixel in the 2nd 3D faceforms, determine the 2nd 3D faces
Face contour characteristic point and its 3D positional informations in model.
According to another aspect of the present invention, there is provided a kind of annotation equipment of human face characteristic point, including：
Acquisition module, suitable for obtaining the mark of the facial contour feature point in the first face picture and first face picture
Note positional information；
Module is rebuild, the labeling position information suitable for the facial contour feature point in first face picture is to institute
State the first face picture and carry out 3D reconstructions, obtain the first 3D faceforms；
Processing module, suitable for the first 3D faceforms are rotated into predetermined angle, obtain the 2nd 3D faceforms；
First determining module, described in being determined according to the positional information of each pixel in the 2nd 3D faceforms
The 3D positional informations of facial contour feature point in 2nd 3D faceforms；
Projection module, suitable for the 2nd 3D faceforms are projected into 2D spaces, obtain the second face picture；
Labeling module, the 3D positional informations suitable for the facial contour feature point in the 2nd 3D faceforms determine
The positional information of facial contour feature point in second face picture.
Further, the face in first face picture and the first 3D faceforms is to be in first angle
It is existing；Face in second face picture and the 2nd 3D faceforms is presented with second angle；The first angle
Difference with the second angle is the predetermined angle.
Further, the processing module is further adapted for：By the first 3D faceforms using default center point as rotation
Turn central rotation predetermined angle, obtain the 2nd 3D faceforms.
Further, described device also includes：Second determining module, suitable for the positional information according to default center point and
Predetermined angle determines the positional information of each pixel in the 2nd 3D faceforms.
Further, first determining module is further adapted for：
According to the positional information of each pixel in the 2nd 3D faceforms, determine in the 2nd 3D faceforms
The 3D positional informations of face contour feature point；Wherein, face contour feature point and the first face in the 2nd 3D faceforms
Face contour feature point in picture corresponds；
And the positional information according to each pixel in the 2nd 3D faceforms, determine the 2nd 3D faces
Face contour characteristic point and its 3D positional informations in model.
According to another aspect of the invention, there is provided a kind of computing device, including：Processor, memory, communication interface and
Communication bus, the processor, the memory and the communication interface complete mutual communication by the communication bus；
The memory is used to deposit an at least executable instruction, and the executable instruction makes the computing device above-mentioned
Operated corresponding to the mask method of human face characteristic point.
In accordance with a further aspect of the present invention, there is provided a kind of computer-readable storage medium, be stored with the storage medium to
A few executable instruction, the executable instruction make computing device be grasped as corresponding to the mask method of above-mentioned human face characteristic point
Make.
As can be seen here, mask method, device and the computing device of the human face characteristic point provided using the present embodiment, can be with base
3D reconstructions are carried out in the first face picture of the labeling position information of existing facial contour feature point, by the first 3D people after reconstruction
Face model rotation predetermined angle obtains the 2nd 3D faceforms of different angle, and then overcomes and need to adopt again in the prior art
The problem of collecting the face of different angle, save manpower and time；And according to each pixel in the 2nd 3D faceforms
Positional information determines the 3D positional informations of the facial contour feature point in the 2nd 3D faceforms, and the 2nd 3D faceforms are projected
To 2D spaces, the second face picture after corresponding rotation predetermined angle is obtained, the facial contour in the 2nd 3D faceforms is special
The depth information levied in the 3D positional informations of point removes, and obtains positional information of the facial contour feature point in 2D spaces, is
The labeling position information of the facial contour feature point of second face picture, realizes the full-automatic of annotation process, and then reduce mark
The human input of note, improve the efficiency of mark.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, and in order to allow above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by the embodiment of the present invention.
Brief description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this area
Technical staff will be clear understanding.Accompanying drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And in whole accompanying drawing, identical part is denoted by the same reference numerals.In the accompanying drawings：
Fig. 1 shows the flow chart of the mask method of human face characteristic point according to an embodiment of the invention；
Fig. 2 shows the flow chart of the mask method of human face characteristic point in accordance with another embodiment of the present invention；
Fig. 3 shows the facial contour feature point in the 3D faceforms of determination the 2nd of a specific embodiment of the invention
The schematic diagram of 3D positional informations；
Fig. 4 shows the functional block diagram of the annotation equipment of human face characteristic point according to an embodiment of the invention；
Fig. 5 shows the functional block diagram of the annotation equipment of human face characteristic point in accordance with another embodiment of the present invention；
Fig. 6 shows a kind of structural representation of computing device according to embodiments of the present invention.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
To overcome the mark difficulty of human face characteristic point notation methods in the prior art big, cost is high, and take time and effort
Problem, the present invention propose a kind of mark of facial contour feature point that can be based on existing face picture and face picture
Positional information, the mark of the facial contour feature point of the face picture of different angle is carried out, obtain the face of corresponding different angle
Labeling position information, for example, using the face picture and its labeling position information of existing positive face, obtain the mark position of side face
Confidence ceases.The annotation process of the present invention program, the mark without the facial contour feature point for different angle face are adopted again
Collect face, and without manually being marked, you can the labeling position information of different angle face is automatically derived, thus can pole
Big reduction mark cost, and save manpower.
Fig. 1 shows the flow chart of the mask method of human face characteristic point according to an embodiment of the invention.Such as Fig. 1 institutes
Show, this method comprises the following steps：
Step S101：Obtain the labeling position letter of the facial contour feature point in the first face picture and the first face picture
Breath.
The first face picture of the labeling position information of existing facial contour feature point is obtained, using as obtaining other angles
Face picture basic picture；And the labeling position information of first face picture is obtained, using as to other angles
The Back ground Information that face picture is labeled.
Wherein, facial contour feature point includes that the shape of face feature, expressive features, and/or face feature of face can be represented
Etc. the characteristic point of information, for example, face contour feature point.Accordingly, the labeling position information of facial contour feature point is above-mentioned
Position of the characteristic point in the first face picture.For example, coordinate value of the eye contour o'clock in the first face picture.Specifically,
In the present embodiment, not to the notation methods of the labeling position information of the facial contour feature point in the first face picture of acquisition
It is specifically limited, the labeling position information can be obtained by way of any mark facial contour feature point of the prior art
Arrive, can also be obtained by mask method provided by the invention, in the specific implementation, those skilled in the art can be according to reality
Demand is selected.
Step S102：The labeling position information of facial contour feature point in the first face picture is to the first face figure
Piece carries out 3D reconstructions, obtains the first 3D faceforms.
In this step, 3D reconstructions are carried out according to the first face picture and its labeling position information, obtain the first 3D face moulds
Type, to fully demonstrate the face information of the first face of corresponding first face picture, for example, the first face picture is the first face
Front view picture, then the information of the first face side face can not fully demonstrate out in the first face picture, and the first 3D
Faceform then adds depth information, can fully demonstrate the profile information of side face.Wherein, it is each in the first 3D faceforms
Individual pixel corresponds to a positional information respectively in a coordinate system, for example, position coordinates.
Step S103：First 3D faceforms are rotated into predetermined angle, obtain the 2nd 3D faceforms.
Before being labeled to the face picture of different angle, first have to collection to should angle face picture, and
In this step, then it is by the way that the first 3D faceforms are rotated, to obtain the faceform of different angle, i.e. the 2nd 3D
Faceform, thus the process of the face picture of collection different angle can be saved.And by setting different preset angles
Degree, or different numbers is rotated by identical predetermined angle, then it can obtain faceform at any angle.In addition, revolving
During turning the first 3D faceforms, keep coordinate system constant, to ensure the faceform of different angle or face picture
Normative reference is identical, and then causes the labeling position information of the face picture of corresponding different angle to have uniformity.
Specifically, the first 3D faceforms are rotated into predetermined angle, each pixel in the first 3D faceforms is relative
Predetermined angle is have rotated in pivot, according to the positional information of each pixel in the first 3D faceforms and this is default
Angle, the positional information of each pixel in the 2nd 3D faceforms can be obtained.
Step S104：Determined according to the positional information of each pixel in the 2nd 3D faceforms in the 2nd 3D faceforms
Facial contour feature point 3D positional informations.
The positional information of each pixel in a coordinate system in the 2nd 3D faceforms, and according to facial contour
Characteristic point and the corresponding relation of each pixel in the 2nd 3D faceforms, determine that the facial contour in the 2nd 3D faceforms is special
Levy point 3D positional informations, and then can by it is obstructed manually mark excessively in a manner of obtain facial contour feature point 3D positions believe
Breath.
Wherein, the corresponding relation of each pixel can be according to first in facial contour feature point and the 2nd 3D faceforms
The corresponding relation of facial contour feature point and each pixel in the first 3D faceforms determines in 3D faceforms；And/or
Determined according to the positional information of each pixel in the 2nd 3D faceforms.
Step S105：2nd 3D faceforms are projected into 2D spaces, obtain the second face picture, and according to the 2nd 3D people
The 3D positional informations of facial contour feature point in face model determine the position of the facial contour feature point in the second face picture
Information.
2nd 3D faceforms are projected into 2D spaces, obtain the second face picture after corresponding rotation predetermined angle, will
Depth information in the 3D positional informations of facial contour feature point in 2nd 3D faceforms removes, and obtains facial contour feature
Positional information of the point in 2D spaces, the labeling position information of the facial contour feature point of as the second face picture.
As can be seen here, the mask method of the human face characteristic point provided using the present embodiment, existing facial contour can be based on
First face picture of the labeling position information of characteristic point carries out 3D reconstructions, the first 3D faceforms after reconstruction is rotated default
Angle obtains the 2nd 3D faceforms of different angle, and then overcomes in the prior art, it is necessary to resurvey different angle
The problem of face, save manpower and time；And determined according to the positional information of each pixel in the 2nd 3D faceforms
The 3D positional informations of facial contour feature point in 2nd 3D faceforms, the 2nd 3D faceforms are projected into 2D spaces, obtained
The second face picture after to corresponding rotation predetermined angle, by the 3D positions of the facial contour feature point in the 2nd 3D faceforms
Depth information in information removes, and obtains positional information of the facial contour feature point in 2D spaces, as the second face picture
Facial contour feature point labeling position information, realize the full-automatic of annotation process, and then reduce the human input of mark,
Improve the efficiency of mark.
Fig. 2 shows the flow chart of the mask method of human face characteristic point in accordance with another embodiment of the present invention.Such as Fig. 2 institutes
Show, this method comprises the following steps：
Step S201：Obtain the labeling position letter of the facial contour feature point in the first face picture and the first face picture
Breath.
The the first face figure and its labeling position information of the labeling position information of existing facial contour feature point are obtained, so as to
In the second face picture of the face that corresponding different angle is obtained according to first face picture, and it is easy to according to the mark position
Confidence breath carries out the mark of facial contour feature point to the second face picture, obtains the labeling position information of the second face picture.
Step S202：The labeling position information of facial contour feature point in the first face picture is to the first face figure
Piece carries out 3D reconstructions, obtains the first 3D faceforms.
The labeling position information of facial contour feature point in the first face picture, to corresponding to the first face picture
The information such as the face of the first face and the positional structure of face contour, the angle of the first face is analyzed.For example, according to left and right
Whether the face of labeling position information analysis first of the contour feature point of eye is positive face；Then according to analysis result to the first face
Picture carries out 3D reconstructions, obtains the first 3D faceforms.
Wherein, the pixel in the first 3D faceforms is divided into two classes：The first kind is corresponding with facial contour feature point
Pixel, for example, the pixel of corresponding face contour feature point, and/or, the pixel of corresponding face contour characteristic point；Second
Class is common pixel, i.e., pixel not corresponding with facial contour feature point.Also, by facial contour feature o'clock first
Positional information in 3D faceforms is designated as 3D positional informations, and the 3D positional informations include labeling position information and depth is believed
Breath, the labeling position information and depth information form coordinate position of each facial contour feature point in three-dimensional coordinate, example
Such as, the labeling position information of facial contour feature point 1 is (x1, y1), the pixel a in the first 3D faceforms is correspondence profile
The pixel of characteristic point 1, pixel a positional information is (x1, y1, z1), then the 3D positional informations of facial contour feature point 1 are
(x1, y1, z1), wherein z1For depth information；The positional information of second class pixel is seat of each pixel in three-dimensional coordinate
Cursor position.
Step S203：First 3D faceforms are rotated into predetermined angle by pivot of default center point, obtain second
3D faceforms.
This step, by the way that the first 3D faceforms are rotated into predetermined angle by pivot of default center point, obtain not
The 2nd 3D faceforms of the angle of the first face are same as, and then the first face picture of existing first angle can be utilized,
The 2nd 3D faceforms of second angle are obtained, therefore the process of the face picture of collection different angle can be saved.Wherein, in advance
If central point can be the arbitrfary point in the first 3D faceforms, it is generally the case that for the ease of calculating the 2nd 3D faceforms
In each pixel positional information, point default center point being defined as on facial symmetry axle, or, by default center point
It is defined as the origin of coordinates.Meanwhile the direction of rotation can be determined according to the demand of mark.
In addition, in the present embodiment, the face in the first face picture and the first 3D faceforms is to be in first angle
It is existing；Face in second face picture and the 2nd 3D faceforms is presented with second angle；First angle and second angle it
Difference is predetermined angle.
Step S204：Determined according to the positional information of default center point and predetermined angle each in the 2nd 3D faceforms
The positional information of pixel.
After obtaining the 2nd 3D faceforms, the positional information of each pixel in the 2nd 3D faceforms is determined, so as to root
According to the positional information of each pixel, and the corresponding relation of facial contour feature point and each pixel, the 2nd 3D people is determined
The 3D positional informations of facial contour feature point in face model.
Specifically, according to the positional information of default center point, predetermined angle, direction of rotation and/or each pixel
Positional information in one 3D faceforms determines the positional information of each pixel in the 2nd 3D faceforms.For example, sit
Origin is marked in two centers of the first 3D faceforms, default center point is also two centers, with the first 3D faces
Model is rotated clockwise 60 degree, if pixel b positional information is (4,0,0) in the first 3D faceforms, then the 2nd 3D
In faceform pixel b positional information for (2,0,).With this principle, each pixel in the 2nd 3D faceforms is determined
The positional information of point, optionally, in order to simplify the positional information for determining each pixel in the 2nd 3D faceforms, rotation can be introduced
Torque battle array is calculated.
Step S205：Determined according to the positional information of each pixel in the 2nd 3D faceforms in the 2nd 3D faceforms
Facial contour feature point 3D positional informations.
According to the positional information of each pixel in the 2nd 3D faceforms, and according to facial contour feature point and second
The corresponding relation of each pixel in 3D faceforms, determine the 3D positions of the facial contour feature point in the 2nd 3D faceforms
Information, so can by it is obstructed manually mark excessively in a manner of obtain the 3D positional informations of facial contour feature point.
Wherein, similar with the pixel in the first 3D faceforms, the pixel in the 2nd 3D faceforms is also classified into two
Class：The first kind is pixel corresponding with facial contour feature point, for example, face contour feature point, and/or, face contour is special
Sign point；Second class is common pixel, i.e., pixel not corresponding with facial contour feature point.In the present invention to facial contour
In the scheme that characteristic point is labeled, the positional information of first kind pixel is mainly to determine, that is, determines the 2nd 3D faceforms
In facial contour feature point 3D positional informations.
Specifically, according to the difference of facial contour feature point and the corresponding relation of each pixel, by the 2nd 3D face moulds
The 3D positional informations of facial contour feature point in type are divided into two parts to determine respectively：
Part I, it is determined that the 3D positional informations of corresponding face contour feature point.According to each in the 2nd 3D faceforms
The positional information of pixel, determine the 3D positional informations of face contour feature point in the 2nd 3D faceforms；Wherein, the 2nd 3D people
Face contour feature point in face model in face contour feature point and the first face picture corresponds.Specifically, face wheel
The corresponding relation of wide characteristic point and the first 3D faceforms and the pixel in the 2nd 3D faceforms is fixed, simply pixel
The positional information of point is changed, and accordingly, the 3D positional informations of face contour feature point can also change therewith.Fig. 3 is shown
The 3D positional informations of facial contour feature point in determination the 2nd 3D faceforms of a specific embodiment of the invention are shown
It is intended to.As shown in figure 3, the left side is the first 3D faceforms in figure, the first 3D faceforms rotate horizontally predetermined angle, obtain the right side
The 2nd 3D faceforms on side, the eyebrow outline characteristic point 1 of the first face picture is corresponding to the pixel in the first 3D faceforms
Point b, then in the 2nd 3D faceforms, pixel b still be to should identical eyebrow outline characteristic point 1 pixel, simply
The 3D positional informations of eyebrow outline characteristic point 1 are changed, for example, be changed into by (4,0,0) (2,0,).Therefore, at this
In embodiment, then according to face contour feature point in the first 3D faceforms corresponding pixel, and according to the pixel
Positional information in the 2nd 3D faceforms, it is determined that the 3D positional informations of corresponding face contour feature point.
Part II, determine the 3D positional informations of face contour characteristic point.According to each pixel in the 2nd 3D faceforms
The positional information of point, determines face contour characteristic point and its 3D positional informations in the 2nd 3D faceforms.Specifically, generally come
Say, when face contour characteristic point refers to face face, the characteristic point on the outermost contour line of face, it is seen then that with face
Angle is different, face contour characteristic point and the corresponding relation meeting of the first 3D faceforms and the pixel in the 2nd 3D faceforms
Change, i.e., corresponding relation is unfixed.Still by taking Fig. 3 as an example, pixel a is to correspond to shape of face wheel in the first 3D faceforms
The pixel of wide characteristic point 2, but in the 2nd 3D faceforms, pixel a is no longer on the outermost contour line of face, accordingly
, the pixel of corresponding face contour characteristic point 2 is moved to right to pixel c by pixel a；Similarly, corresponding face contour characteristic point 3
Pixel moved to right by pixel d to pixel e.Therefore, in the present embodiment, then according to each picture in the 2nd 3D faceforms
The positional information of vegetarian refreshments, for example, the coordinate value of each pixel, determines face contour characteristic point and determine face contour feature
The 3D positional informations of point.
More specifically, determined according to the size of the coordinate value of each pixel in the 2nd 3D faceforms and variation tendency
Multiple pixels on face contour line, and, with reference to the 3D positional informations of face contour characteristic point in the first 3D faceforms,
The pixel of face contour characteristic point is corresponded to from the plurality of pixel point selection, the pixel is defined as face contour characteristic point.
By taking Fig. 3 as an example, it is assumed that vertically downward direction is the positive direction of the longitudinal axis, and horizontal direction to the right is the positive direction of transverse axis, then one
The mode of kind of the corresponding face contour characteristic point 3 of selection for：The coordinate value of each pixel in the 2nd 3D faceforms
Size and variation tendency determine multiple pixels on face mask line；Then according to face contour in the first 3D faceforms
The ordinate value of ordinate value, i.e. pixel d in the 3D positional informations of characteristic point 3, multiple pixels on face contour line
Some pixels of ordinate value identical with pixel d are searched in point, select abscissa value minimum from some pixels
Pixel e, pixel e is defined as corresponding in the 2nd 3D faceforms to the pixel of face contour characteristic point 3.It is determined that
After face contour characteristic point, according to positional information of the pixel in the 2nd 3D faceforms corresponding to face contour characteristic point
Determine the 3D positional informations of face contour characteristic point.For example, pixel e coordinate value is defined as face contour characteristic point 3
3D positional informations.
Step S206：2nd 3D faceforms are projected into 2D spaces, obtain the second face picture, and according to the 2nd 3D people
The 3D positional informations of facial contour feature point in face model determine the position of the facial contour feature point in the second face picture
Information.
2nd 3D faceforms are projected into 2D spaces, obtain the second face picture after corresponding rotation predetermined angle, will
Depth information in the 3D positional informations of facial contour feature point in 2nd 3D faceforms removes, and obtains facial contour feature
Positional information of the point in 2D spaces, the labeling position information of the facial contour feature point of as the second face picture.
As can be seen here, the mask method of the human face characteristic point provided using the present embodiment, existing facial contour can be based on
First face picture of the labeling position information of characteristic point carries out 3D reconstructions, the first 3D faceforms after reconstruction is rotated default
Angle obtains the 2nd 3D faceforms of different angle, and then overcomes in the prior art, it is necessary to resurvey different angle
The problem of face, save manpower and time；2nd 3D people is determined according to the positional information of default center point and predetermined angle
The positional information of each pixel in face model, then according to the picture in the faceform of facial contour feature point and different angle
The difference of the corresponding relation of vegetarian refreshments, the 3D positional informations of the facial contour feature point determined in the 2nd 3D faceforms are divided into really
Determine the 3D positional informations of face contour feature point and determine the 3D positional informations of face contour characteristic point；By the 2nd 3D face moulds
Type projects to 2D spaces, obtains the second face picture after corresponding rotation predetermined angle, by the face in the 2nd 3D faceforms
Depth information in the 3D positional informations of contour feature point removes, and obtains position letter of the facial contour feature point in 2D spaces
Breath, the labeling position information of the facial contour feature point of as the second face picture, realizes the full-automatic of annotation process, and then subtract
Lack the human input of mark, improve the efficiency of mark.
The mask method of the human face characteristic point provided using above method embodiment of the present invention, can obtain second angle people
The labeling position information of the facial contour feature point of face, if predetermined angle is different, or the angle of the first face is different, then can obtain
To the labeling position information of each different angle face；And rotated obtained all angles face of the invention and corresponding mark
Note positional information, training sample can be used as to be trained, make training sample data more comprehensively, with obtain being applied to it is live,
The positioning feature point algorithm of the applications such as camera, U.S. face, and then make it that the positioning feature point algorithm that training obtains is more accurate, therefore energy
Enough real-time facial contour feature points more accurately positioned in the application such as live, camera, U.S. face, for example, accurately identifying
Lip, it so can aid in and realize some specific functions in such applications, for example, carrying out makeup to face.
Fig. 4 shows the functional block diagram of the annotation equipment of human face characteristic point according to an embodiment of the invention.Such as Fig. 4 institutes
Show, the device includes：Acquisition module 401, rebuild module 402, processing module 403, the first determining module 404, projection module 405
And labeling module 406.
Acquisition module 401, suitable for obtaining the mark of the facial contour feature point in the first face picture and the first face picture
Note positional information；
Module 402 is rebuild, the labeling position information suitable for the facial contour feature point in the first face picture is to the
One face picture carries out 3D reconstructions, obtains the first 3D faceforms；
Processing module 403, suitable for the first 3D faceforms are rotated into predetermined angle, obtain the 2nd 3D faceforms；
First determining module 404, suitable for determining second according to the positional information of each pixel in the 2nd 3D faceforms
The 3D positional informations of facial contour feature point in 3D faceforms；
Projection module 405, suitable for the 2nd 3D faceforms are projected into 2D spaces, obtain the second face picture；
Labeling module 406, the 3D positional informations suitable for the facial contour feature point in the 2nd 3D faceforms determine
The positional information of facial contour feature point in second face picture.
Fig. 5 shows the functional block diagram of the annotation equipment of human face characteristic point in accordance with another embodiment of the present invention.Such as Fig. 5
Shown, on the basis of Fig. 4, the device also includes：Second determining module 501.
Face in first face picture and the first 3D faceforms is presented with first angle；Second face picture and
Face in two 3D faceforms is presented with second angle；The difference of first angle and second angle is predetermined angle.
Processing module 403 is further adapted for：First 3D faceforms are rotated using default center point as pivot and preset
Angle, obtain the 2nd 3D faceforms.
Second determining module 501, the 2nd 3D people is determined suitable for the positional information according to default center point and predetermined angle
The positional information of each pixel in face model.
First determining module 404 is further adapted for：
According to the positional information of each pixel in the 2nd 3D faceforms, face profile in the 2nd 3D faceforms is determined
The 3D positional informations of characteristic point；Wherein, the face in the 2nd 3D faceforms in face contour feature point and the first face picture
Contour feature point corresponds；
And the positional information according to each pixel in the 2nd 3D faceforms, determine face in the 2nd 3D faceforms
Type contour feature point and its 3D positional informations.
Concrete structure and operation principle on above-mentioned modules can refer to the description of corresponding steps in embodiment of the method,
Here is omitted.
The embodiment of the present application provides a kind of nonvolatile computer storage media, and computer-readable storage medium is stored with least
One executable instruction, the computer executable instructions can perform the mark side of the human face characteristic point in above-mentioned any means embodiment
Method.
Fig. 6 shows a kind of structural representation of computing device according to embodiments of the present invention, the specific embodiment of the invention
The specific implementation to computing device does not limit.
As shown in fig. 6, the computing device can include：Processor (processor) 602, communication interface
(Communications Interface) 604, memory (memory) 606 and communication bus 608.
Wherein：
Processor 602, communication interface 604 and memory 606 complete mutual communication by communication bus 608.
Communication interface 604, for being communicated with the network element of miscellaneous equipment such as client or other servers etc..
Processor 602, for configuration processor 610, it can specifically perform the mask method embodiment of above-mentioned human face characteristic point
In correlation step.
Specifically, program 610 can include program code, and the program code includes computer-managed instruction.
Processor 602 is probably central processor CPU, or specific integrated circuit ASIC (Application
Specific Integrated Circuit), or it is arranged to implement the integrated electricity of one or more of the embodiment of the present invention
Road.The one or more processors that computing device includes, can be same type of processor, such as one or more CPU；Also may be used
To be different types of processor, such as one or more CPU and one or more ASIC.
Memory 606, for depositing program 610.Memory 606 may include high-speed RAM memory, it is also possible to also include
Nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.
Program 610 specifically can be used for so that processor 602 performs following operation：
Obtain the labeling position information of the facial contour feature point in the first face picture and the first face picture；
The labeling position information of facial contour feature point in the first face picture carries out 3D to the first face picture
Rebuild, obtain the first 3D faceforms；
First 3D faceforms are rotated into predetermined angle, obtain the 2nd 3D faceforms；
The face wheel in the 2nd 3D faceforms is determined according to the positional information of each pixel in the 2nd 3D faceforms
The 3D positional informations of wide characteristic point；
2nd 3D faceforms are projected into 2D spaces, obtain the second face picture, and according in the 2nd 3D faceforms
The 3D positional informations of facial contour feature point determine the positional information of the facial contour feature point in the second face picture.
In a kind of optional mode：Face in first face picture and the first 3D faceforms is to be in first angle
It is existing；Face in second face picture and the 2nd 3D faceforms is presented with second angle；First angle and second angle it
Difference is predetermined angle.
In a kind of optional mode, program 610 can specifically be further used for so that processor 602 performs following behaviour
Make：First 3D faceforms are rotated into predetermined angle by pivot of default center point, obtain the 2nd 3D faceforms.
In a kind of optional mode, program 610 can specifically be further used for so that processor 602 performs following behaviour
Make：Believe the position that each pixel in 2nd 3D faceforms is determined according to the positional information of default center point and predetermined angle
Breath.
In a kind of optional mode, program 610 can specifically be further used for so that processor 602 performs following behaviour
Make：
According to the positional information of each pixel in the 2nd 3D faceforms, face profile in the 2nd 3D faceforms is determined
The 3D positional informations of characteristic point；Wherein, the face in the 2nd 3D faceforms in face contour feature point and the first face picture
Contour feature point corresponds；
And the positional information according to each pixel in the 2nd 3D faceforms, determine face in the 2nd 3D faceforms
Type contour feature point and its 3D positional informations.
Algorithm and display be not inherently related to any certain computer, virtual system or miscellaneous equipment provided herein.
Various general-purpose systems can also be used together with teaching based on this.As described above, required by constructing this kind of system
Structure be obvious.In addition, the present invention is not also directed to any certain programmed language.It should be understood that it can utilize various
Programming language realizes the content of invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the specification that this place provides, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice in the case of these no details.In some instances, known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it will be appreciated that in order to simplify the disclosure and help to understand one or more of each inventive aspect,
Above in the description to the exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention：I.e. required guarantor
The application claims of shield features more more than the feature being expressly recited in each claim.It is more precisely, such as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following embodiment are expressly incorporated in the embodiment, wherein each claim is in itself
Separate embodiments all as the present invention.
Those skilled in the art, which are appreciated that, to be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more equipment different from the embodiment.Can be the module or list in embodiment
Member or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement or
Sub-component.In addition at least some in such feature and/or process or unit exclude each other, it can use any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, summary and accompanying drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (including adjoint power
Profit requires, summary and accompanying drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
Replace.
In addition, it will be appreciated by those of skill in the art that although some embodiments in this include institute in other embodiments
Including some features rather than further feature, but the combination of the feature of different embodiments means to be in the scope of the present invention
Within and form different embodiments.For example, in the following claims, embodiment claimed it is any it
One mode can use in any combination.
The all parts embodiment of the present invention can be realized with hardware, or to be run on one or more processor
Software module realize, or realized with combinations thereof.It will be understood by those of skill in the art that it can use in practice
Microprocessor or digital signal processor (DSP) are realized in the annotation equipment of human face characteristic point according to embodiments of the present invention
Some or all parts some or all functions.The present invention is also implemented as being used to perform side as described herein
The some or all equipment or program of device (for example, computer program and computer program product) of method.It is such
Realizing the program of the present invention can store on a computer-readable medium, or can have the shape of one or more signal
Formula.Such signal can be downloaded from internet website and obtained, and either be provided or with any other shape on carrier signal
Formula provides.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of some different elements and being come by means of properly programmed computer real
It is existing.In if the unit claim of equipment for drying is listed, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and run after fame
Claim.
Claims (10)
1. a kind of mask method of human face characteristic point, including：
Obtain the labeling position information of the facial contour feature point in the first face picture and first face picture；
The labeling position information of facial contour feature point in first face picture is entered to first face picture
Row 3D is rebuild, and obtains the first 3D faceforms；
The first 3D faceforms are rotated into predetermined angle, obtain the 2nd 3D faceforms；
The people in the 2nd 3D faceforms is determined according to the positional information of each pixel in the 2nd 3D faceforms
The 3D positional informations of face contour feature point；
The 2nd 3D faceforms are projected into 2D spaces, obtain the second face picture, and according to the 2nd 3D face moulds
The 3D positional informations of facial contour feature point in type determine the position of the facial contour feature point in second face picture
Information.
2. the method according to claim 11, wherein, the people in first face picture and the first 3D faceforms
Face is presented with first angle；Face in second face picture and the 2nd 3D faceforms is to be in second angle
It is existing；The difference of the first angle and the second angle is the predetermined angle.
3. method according to claim 1 or 2, wherein, it is described that the first 3D faceforms are rotated into predetermined angle, obtain
It is specially to the 2nd 3D faceforms：The first 3D faceforms are rotated into preset angle by pivot of default center point
Degree, obtains the 2nd 3D faceforms.
4. the method according to claim 11, wherein, in the position according to each pixel in the 2nd 3D faceforms
Before information determines the 3D positional informations of the facial contour feature point in the 2nd 3D faceforms, methods described also includes：
The positional information of each pixel in the 2nd 3D faceforms is determined according to the positional information of default center point and predetermined angle.
5. according to the method any one of claim 1-4, wherein, it is described according to each in the 2nd 3D faceforms
The positional information of pixel determines that the 3D positional informations of the facial contour feature point in the 2nd 3D faceforms are further wrapped
Include：
According to the positional information of each pixel in the 2nd 3D faceforms, face in the 2nd 3D faceforms are determined
The 3D positional informations of contour feature point；Wherein, face contour feature point and the first face picture in the 2nd 3D faceforms
In face contour feature point correspond；
And the positional information according to each pixel in the 2nd 3D faceforms, determine the 2nd 3D faceforms
Middle face contour characteristic point and its 3D positional informations.
6. a kind of annotation equipment of human face characteristic point, including：
Acquisition module, suitable for obtaining the mark position of the facial contour feature point in the first face picture and first face picture
Confidence ceases；
Module is rebuild, the labeling position information suitable for the facial contour feature point in first face picture is to described the
One face picture carries out 3D reconstructions, obtains the first 3D faceforms；
Processing module, suitable for the first 3D faceforms are rotated into predetermined angle, obtain the 2nd 3D faceforms；
First determining module, suitable for determining described second according to the positional information of each pixel in the 2nd 3D faceforms
The 3D positional informations of facial contour feature point in 3D faceforms；
Projection module, suitable for the 2nd 3D faceforms are projected into 2D spaces, obtain the second face picture；
Labeling module, suitable for described in the 3D positional informations determination of the facial contour feature point in the 2nd 3D faceforms
The positional information of facial contour feature point in second face picture.
7. device according to claim 6, wherein, the people in first face picture and the first 3D faceforms
Face is presented with first angle；Face in second face picture and the 2nd 3D faceforms is to be in second angle
It is existing；The difference of the first angle and the second angle is the predetermined angle.
8. the device according to claim 6 or 7, wherein, the processing module is further adapted for：By the first 3D faces
Model rotates predetermined angle by pivot of default center point, obtains the 2nd 3D faceforms.
9. a kind of computing device, including：Processor, memory, communication interface and communication bus, the processor, the storage
Device and the communication interface complete mutual communication by the communication bus；
The memory is used to deposit an at least executable instruction, and the executable instruction makes the computing device such as right will
Ask and operated corresponding to the mask method of the human face characteristic point any one of 1-5.
10. a kind of computer-readable storage medium, an at least executable instruction, the executable instruction are stored with the storage medium
Make operation corresponding to the mask method of human face characteristic point of the computing device as any one of claim 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711351407.9A CN107832751A (en) | 2017-12-15 | 2017-12-15 | Mask method, device and the computing device of human face characteristic point |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711351407.9A CN107832751A (en) | 2017-12-15 | 2017-12-15 | Mask method, device and the computing device of human face characteristic point |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107832751A true CN107832751A (en) | 2018-03-23 |
Family
ID=61644920
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711351407.9A Pending CN107832751A (en) | 2017-12-15 | 2017-12-15 | Mask method, device and the computing device of human face characteristic point |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107832751A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086798A (en) * | 2018-07-03 | 2018-12-25 | 迈吉客科技（北京）有限公司 | A kind of data mask method and annotation equipment |
| CN111695628A (en) * | 2020-06-11 | 2020-09-22 | 北京百度网讯科技有限公司 | Key point marking method and device, electronic equipment and storage medium |
| CN112101257A (en) * | 2020-09-21 | 2020-12-18 | 北京字节跳动网络技术有限公司 | Training sample generation method, image processing method, device, equipment and medium |
| WO2021003964A1 (en) * | 2019-07-05 | 2021-01-14 | 深圳云天励飞技术有限公司 | Method and apparatus for face shape recognition, electronic device and storage medium |
| CN113128320A (en) * | 2020-01-16 | 2021-07-16 | 浙江舜宇智能光学技术有限公司 | Face living body detection method and device based on TOF camera and electronic equipment |
| CN114398118A (en) * | 2021-12-21 | 2022-04-26 | 深圳市易图资讯股份有限公司 | Intelligent positioning system and method for smart city based on space anchor |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070152037A1 (en) * | 2005-12-29 | 2007-07-05 | Industrial Technology Research Institute | Three-dimensional face recognition system and method |
| CN101320484A (en) * | 2008-07-17 | 2008-12-10 | 清华大学 | Three-dimensional human face recognition method based on human face full-automatic positioning |
| CN104036546A (en) * | 2014-06-30 | 2014-09-10 | 清华大学 | Method for carrying out face three-dimensional reconstruction at any viewing angle on basis of self-adaptive deformable model |
| CN105184283A (en) * | 2015-10-16 | 2015-12-23 | 天津中科智能识别产业技术研究院有限公司 | Method and system for marking key points in human face images |
| CN106022267A (en) * | 2016-05-20 | 2016-10-12 | 北京师范大学 | Automatic positioning method of weak feature point of three-dimensional face model |
| CN106203400A (en) * | 2016-07-29 | 2016-12-07 | 广州国信达计算机网络通讯有限公司 | A kind of face identification method and device |
| CN107146199A (en) * | 2017-05-02 | 2017-09-08 | 厦门美图之家科技有限公司 | A kind of fusion method of facial image, device and computing device |
| CN107423689A (en) * | 2017-06-23 | 2017-12-01 | 中国科学技术大学 | Intelligent interactive face key point mask method |
-
2017
- 2017-12-15 CN CN201711351407.9A patent/CN107832751A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070152037A1 (en) * | 2005-12-29 | 2007-07-05 | Industrial Technology Research Institute | Three-dimensional face recognition system and method |
| CN101320484A (en) * | 2008-07-17 | 2008-12-10 | 清华大学 | Three-dimensional human face recognition method based on human face full-automatic positioning |
| CN104036546A (en) * | 2014-06-30 | 2014-09-10 | 清华大学 | Method for carrying out face three-dimensional reconstruction at any viewing angle on basis of self-adaptive deformable model |
| CN105184283A (en) * | 2015-10-16 | 2015-12-23 | 天津中科智能识别产业技术研究院有限公司 | Method and system for marking key points in human face images |
| CN106022267A (en) * | 2016-05-20 | 2016-10-12 | 北京师范大学 | Automatic positioning method of weak feature point of three-dimensional face model |
| CN106203400A (en) * | 2016-07-29 | 2016-12-07 | 广州国信达计算机网络通讯有限公司 | A kind of face identification method and device |
| CN107146199A (en) * | 2017-05-02 | 2017-09-08 | 厦门美图之家科技有限公司 | A kind of fusion method of facial image, device and computing device |
| CN107423689A (en) * | 2017-06-23 | 2017-12-01 | 中国科学技术大学 | Intelligent interactive face key point mask method |
Non-Patent Citations (3)
| Title |
|---|
| SEONG-GYUN JEONG ET AL.: "Marked point process model for facial wrinkle detection", 《 2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)》 * |
| 刘杰锋 等: "《大洋非线性编辑实用教程 高级篇》", 31 October 2016, 北京：中国传媒大学出版社 * |
| 赵宁: "人脸特征点自动标注及表情生成", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086798A (en) * | 2018-07-03 | 2018-12-25 | 迈吉客科技（北京）有限公司 | A kind of data mask method and annotation equipment |
| WO2021003964A1 (en) * | 2019-07-05 | 2021-01-14 | 深圳云天励飞技术有限公司 | Method and apparatus for face shape recognition, electronic device and storage medium |
| CN113128320A (en) * | 2020-01-16 | 2021-07-16 | 浙江舜宇智能光学技术有限公司 | Face living body detection method and device based on TOF camera and electronic equipment |
| CN113128320B (en) * | 2020-01-16 | 2023-05-16 | 浙江舜宇智能光学技术有限公司 | Human face living body detection method and device based on TOF camera and electronic equipment |
| CN111695628A (en) * | 2020-06-11 | 2020-09-22 | 北京百度网讯科技有限公司 | Key point marking method and device, electronic equipment and storage medium |
| CN111695628B (en) * | 2020-06-11 | 2023-05-05 | 北京百度网讯科技有限公司 | Key point labeling method and device, electronic equipment and storage medium |
| CN112101257A (en) * | 2020-09-21 | 2020-12-18 | 北京字节跳动网络技术有限公司 | Training sample generation method, image processing method, device, equipment and medium |
| CN112101257B (en) * | 2020-09-21 | 2022-05-31 | 北京字节跳动网络技术有限公司 | Training sample generation method, image processing method, device, equipment and medium |
| CN114398118A (en) * | 2021-12-21 | 2022-04-26 | 深圳市易图资讯股份有限公司 | Intelligent positioning system and method for smart city based on space anchor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107832751A (en) | Mask method, device and the computing device of human face characteristic point | |
| EP4120199A1 (en) | Image rendering method and apparatus, and electronic device and storage medium | |
| CN104376594B (en) | Three-dimensional face modeling method and device | |
| CN108875524A (en) | Gaze estimation method, device, system and storage medium | |
| CN107481218B (en) | Image aesthetic feeling evaluation method and device | |
| WO2021233017A1 (en) | Image processing method and apparatus, and device and computer-readable storage medium | |
| CN108320325A (en) | The generation method and device of dental arch model | |
| CN105139007B (en) | Man face characteristic point positioning method and device | |
| CN103617615A (en) | Radial distortion parameter obtaining method and obtaining device | |
| CN108876893A (en) | Method, apparatus, system and the computer storage medium of three-dimensional facial reconstruction | |
| CN107452061A (en) | Generation method, device, equipment and the computer-readable recording medium of building model based on oblique photograph technology | |
| US10922852B2 (en) | Oil painting stroke simulation using neural network | |
| US11423617B2 (en) | Subdividing a three-dimensional mesh utilizing a neural network | |
| CN107784321A (en) | Numeral paints this method for quickly identifying, system and computer-readable recording medium | |
| CN109300188A (en) | Threedimensional model processing method and processing device | |
| CN104299241A (en) | Remote sensing image significance target detection method and system based on Hadoop | |
| CN112132812B (en) | Certificate verification method and device, electronic equipment and medium | |
| CN112330815A (en) | Three-dimensional point cloud data processing method, device and equipment based on obstacle fusion | |
| CN108573192B (en) | Glasses try-on method and device matched with human face | |
| Xiao | Research on visual image texture rendering for artistic aided design | |
| WO2023005934A1 (en) | Data processing method and system, and electronic device | |
| CN113361380B (en) | Human body key point detection model training method, detection method and device | |
| CN114638867A (en) | Point cloud registration method and system based on feature extraction module and dual quaternion | |
| CN113593007A (en) | Single-view three-dimensional point cloud reconstruction method and system based on variational self-coding | |
| CN109658489B (en) | Three-dimensional grid data processing method and system based on neural network |
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 |
Application publication date: 20180323 |
|
| RJ01 | Rejection of invention patent application after publication |