CN107066919A - Pen tip position method for solving, equipment and computer-readable recording medium - Google Patents
Pen tip position method for solving, equipment and computer-readable recording medium Download PDFInfo
- Publication number
- CN107066919A CN107066919A CN201611188735.7A CN201611188735A CN107066919A CN 107066919 A CN107066919 A CN 107066919A CN 201611188735 A CN201611188735 A CN 201611188735A CN 107066919 A CN107066919 A CN 107066919A
- Authority
- CN
- China
- Prior art keywords
- coordinate
- image
- paper
- image coordinate
- point
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/32—Digital ink
Abstract
Embodiments of the present invention provide a kind of pen tip position method for solving, including：The first image for shooting when user clicks on first in paper by nib is obtained, known to described first point of paper coordinate；According to the transforming function transformation function of image information acquisition first in described first image；According to described first point of paper coordinate and the image coordinate of described first point of the first transforming function transformation function calculating, described first point of image coordinate is regard as nib image coordinate.The method of the present invention causes the pen tip position of smart pen is solved convenient, so as to significantly reduce amount of calculation.In addition, embodiments of the present invention provide a kind of pen tip position solving device.
Description
Technical field
Embodiments of the present invention are related to image processing field, more specifically, embodiments of the present invention are related to a kind of pen
Sharp position method for solving, equipment.
Background technology
This part is it is intended that the embodiments of the present invention stated in claims provide background or context.Herein
Description recognizes it is prior art not because not being included in this part.
Smart pen is a kind of electronic pen of built-in camera, and the code-point on paper can be continuously shot in writing, and then
Calculate person's handwriting.During using this kind of smart pen, user can traditionally writing style in the enterprising running hand of paper for being printed on code-point
Write, the written handwriting and writing process of user will all be recorded, and can be synchronized to immediately in other equipment, for inhomogeneity
The equipment application of type.
At present, there are some smart pens, written handwriting for smart pen and it is written during, the nib of smart pen
Image coordinate be the operation of whole smart pen key, due to the limitation of smart pen hardware, the image coordinate of the nib is without Faxian
Show on the image shot in writing process, so the solution of the image coordinate of nib, which turns into smart pen, can reduce the base of person's handwriting
The calculating correction of the image coordinate of nib or the calculating of nib track, are generally referred to as the solution of smart pen pen tip position, mesh by plinth
Preceding pen tip position is solved often using operations such as recursive calculation, angle rotation transformation corrections, and user's operation difficulty is big, amount of calculation
Greatly.
The content of the invention
But, for the reason for current technology and operation, the operation difficulty of existing pen tip position method for solving is big, calculates
It is complicated.
Therefore in the prior art, operation difficulty is big, and calculating complexity, this is very bothersome process.
Therefore, a kind of improved pen tip position method for solving is highly desirable to, so that simple to operate, amount of calculation is small.
In the present context, embodiments of the present invention are expected to provide a kind of pen tip position method for solving.
There is provided a kind of pen tip position method for solving in the first aspect of embodiment of the present invention, including：Obtain user
The first image for shooting when clicking on first in paper by nib, known to described first point of paper coordinate；According to described
The transforming function transformation function of image information acquisition first on first image；According to described first point of paper coordinate and the first transforming function transformation function meter
Described first point of image coordinate is calculated, nib image coordinate is obtained according to described first point of image coordinate.
In an embodiment of first aspect present invention, converted according to the image information acquisition first in described first image
Function includes：Image coordinate and paper coordinate that graphical analysis obtains at least four point in image are carried out to described first image；According to
The first change exchange the letters that paper coordinate is transformed to from image coordinate is calculated according to the image coordinate of at least four point, paper coordinate
Number.
In an embodiment of first aspect present invention, wherein it is saturating to obtain the first transforming function transformation function first including acquisition 3*3
Depending on transformation matrix；According to described first point of paper coordinate and the image coordinate bag of described first point of the first transforming function transformation function calculating
Include：The perspective transformation matrix is inverted and obtains the perspective transform inverse matrix；Described first point of image coordinate is equal to described
The paper coordinate that first perspective transform inverse matrix is multiplied by first point is multiplied by the first proportionality coefficient, and first proportionality coefficient is described
First perspective transform inverse matrix is multiplied by the inverse of the homogeneous item of first point of paper coordinate acquired results.
In the embodiment of first aspect present invention one, the above method also includes：Sat by clicking on other papers on paper
The known preset of mark, is corrected to the nib image coordinate.
In an embodiment of first aspect present invention, described be corrected to the nib image coordinate specifically includes：
Step one：When user clicks on the N points in paper by nib, the N images shot are obtained, the paper of the N points is sat
Mark is known；Step 2：According to the image information acquisition N transforming function transformation functions on the N images；Step 3：According to the N points
Paper coordinate and N transforming function transformation functions calculate the image coordinates of the N points, wherein N is the integer more than or equal to 2；In pen
During sharp position movement, repeating said steps one to step 3 calculate M image coordinate of pen tip position, and wherein M is positive integer；
According to first point of image coordinate and M image coordinate correction nib image coordinate.
In an embodiment of first aspect present invention, exchange the letters is become according to the image information acquisition N on the N images
Number includes：Image coordinate and paper coordinate that graphical analysis obtains at least four point in image are carried out to the N images；Foundation
The image coordinate of at least four point, paper coordinate calculate the N transforming function transformation functions that paper coordinate is transformed to from image coordinate.
In one embodiment of first aspect present invention, wherein it is saturating including the N for obtaining 3*3 to obtain N transforming function transformation functions
Depending on transformation matrix；The image coordinate that paper according to the N points sits the N transforming function transformation functions calculating N points includes：To described
N perspective transformation matrixs, which are inverted, obtains N perspective transform inverse matrixs；It is inverse that the image coordinate of the N points is equal to the N perspective transforms
Matrix Multiplication is multiplied by N proportionality coefficients with the paper coordinate of N points, and the N proportionality coefficients are the N perspective transform inverse matrixs
It is multiplied by the inverse of the homogeneous item of the paper coordinate acquired results of N points.
In one embodiment of first aspect present invention, according to first point of image coordinate and the M image coordinate
Correction nib image coordinate includes：Delete and X are obtained after the exceptional value in the M image coordinate and first point of image coordinate
Image coordinate, regard the average value of the X image coordinate as nib image coordinate；Or by first point of image coordinate and described
The average value of M image coordinate is used as nib image coordinate.
In one embodiment of first aspect present invention, any of the above-described method also includes：It is many during acquisition user writing
Individual measuring image；The corresponding multiple actual measurements of the multiple measuring image of image information acquisition according to the multiple measuring image become
Exchange the letters number；According to the multiple actual measurement transforming function transformation function and the nib image coordinate, multiple nib paper coordinates are obtained, according to institute
State multiple nib paper coordinates and obtain user handwriting.
In one embodiment of first aspect present invention, according to described in the image information acquisition of the multiple measuring image
The corresponding multiple actual measurement transforming function transformation functions of multiple measuring images include：Each image information analysis of multiple measuring images is obtained often
The image coordinate and paper coordinate of at least four point in individual image；Image coordinate and paper coordinate meter according at least four point
Calculate the corresponding multiple actual measurement transforming function transformation functions of the multiple measuring image for transforming to paper coordinate from image coordinate.
In one embodiment of first aspect present invention, the corresponding multiple actual measurement conversion of the multiple measuring image are obtained
Function includes the perspective transformation matrix for obtaining the corresponding 3*3 of the multiple measuring image；According to the multiple actual measurement transforming function transformation function
With the nib image coordinate, obtaining multiple nib paper coordinates includes：The multiple nib paper coordinate is equal to the nib
The perspective transformation matrix that image coordinate is multiplied by the corresponding 3*3 of the multiple measuring image is multiplied by corresponding proportionality coefficient, the ratio
Example coefficient is the inverse for the homogeneous item that the nib image coordinate is multiplied by corresponding perspective transformation matrix acquired results.
There is provided a kind of pen tip position solving device in the second aspect of embodiment of the present invention, including：Obtain single
Member, for obtaining the first image shot when user clicks on first in paper by nib, described first point of paper is sat
Mark is known；Processing unit, for according to the transforming function transformation function of image information acquisition first in described first image；Computing unit, is used
Described first point of image coordinate is calculated in the paper coordinate according to described first point and the first transforming function transformation function, according to described first
The image coordinate of point obtains nib image coordinate.
In an embodiment of second aspect of the present invention, processing unit to described first image specifically for carrying out image point
Analysis obtains the image coordinate and paper coordinate of at least four point in image；Image coordinate, paper according at least four point are sat
Mark calculates the first transforming function transformation function that paper coordinate is transformed to from image coordinate.
In an embodiment of second aspect of the present invention, first perspective transform square of the processing unit specifically for acquisition 3*3
Battle array；The computing unit is specific, and the perspective transform inverse matrix is obtained for being inverted to the perspective transformation matrix；Described first
The image coordinate of point is multiplied by the first proportionality coefficient equal to the paper coordinate that the first perspective transform inverse matrix is multiplied by first point, institute
State the homogeneous item that the first proportionality coefficient is the paper coordinate acquired results that the first perspective transform inverse matrix is multiplied by first point
It is reciprocal.
In an embodiment of second aspect of the present invention, said apparatus also includes：Unit is corrected, for by clicking on paper
Preset known to upper other paper coordinates, is corrected to the nib image coordinate.
In an embodiment of second aspect of the present invention, the correction unit is corrected to the nib image coordinate,
Specifically include：Step one：When user clicks on the N points in paper by nib, the N images shot, the N points are obtained
Paper coordinate known to；Step 2：According to the image information acquisition N transforming function transformation functions on the N images；Step 3：Foundation
The paper coordinate N transforming function transformation functions of the N points calculate the image coordinate of the N points, and wherein N is the integer more than or equal to 2；
When pen tip position is moved, repeating said steps one to step 3 calculate M image coordinate of pen tip position, and wherein M is just whole
Number；According to first point and M image coordinate correction nib image coordinate.
In an embodiment of second aspect of the present invention, exchange the letters is become according to the image information acquisition N on the N images
Number includes：Image coordinate and paper coordinate that graphical analysis obtains at least four point in image are carried out to the N images；Foundation
The image coordinate of at least four point, paper coordinate calculate the first transforming function transformation function that paper coordinate is transformed to from image coordinate.
In one embodiment of second aspect of the present invention, obtaining N transforming function transformation functions includes obtaining 3*3 N perspective changes
Change matrix；The image coordinate that paper according to the N points sits the N transforming function transformation functions calculating N points includes：It is saturating to the N
Inverted depending on transformation matrix and obtain N perspective transform inverse matrixs；The image coordinate of the N points is equal to the N perspective transforms against square
The paper coordinate that battle array is multiplied by N points is multiplied by N proportionality coefficients, and the N proportionality coefficients are that the N perspective transform inverse matrixs multiply
With the inverse of the homogeneous item of the paper coordinate acquired results of N points.
In one embodiment of second aspect of the present invention, according to first point of image coordinate and the M image coordinate
Correction nib image coordinate includes：Delete and X are obtained after the exceptional value in the M image coordinate and first point of image coordinate
Image coordinate, regard the average value of X image coordinate as nib image coordinate；Or first point of image coordinate and the M is individual
The average value of image coordinate is used as nib image coordinate.
In one embodiment of second aspect of the present invention, any of the above-described device also includes：Person's handwriting unit, is used for obtaining
Multiple measuring images when family is write；The multiple measuring image correspondence of image information acquisition according to the multiple measuring image
Multiple actual measurement transforming function transformation functions；According to the multiple actual measurement transforming function transformation function and the nib image coordinate, multiple nib paper are obtained
Areal coordinate, user handwriting is obtained according to the multiple nib paper coordinate.
In one embodiment of second aspect of the present invention, according to described in the image information acquisition of the multiple measuring image
The corresponding multiple actual measurement transforming function transformation functions of multiple measuring images include：Each image information analysis of multiple measuring images is obtained often
The image coordinate and paper coordinate of at least four point in individual image；Image coordinate and paper coordinate meter according at least four point
Calculate the corresponding multiple actual measurement transforming function transformation functions of the multiple measuring image for transforming to paper coordinate from image coordinate.
In one embodiment of second aspect of the present invention, the corresponding multiple actual measurement conversion of the multiple measuring image are obtained
Function includes the perspective transformation matrix for obtaining the corresponding 3*3 of the multiple measuring image；According to the multiple actual measurement transforming function transformation function
With the nib image coordinate, obtaining multiple nib paper coordinates includes：The multiple nib paper coordinate is equal to the nib
The perspective transformation matrix that image coordinate is multiplied by the corresponding 3*3 of the multiple measuring image is multiplied by corresponding proportionality coefficient, the ratio
Example coefficient is the inverse for the homogeneous item that the nib image coordinate is multiplied by corresponding perspective transformation matrix acquired results.
There is provided a kind of computer-readable recording medium in the third aspect of embodiment of the present invention, it is stored thereon with
Computer program, the program realizes any pen tip position method for solving that above-mentioned first aspect is provided when being executed by processor.
Only being needed user to click on a point according to embodiment of the present invention can be calculated nib image coordinate,
So its is simple to operate, in addition, this calculating needs to carry out perspective transform and has an X-rayed inverse transformation, its amount of calculation is small, so its
With simple to operate, the small advantage of amount of calculation.
Brief description of the drawings
Detailed description below, above-mentioned and other mesh of exemplary embodiment of the invention are read by reference to accompanying drawing
, feature and advantage will become prone to understand.In the accompanying drawings, if showing the present invention's by way of example, and not by way of limitation
Dry embodiment, wherein：
Fig. 1 schematically shows the structure of smart pen and shoots schematic diagram；
Fig. 2A schematically shows the flow chart of pen tip position method for solving according to an embodiment of the invention；
Fig. 2 B schematically show the first image schematic diagram according to an embodiment of the invention；
Fig. 2 C schematically show the image schematic diagram after perspective transform according to an embodiment of the invention；
Fig. 3 schematically shows the flow chart of pen tip position method for solving according to another embodiment of the present invention；
Fig. 4 schematically shows the structural representation of the pen tip position solving device according to further embodiment of this invention；
Fig. 5 schematically shows the hardware architecture diagram of smart pen device according to yet another embodiment of the invention；
Fig. 6 schematically shows the structural representation of the computer-readable recording medium according to latter embodiment of the present invention
Figure；
In the accompanying drawings, identical or corresponding label represents identical or corresponding part.
Embodiment
The principle and spirit of the present invention is described below with reference to some illustrative embodiments.It should be appreciated that providing this
A little embodiments are used for the purpose of better understood when those skilled in the art and then realizing the present invention, and not with any
Mode limits the scope of the present invention.On the contrary, these embodiments are provided so that the disclosure is more thorough and complete, and energy
It is enough that the scope of the present disclosure is intactly conveyed into those skilled in the art.
Art technology technical staff knows, embodiments of the present invention can be implemented as a kind of system, device, equipment,
Method or computer program product.Therefore, the disclosure can be implemented as following form, i.e.,：It is complete hardware, complete soft
Part (including firmware, resident software, microcode etc.), or the form that hardware and software is combined.
According to the embodiment of the present invention, it is proposed that a kind of method and apparatus.
Herein, it is to be understood that involved term is represented.In addition, any number of elements in accompanying drawing is used
It is unrestricted in example, and it is any name be only used for distinguish, without any limitation.
Below with reference to the principle and spirit of some representative embodiments of the present invention, in detail the explaination present invention.
Summary of the invention
The inventors discovered that, because the hardware configuration of each smart pen is fixed, for each smart pen, its
The position of camera and nib is relatively fixed, so for the image that camera is shot, its nib is in the position of image
It is relatively fixed, but for different smart pens, because the position of camera and nib is differed, so needing to nib
Image coordinate calculated.The present invention be also based on the image coordinate of the nib of single smart pen camera shoot it is multiple
The characteristics of coordinate in picture is consistent solves come the pen tip position to smart pen.
After the general principle of the present invention is described, lower mask body introduces the various non-limiting embodiment party of the present invention
Formula.
Application scenarios overview
With reference first to Fig. 1, Fig. 1 is a kind of structure of smart pen and shoots schematic diagram, as shown in figure 1, the smart pen bag
Camera 1 and nib 2 are included, its nib 2 is in motion, and camera 1 shoots picture, as shown in the dash area in Fig. 1, the present invention
Technical scheme be solve nib image coordinate, and then can according to the image coordinate of the fixation solve nib paper sit
Mark.
Illustrative methods
With reference to the application scenarios of figure, the side being used for according to exemplary embodiment of the invention is described with reference to figure
Method.Understand spirit and principles of the present invention it should be noted that above-mentioned application scenarios are for only for ease of and show, it is of the invention
Embodiment is unrestricted in this regard.On the contrary, embodiments of the present invention can apply to applicable any scene.
Refering to Fig. 2A, such as Fig. 2A is the method for an example of the present invention, and as shown in Figure 2 A, this method passes through such as Fig. 1 institutes
The smart pen shown is performed, and this method as shown in Figure 2 A, comprises the following steps：
Step S201, smart pen obtain the first image shot when user clicks on first in paper by nib, its
In known to first point of the paper coordinate.
The first image in above-mentioned steps S201 is described for convenience as shown in Figure 2 B, here sits first point of paper
Labeled as (X, Y).Blockage (code-point pattern) in photo produces different deformation because of the angle difference of camera lens, and now
Nib image is not in the first field of view, its image coordinate correspondence (x0, y0).
Step S202, smart pen are according to the transforming function transformation function of image information acquisition first on the first image.
The first transforming function transformation function in step S202 can include 3*3 the first perspective transformation matrix, the first perspective of the 3*3
The acquisition modes of transformation matrix and the first proportionality coefficient are specifically as follows：
Sat by the image of paper coordinate and 4 points that at least four point is obtained to the first graphical analysis as shown in Figure 2 B
Mark, the paper can be code paper, and certain paper can also be the paper of other properties, such as graph paper etc. paper.4 points
The point of quadrangle can be constituted for the line arbitrarily chosen from the plane of delineation, is defined by calculating facility." paper " is not limited to tradition
Paper plane, can be the arbitrary plane such as plastics, display screen.The image coordinate of above-mentioned 4 points can be by the first image
Analysis or measurement are directly obtained.In one embodiment, the paper coordinate of above-mentioned 4 points can be photographed by obtaining first
Coding pattern on image, the paper coordinate for obtaining respective point is calculated according to the preset rules of coding pattern.According at least four point
Paper coordinate and the image coordinates of 4 points calculate and obtain the first perspective transformation function H0, perspective transformation function H0 is one
3*3 matrix, can be directly substituted into and be tried to achieve by the paper coordinate of at least four point and the image coordinate of 4 points, specifically try to achieve method
It may refer to the acquisition perspective transform (English in rendering algorithm：Get Perspective Transform) function, above-mentioned perspective
The mathematic(al) representation of conversion is specifically as follows：
TPpaper=H0 × Pimage；
Wherein t is the first proportionality coefficient, and the first proportionality coefficient can be multiplied by first for the first perspective transform inverse matrix
The inverse of the homogeneous item of the paper coordinate acquired results of point, the first perspective transformation function of H0 positions, Pimage is the plane of delineation 3 × 1
Homogeneous image coordinate, homogeneous item (Section 3) be 1；Ppaper is the homogeneous paper coordinate of paper plane 3 × 1, homogeneous item the (the 3rd
) it is 1；T is the first proportionality coefficient, it is therefore an objective to which the homogeneous item for making Ppaper is 1.Sat for the image of any point of the plane of delineation
Pimage is marked, tPpaper can be obtained by being multiplied by after H0, the homogeneous item that final result is caused to this result divided by t is 1,
That obtain is exactly corresponding paper coordinate Ppaper of this on paper plane, wherein paper coordinate Ppaper preceding two correspondences paper
Face two-dimensional coordinate.
The paper coordinate picture that Fig. 2 B are obtained after perspective transform be Fig. 2 C shown in, wherein, nib coordinate (X, Y)
For the paper coordinate of nib.
In another embodiment, also can according to multiple points on image image coordinate and paper coordinate according to following pass
It is that formula calculates transforming function transformation function：Ppaper=H × Pimage, wherein H are transforming function transformation function.
Step S203, smart pen calculate according to first point of paper coordinate (X, Y) and the first transforming function transformation function and obtain at first point
Image coordinate, according to first point image coordinate obtain nib image coordinate.
Above-mentioned steps S203 implementation method is specifically as follows：Perspective transformation function H0 invert and obtains having an X-rayed inversion
Exchange the letters number H0-1, first point of image coordinate (x0, y0) can be equal to H0-1* (X, Y) * t.
Technical scheme as shown in Figure 2 A only needs user to click on a point can calculate to nib image coordinate
Arrive, so its is simple to operate, in addition, this, which is calculated, carries out perspective transform and perspective inverse transformation, its amount of calculation is smaller, so its
With simple to operate, the small advantage of amount of calculation.
Refering to Fig. 3, such as Fig. 3 is another exemplary method of the invention, as shown in figure 3, this method pass through it is as shown in Figure 1
Smart pen perform, this method further comprises by clicking on paper preset known to other paper coordinates, to nib
Image coordinate be corrected.As shown in figure 3, the following image to nib can also be included after method as shown in Figure 2 A
The step of coordinate is corrected：
Step S301, when user by nib click on paper in N points when, smart pen obtain shoot N images, institute
Known to the paper coordinate for stating N points.
Step S302, smart pen are according to the image information acquisition N transforming function transformation functions on the N images.
The method that the mode of acquisition N transforming function transformation functions in above-mentioned steps S302 may refer to above-mentioned steps S202, here
Do not repeating.
Step S303, smart pen are marked with according to the paper of the N points and N transforming function transformation functions calculate the figure of the N points
As coordinate, wherein N is the integer more than or equal to 2.
Smart pen in above-mentioned steps 303 is marked with according to the paper of the N points and N transforming function transformation functions calculate the N
The concrete mode of the image coordinate of point may refer to step S203 implementation method, not repeat here.
Step S304, when pen tip position is moved, repeating said steps S301 calculates the M of pen tip position to step S303
Individual image coordinate, the M is positive integer.
Step S305, smart pen are according to first point and M image coordinate correction nib image coordinate.
Above-mentioned steps S305 implementation method is specifically as follows：By first point of image coordinate and the M image coordinate
Average value be used as update nib image coordinate.Certainly can also be specifically in above-mentioned steps S305 implementation method：Delete institute
State and X image coordinate is obtained after the exceptional value in M image coordinate and first point of image coordinate, by the flat of X image coordinate
Average is used as renewal nib image coordinate.The judgement of above-mentioned exceptional value can have a variety of, for example, can be by the way that M image is sat
Mark and first point of image coordinate are respectively and the contrast of above-mentioned average value obtains deviation, and such as the deviation exceedes deviation threshold, it is determined that
For exceptional value, there can also be other judgment modes certainly, for example judged by variance etc., the present invention does not limit to above-mentioned
The concrete methods of realizing of judgment mode.
Optionally, the above method can also include after step S305：Obtain multiple measuring images during user writing；
The corresponding multiple actual measurement transforming function transformation functions of the multiple measuring image of image information acquisition according to the multiple measuring image；Foundation
The multiple actual measurement transforming function transformation function and the nib image coordinate, obtain multiple nib paper coordinates, according to the multiple nib
Paper coordinate obtains user handwriting.
Alternatively, wherein the multiple measuring image of image information acquisition according to the multiple measuring image is corresponding more
Individual actual measurement transforming function transformation function includes：At least four point in each image is obtained to each image information analysis of multiple measuring images
Image coordinate and paper coordinate；Image coordinate and paper coordinate according at least four point are calculated from image coordinate conversion
To the corresponding multiple actual measurement transforming function transformation functions of the multiple measuring image of paper coordinate.
Alternatively, wherein obtaining the corresponding multiple actual measurement transforming function transformation functions of the multiple measuring image includes obtaining the multiple
The corresponding 3*3 of measuring image perspective transformation matrix；According to the multiple actual measurement transforming function transformation function and the nib image coordinate, obtain
Multiple nib paper coordinates are taken to include：The multiple nib paper coordinate is multiplied by the multiple reality equal to the nib image coordinate
The corresponding 3*3 of altimetric image perspective transformation matrix is multiplied by corresponding proportionality coefficient, and the proportionality coefficient is the nib image coordinate
It is multiplied by the inverse of the homogeneous item of corresponding perspective transformation matrix acquired results.
Technical scheme as shown in Figure 3 only needs user to click on a point can calculate to nib image coordinate
Arrive, so its is simple to operate, in addition, this calculates the perspective transform carried out and perspective inverse transformation, its amount of calculation is small, so its
With simple to operate, the small advantage of amount of calculation.
Example devices
After the method for exemplary embodiment of the invention is described, next, with reference to Fig. 4 to exemplary reality of the invention
Apply the pen tip position solving device of mode, for realizing above-mentioned pen tip position method for solving, the technology art of equipment as shown in Figure 4
Language, concrete implementation mode and technique effect may refer to the description of embodiment as shown in Figure 2 or Figure 3.The smart pen is such as
Shown in Fig. 4, including：
Acquiring unit 401, for obtaining the first image shot when user clicks on first in paper by nib, institute
Known to the paper coordinate for stating at first point；
Processing unit 402, for according to the transforming function transformation function of image information acquisition first in described first image；
Computing unit 403, calculates at described first point for the paper coordinate according to described first point and the first transforming function transformation function
Image coordinate, according to described first point image coordinate obtain nib image coordinate.
Optionally, processing unit 402 obtains at least four in image specifically for carrying out graphical analysis to described first image
The image coordinate and paper coordinate of point；Image coordinate, paper coordinate according at least four point are calculated to be become from image coordinate
Change to the first transforming function transformation function of paper coordinate.
Optionally, wherein processing unit 402 specifically for obtain 3*3 the first perspective transformation matrix；
Computing unit 403 is specific, and the perspective transform inverse matrix is obtained for being inverted to the perspective transformation matrix；It is described
First point of image coordinate is multiplied by the first ratio system equal to the paper coordinate that the first perspective transform inverse matrix is multiplied by first point
Number, first proportionality coefficient is the homogeneous item for the paper coordinate acquired results that the first perspective transform inverse matrix is multiplied by first point
Inverse.
Optionally, wherein described device also includes：
Unit 404 is corrected, it is described that the nib image coordinate is corrected for being corrected to the nib image coordinate
Specifically, including：
Step one：When user clicks on the N points in paper by nib, the N images shot, the N points are obtained
Paper coordinate known to；
Step 2：According to the image information acquisition N transforming function transformation functions on the N images；
Step 3：Paper coordinate N transforming function transformation functions according to the N points calculate the image coordinate of the N points, wherein N
For the integer more than or equal to 2；
When pen tip position is moved, repeating said steps one to step 3 calculate M image coordinate of pen tip position；
According to first point and M image coordinate correction nib image coordinate.
Optionally, wherein including according to the image information acquisition N transforming function transformation functions on the N images：The N is schemed
The image coordinate and paper coordinate of at least four point in image are obtained as carrying out graphical analysis；Image according at least four point
Coordinate, paper coordinate calculate the first transforming function transformation function that paper coordinate is transformed to from image coordinate.
Optionally, wherein obtaining the N perspective transformation matrixs that N transforming function transformation functions include obtaining 3*3；According to the N points
Paper sit N transforming function transformation functions and calculate the image coordinates of the N points and include：The N perspective transformation matrixs are inverted, and it is saturating to obtain N
Depending on conversion inverse matrix；The image coordinate of the N points is equal to the paper coordinate that the N perspective transform inverse matrixs are multiplied by N points
N proportionality coefficients are multiplied by, the N proportionality coefficients are that the N perspective transform inverse matrixs are multiplied by knot obtained by the paper coordinate of N points
The inverse of the homogeneous item of fruit.
Optionally, wherein updating nib image coordinate at first point according to and the M image coordinate includes：：Delete the M
X image coordinate is obtained after exceptional value in individual image coordinate and first point of image coordinate, by the average value of X image coordinate
It is used as nib image coordinate；Or sat the average value of first point of image coordinate and the M image coordinate as nib image
Mark.
Optionally, wherein, described device also includes：
Person's handwriting unit 405, for obtaining multiple measuring images during user writing；Figure according to the multiple measuring image
As the corresponding multiple actual measurement transforming function transformation functions of the multiple measuring image of acquisition of information；According to the multiple actual measurement transforming function transformation function and institute
Nib image coordinate is stated, multiple nib paper coordinates is obtained, user handwriting is obtained according to the multiple nib paper coordinate.
Optionally, wherein the multiple measuring image of image information acquisition according to the multiple measuring image is corresponding more
Individual actual measurement transforming function transformation function includes：At least four point in each image is obtained to each image information analysis of multiple measuring images
Image coordinate and paper coordinate；Image coordinate and paper coordinate according at least four point are calculated from image coordinate conversion
To the corresponding multiple actual measurement transforming function transformation functions of the multiple measuring image of paper coordinate.
Optionally, wherein obtaining the corresponding multiple actual measurement transforming function transformation functions of the multiple measuring image includes obtaining the multiple
The corresponding 3*3 of measuring image perspective transformation matrix；According to the multiple actual measurement transforming function transformation function and the nib image coordinate, obtain
Multiple nib paper coordinates are taken to include：It is corresponding that the multiple nib paper coordinate is equal to the multiple measuring image of the nib
3*3 perspective transformation matrix is multiplied by corresponding proportionality coefficient, and the proportionality coefficient is multiplied by corresponding for the nib image coordinate
Depending on the inverse of the homogeneous item of transformation matrix acquired results.
Refering to Fig. 5, a kind of smart pen device that Fig. 5 provides for the present invention, including：Processor 501, memory 502, outside
Interface 505, bus 504 and camera 506.External interface 505 is used to interact with transceiving data with external equipment 504.Smart pen
The quantity of processor 501 in equipment 50 can be one or more.In some embodiments of the present application, processor 501, storage
Device 502 and external interface 505 can be connected by bus or other modes.Memory 502 is used for store program codes 5024, processing
Device 501 is used to call the program code 5024 stored in memory 502, to realize the function of smart pen in Fig. 2 or Fig. 3.On
The implication for the term that the present embodiment is related to and citing, may be referred to the corresponding embodiments of Fig. 2 or Fig. 3.Here is omitted.Need
It is noted that processor 501 here can be the general designation of a treatment element or multiple treatment elements.For example,
The treatment element can be central processing unit (English：Central processing unit, referred to as：CPU it is) or special
Determine integrated circuit (English：Application-specific integrated circuit, referred to as：ASIC), or by with
The one or more integrated circuits for implementing the embodiment of the present application are set to, for example：One or more digital signal processor (English：
Digital signal processor, referred to as：), or, one or more field programmable gate array (English DSP：
Field-programmable gate array, referred to as：FPGA).
Memory 502 can be the general designation of a storage device or multiple memory elements, and for storing and can hold
Parameter, data etc. required for line program code or the operation of application program running gear.And memory 503 can include random storage
(the English of device 5021：Random-access memory, referred to as：RAM), nonvolatile memory (non-can also be included
Volatile memory), such as magnetic disk storage, flash memory (flash) etc., cache memory can also be included certainly
5022 or read-only storage (English：Read-only memory, ROM).
Bus 503 can be industry standard architecture (English：Industry Standard Architecture, letter
Claim：ISA) bus, external equipment interconnection (English：Peripheral Component Interconnect, referred to as：PCI) bus
Or extended industry-standard architecture (English：Extended Industry Standard Architecture, referred to as：
EISA) bus etc..The bus can be divided into address bus, data/address bus, controlling bus etc..For ease of representing, only with one in Fig. 5
Bar line is represented, it is not intended that only one bus or a type of bus.
Refering to Fig. 6, Fig. 6 provides a kind of computer-readable recording medium 60 for the present invention, is stored thereon with computer program,
The method in embodiment as shown in Figure 2 or Figure 3 is realized when the program is executed by processor.
If although it should be noted that being referred to the equipment for drying or sub-device of equipment, this stroke in above-detailed
Divide only not enforceable.In fact, according to the embodiment of the present invention, the feature of two or more above-described devices
It can be embodied in one apparatus with function.Conversely, the feature and function of an above-described device can further be drawn
It is divided into by multiple devices embodying.
In addition, although the operation of the inventive method is described with particular order in the accompanying drawings, this do not require that or
Hint must be performed according to the particular order these operation, or the operation having to carry out shown in whole could realize it is desired
As a result.Additionally or alternatively, it is convenient to omit some steps, multiple steps are merged into a step execution, and/or by one
Step is decomposed into execution of multiple steps.
Although describing spirit and principles of the present invention by reference to some embodiments, it should be appreciated that, this
Invention is not limited to disclosed embodiment, and the division to each side does not mean that the feature in these aspects can not yet
Combination is this to divide merely to the convenience of statement to be benefited.It is contemplated that cover appended claims spirit and
In the range of included various modifications and equivalent arrangements.
Claims (10)
1. a kind of pen tip position method for solving, including：
The first image shot when user clicks on first in paper by nib is obtained, described first point of paper coordinate is
Know；
According to the transforming function transformation function of image information acquisition first in described first image；
Described first point of image coordinate is calculated according to described first point of paper coordinate and the first transforming function transformation function, according to described the
The image coordinate of any obtains nib image coordinate.
2. according to the method described in claim 1, wherein becoming exchange the letters according to the image information acquisition first in described first image
Number includes：
Image coordinate and paper coordinate that graphical analysis obtains at least four point in image are carried out to described first image；
Image coordinate, paper coordinate according at least four point calculate and the first of paper coordinate are transformed to from image coordinate
Transforming function transformation function.
3. method according to claim 2, wherein obtaining the first perspective transform square that the first transforming function transformation function includes obtaining 3*3
Battle array；
The image coordinate for calculating at described first point according to described first point of paper coordinate and the first transforming function transformation function includes：
The perspective transformation matrix is inverted and obtains the perspective transform inverse matrix；
Described first point of image coordinate, which is equal to the first perspective transform inverse matrix and is multiplied by first point of paper coordinate, is multiplied by the
One proportionality coefficient, first proportionality coefficient is the paper coordinate gained knot that the first perspective transform inverse matrix is multiplied by first point
The inverse of the homogeneous item of fruit.
4. according to the method described in claim 1, in addition to：Preset by clicking on paper known to other paper coordinates
Point, is corrected to the nib image coordinate.
5. according to the method described in claim 1, specifically included wherein being corrected to the nib image coordinate：
Step one：When user clicks on the N points in paper by nib, the N images shot, the paper of the N points are obtained
Known to areal coordinate；
Step 2：According to the image information acquisition N transforming function transformation functions on the N images；
Step 3：Paper coordinate and N transforming function transformation functions according to the N points calculate the image coordinate of the N points, wherein
N is the integer more than or equal to 2；
When pen tip position is moved, repeating said steps one to step 3 calculate M image coordinate of pen tip position, wherein M
For positive integer；
According to first point of image coordinate and M image coordinate correction nib image coordinate.
6. method according to claim 5, wherein according to the image information acquisition N transforming function transformation functions on the N images
Including：
Image coordinate and paper coordinate that graphical analysis obtains at least four point in image are carried out to the N images；
Image coordinate, paper coordinate according at least four point calculate the N for transforming to paper coordinate from image coordinate and become
Exchange the letters number.
7. method according to claim 6, wherein obtaining the N perspective transform squares that N transforming function transformation functions include obtaining 3*3
Battle array；
The image coordinate that paper according to the N points sits the N transforming function transformation functions calculating N points includes：
The N perspective transformation matrixs are inverted and obtain N perspective transform inverse matrixs；
The image coordinate of the N points is multiplied by N ratios equal to the paper coordinate that the N perspective transform inverse matrixs are multiplied by N points
Example coefficient, the N proportionality coefficients are the neat of the paper coordinate acquired results that the N perspective transform inverse matrixs are multiplied by N points
The inverse of secondary item.
8. method according to claim 5, wherein image coordinate and the M image coordinate correction pen according to first point
Sharp image coordinate includes：
X image coordinate is obtained after deleting the exceptional value in the M image coordinate and first point of image coordinate, by the X
The average value of individual image coordinate is used as nib image coordinate；
Or it regard the average value of first point of image coordinate and the M image coordinate as nib image coordinate.
9. the method according to claim any one of 1-8, wherein, methods described also includes：
Obtain multiple measuring images during user writing；
The corresponding multiple actual measurement transforming function transformation functions of the multiple measuring image of image information acquisition according to the multiple measuring image；
According to the multiple actual measurement transforming function transformation function and the nib image coordinate, multiple nib paper coordinates are obtained, according to described
Multiple nib paper coordinates obtain user handwriting.
10. method according to claim 9, wherein the image information acquisition according to the multiple measuring image is the multiple
The corresponding multiple actual measurement transforming function transformation functions of measuring image include：
The image coordinate of at least four point and paper seat in each image are obtained to each image information analysis of multiple measuring images
Mark；
Image coordinate and paper coordinate according at least four point are calculated and transformed to from image coordinate described in paper coordinate
The corresponding multiple actual measurement transforming function transformation functions of multiple measuring images.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611188735.7A CN107066919B (en) | 2016-12-21 | 2016-12-21 | Method, apparatus and computer-readable storage medium for solving pen tip position |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611188735.7A CN107066919B (en) | 2016-12-21 | 2016-12-21 | Method, apparatus and computer-readable storage medium for solving pen tip position |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107066919A true CN107066919A (en) | 2017-08-18 |
| CN107066919B CN107066919B (en) | 2020-09-29 |
Family
ID=59619225
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611188735.7A Active CN107066919B (en) | 2016-12-21 | 2016-12-21 | Method, apparatus and computer-readable storage medium for solving pen tip position |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107066919B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1619581A (en) * | 2003-11-21 | 2005-05-25 | 国际商业机器公司 | Video based handwriting recognition system and method |
| CN1881235A (en) * | 2005-06-15 | 2006-12-20 | 富士施乐株式会社 | Electronic document management system, image forming device, method of managing electronic document, and program |
| US20070195070A1 (en) * | 2006-02-20 | 2007-08-23 | Sadao Takahashi | Coordinate detecting device, writing instrument, and coordinate inputting system |
| CN101093543A (en) * | 2007-06-13 | 2007-12-26 | 中兴通讯股份有限公司 | Method for correcting image in 2D code of quick response matrix |
| US20080080791A1 (en) * | 2003-02-24 | 2008-04-03 | Carl Stewart R | Implement for optically inferring information from a jotting surface and environmental landmarks |
| CN101799996A (en) * | 2010-03-11 | 2010-08-11 | 南昌航空大学 | Click-reading method of click-reading machine based on video image |
| CN101847209A (en) * | 2010-06-01 | 2010-09-29 | 福建新大陆电脑股份有限公司 | Character image correction method |
| CN102135821A (en) * | 2011-03-08 | 2011-07-27 | 中国科学技术大学 | Handwriting pen and graphic restoration system |
| CN202472687U (en) * | 2011-11-04 | 2012-10-03 | 刘建生 | Multifunctional digital pen |
| JP2014006579A (en) * | 2012-06-21 | 2014-01-16 | Dainippon Printing Co Ltd | Electronic pen system and program |
| CN103605974A (en) * | 2013-11-15 | 2014-02-26 | 刘建生 | A coordinate positioning method based on two dimensional codes and a multimedia and handwriting data acquisition method |
| CN104656880A (en) * | 2013-11-21 | 2015-05-27 | 深圳先进技术研究院 | Writing system and method based on smart glasses |
-
2016
- 2016-12-21 CN CN201611188735.7A patent/CN107066919B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080080791A1 (en) * | 2003-02-24 | 2008-04-03 | Carl Stewart R | Implement for optically inferring information from a jotting surface and environmental landmarks |
| CN1619581A (en) * | 2003-11-21 | 2005-05-25 | 国际商业机器公司 | Video based handwriting recognition system and method |
| CN1881235A (en) * | 2005-06-15 | 2006-12-20 | 富士施乐株式会社 | Electronic document management system, image forming device, method of managing electronic document, and program |
| US20070195070A1 (en) * | 2006-02-20 | 2007-08-23 | Sadao Takahashi | Coordinate detecting device, writing instrument, and coordinate inputting system |
| CN101093543A (en) * | 2007-06-13 | 2007-12-26 | 中兴通讯股份有限公司 | Method for correcting image in 2D code of quick response matrix |
| CN101799996A (en) * | 2010-03-11 | 2010-08-11 | 南昌航空大学 | Click-reading method of click-reading machine based on video image |
| CN101847209A (en) * | 2010-06-01 | 2010-09-29 | 福建新大陆电脑股份有限公司 | Character image correction method |
| CN102135821A (en) * | 2011-03-08 | 2011-07-27 | 中国科学技术大学 | Handwriting pen and graphic restoration system |
| CN202472687U (en) * | 2011-11-04 | 2012-10-03 | 刘建生 | Multifunctional digital pen |
| JP2014006579A (en) * | 2012-06-21 | 2014-01-16 | Dainippon Printing Co Ltd | Electronic pen system and program |
| CN103605974A (en) * | 2013-11-15 | 2014-02-26 | 刘建生 | A coordinate positioning method based on two dimensional codes and a multimedia and handwriting data acquisition method |
| CN104656880A (en) * | 2013-11-21 | 2015-05-27 | 深圳先进技术研究院 | Writing system and method based on smart glasses |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107066919B (en) | 2020-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jiang et al. | Neuman: Neural human radiance field from a single video | |
| Bredies et al. | Mathematical image processing | |
| Xie et al. | Shape matching and modeling using skeletal context | |
| JP6344050B2 (en) | Image processing system, image processing apparatus, and program | |
| CN107590811B (en) | Scene segmentation based landscape image processing method and device and computing equipment | |
| CN109377467A (en) | Generation method, object detection method and the device of training sample | |
| CN107644423B (en) | Scene segmentation-based video data real-time processing method and device and computing equipment | |
| WO2021253788A1 (en) | Three-dimensional human body model construction method and apparatus | |
| CN109584168A (en) | Image processing method and device, electronic equipment and computer storage medium | |
| CN111598111A (en) | Three-dimensional model generation method and device, computer equipment and storage medium | |
| Sadun | IOS Drawing | |
| CN111080755B (en) | Motion calculation method and device, storage medium and electronic equipment | |
| CN106250813B (en) | Facial expression migration method and equipment | |
| US20170363936A1 (en) | Image processing apparatus, image processing method, and program | |
| CN110895823A (en) | Texture obtaining method, device, equipment and medium for three-dimensional model | |
| CN110097560A (en) | Scratch drawing method and device | |
| CN107146243B (en) | Method for registering images and device | |
| CN113034582A (en) | Pose optimization device and method, electronic device and computer readable storage medium | |
| CN113516697A (en) | Image registration method and device, electronic equipment and computer-readable storage medium | |
| CN107066919A (en) | Pen tip position method for solving, equipment and computer-readable recording medium | |
| CN107622498B (en) | Image crossing processing method and device based on scene segmentation and computing equipment | |
| CN115862149B (en) | Method and system for generating 3D human skeleton key point data set | |
| CN109741420B (en) | Region filling method and device, electronic equipment and storage medium | |
| WO2020098566A1 (en) | Three-dimensional modeling method and device, and computer readable storage medium | |
| KR101582225B1 (en) | System and method for providing interactive augmented reality service |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |