CN108776992A - Recognition methods, device, user terminal and the storage medium of tooth type - Google Patents
Recognition methods, device, user terminal and the storage medium of tooth type Download PDFInfo
- Publication number
- CN108776992A CN108776992A CN201810417306.5A CN201810417306A CN108776992A CN 108776992 A CN108776992 A CN 108776992A CN 201810417306 A CN201810417306 A CN 201810417306A CN 108776992 A CN108776992 A CN 108776992A
- Authority
- CN
- China
- Prior art keywords
- tooth
- identified
- standard
- gravity
- centre
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30036—Dental; Teeth
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of recognition methods, device, user terminal and the storage mediums of tooth type.The method comprising the steps of：Standard three-dimensional tooth model is established, and builds the conventional coordinates of the standard three-dimensional tooth model；The three-dimensional tooth model to be identified divided is obtained, and builds the coordinate system of the three-dimensional tooth model to be identified；According to the coordinate system of the conventional coordinates and the three-dimensional tooth model to be identified, the position of centre of gravity of every standard tooth in the standard three-dimensional tooth model and the position of centre of gravity of every tooth to be identified in the three-dimensional tooth model to be identified are determined；According to the position of centre of gravity of the position of centre of gravity of the standard tooth and the tooth to be identified, the type of the tooth to be identified is determined by way of being aligned and being registrated.Recognition methods, device, user terminal and the storage medium of tooth type can realize automatic identification tooth type, improve accuracy and efficiency.
Description
Technical field
The present invention relates to orthodontic technology fields, more particularly to a kind of recognition methods of tooth type, device, user terminal
And storage medium.
Background technology
Stealthy facing due to it is beautiful, facilitate the advantages that it is more and more welcomed by the people.In the manufacturing process of stealthy facing,
It needs first to obtain the dentognathic model of patient, then the dentognathic model is rebuild, is divided, by the tooth one in dentognathic model
One branches away, then the row's of progress tooth and treatment plan determination.However for the patient for having agomphosis, split in tooth
Later, it needs to confirm that type each tooth belongs to, such as incisor, grinds one's teeth in sleep.Usually, every tooth is rule of thumb determined
The type of tooth, this mode is easier error and efficiency is low.
Invention content
Based on this, it is necessary to for how to improve tooth identification accuracy rate the problem of, a kind of knowledge of tooth type is provided
Other method, apparatus, user terminal and storage medium.
A kind of recognition methods of tooth type, including step：
Standard three-dimensional tooth model is established, and builds the conventional coordinates of the standard three-dimensional tooth model；
The three-dimensional tooth model to be identified divided is obtained, and builds the coordinate system of the three-dimensional tooth model to be identified；
According to the coordinate system of the conventional coordinates and the three-dimensional tooth model to be identified, the standard three-dimensional tooth is determined
Every tooth to be identified in the position of centre of gravity of every standard tooth in tooth model and the three-dimensional tooth model to be identified
Position of centre of gravity；
According to the position of centre of gravity of the position of centre of gravity of the standard tooth and the tooth to be identified, by the side for being aligned registration
Formula determines the type of the tooth to be identified.
The position of centre of gravity of every standard tooth in the standard three-dimensional tooth model is determined in one of the embodiments,
And include the step of the position of centre of gravity of every tooth to be identified in the three-dimensional tooth model to be identified：
The coordinate system of the conventional coordinates and the three-dimensional tooth model to be identified is overlapped, obtains overlapping coordinate
System；
Determine the center of gravity of the every standard tooth and every tooth to be identified under the coincidence coordinate system
Position.
In one of the embodiments, according to the center of gravity position of the position of centre of gravity of the standard tooth and the tooth to be identified
Set, be aligned be registrated by way of determine the type of the tooth to be identified the step of include：
(1) according to current Mk、Rk、tk, the position of centre of gravity of the standard tooth and the center of gravity position of the tooth to be identified
It sets, determines the current value of object function；Wherein, M indicates matching matrix, M ∈ Zn×16, n indicates the number of the tooth to be identified；
R indicates rotation amount；T indicates translational movement；K is iterations；
(2) the fixed MkIt is constant, update the RkAnd tkSo that the value of the object function is minimum, determines the target
Corresponding R when the value minimum of functionkAnd tkFor Rk(min)And tk(min)；
(3) the fixed Rk(min)And tk(min)It is constant, update the MkSo that the value of the object function is minimum, determines
Corresponding M when the value minimum of the object functionkFor Mk(min)；
(4) according to the Rk(min)、tk(min)And Mk(min), calculate the current minimum value of the object function；
(5) if the current value of the object function and the variation of the current minimum value of the object function are less than threshold value,
The Mk(min)In the type of standard tooth represented by row corresponding to maximum value per a line be that row corresponding to it indicates
The tooth to be identified type；If the variation of the current value of the object function and the current minimum value of the object function
More than or equal to threshold value, then return to step (1), k adds 1.
The determination process of initial M is as follows in one of the embodiments,：Based on every institute under the coincidence coordinate system
The position of centre of gravity of standard tooth and every tooth to be identified is stated, i-th tooth to be identified and jth tooth are calculated
Centroidal distance between the standard tooth, and the initial M is determined according to the centroidal distance；Wherein, whole during i is 1 to n
Number；J is the integer in 1 to 16.
The formula of the object function is in one of the embodiments,：AndWherein, PjIndicate the position of centre of gravity of the jth standard tooth；QiIt indicates described in i-th
The position of centre of gravity of tooth to be identified；mijFor the element that the i-th row jth in M arranges, mijIndicate that i-th tooth to be identified belongs to the
The matching degree of the j mark tooth.
In one of the embodiments,
The tkMore new formula be：The RkUpdate
Formula is：Rk=VUT；Wherein, V and U decomposes to obtain by the SVD of matrix S, and
The m in one of the embodiments,kThe more new formulas of element of the i-th row jth row be：mij=exp (- | |
RkQi+tk-Pj||2)。
A kind of identification device of tooth type, including：
Standard three-dimensional tooth model establishes module, for establishing standard three-dimensional tooth model, and builds the standard three-dimensional
The conventional coordinates of tooth model；
Three-dimensional tooth model acquisition module to be identified for obtaining the three-dimensional tooth model to be identified divided, and is built
The coordinate system of the three-dimensional tooth model to be identified；
Position of centre of gravity determining module, for the coordinate according to the conventional coordinates and the three-dimensional tooth model to be identified
System, determines the position of centre of gravity of every standard tooth in the standard three-dimensional tooth model and the three-dimensional tooth mould to be identified
The position of centre of gravity of every tooth to be identified in type；
Tooth determination type module to be identified is used for the position of centre of gravity according to the standard tooth and the tooth to be identified
Position of centre of gravity, the type of the tooth to be identified is determined by way of being aligned and being registrated.
A kind of user terminal, including memory, processor and storage are on a memory and the meter that can run on a processor
The step of calculation machine program, the processor realizes the above method when executing described program.
A kind of computer readable storage medium, is stored thereon with computer program, which realizes when being executed by processor
The step of above method.
Recognition methods, device, user terminal and the storage medium of above-mentioned tooth type, by establishing three-dimensional tooth model,
And its conventional coordinates is built, then the three-dimensional tooth model to be identified divided is obtained, its coordinate system is built, according to the seat of the two
Mark system, determine in standard three-dimensional tooth model every standard tooth position of centre of gravity and three-dimensional tooth model to be identified in every
The position of centre of gravity of tooth to be identified, the position of centre of gravity of position of centre of gravity and tooth to be identified further according to standard tooth, passes through alignment
The mode of registration determines the type of tooth to be identified, to realize automatic identification tooth type, improves accuracy, moreover it is possible to improve effect
Rate.
Description of the drawings
Fig. 1 is the flow diagram of the recognition methods of the tooth type of an embodiment；
Fig. 2 is the flow diagram of the type of the determination tooth to be identified of an embodiment；
Fig. 3 is the structural schematic diagram of the identification device of the tooth type of an embodiment；
Fig. 4 is the structural schematic diagram of the user terminal of an embodiment.
Specific implementation mode
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the present invention, not
For limiting the present invention.
Referring to Fig. 1, Fig. 1 is the flow diagram of the recognition methods of the tooth type in an embodiment.This method is specific
Include the following steps：
S110：Standard three-dimensional tooth model is established, and builds its conventional coordinates.
Specifically, several three-dimensional tooth models are chosen in the database, and the tooth numbers of these three-dimensional tooth models are equal
Be 16, and in each three-dimensional tooth model each tooth type it is known that such as left side incisor, left side canine tooth, a left side
Side frist premolar, left side first molar etc..In addition, the reality of 16 teeth in each three-dimensional tooth model according to patient
Tooth is ranked sequentially, and to each tooth into line label, and label is followed successively by 1,2 ... 16.To several three-dimensional tooth moulds
The label of same type of tooth in type is identical.It should be noted that three-dimensional tooth model described herein refers to
Tooth jaw three-dimensional tooth model or lower tooth jaw three-dimensional tooth model.
Each tooth individually separates in several three-dimensional tooth models, and handles respectively every a kind of tooth, obtains
The standard tooth of such tooth.Specifically, in one of the embodiments, by taking incisor as an example, to each three-dimensional tooth model
In preceding incisor handled with template so that the point on each preceding incisor carries out unification, then by all preceding incisors
The position of point is averaged, point of the obtained average value as incisor before standard, incisor before these point composition standards.Similarly,
It adopts in a like fashion, the standard of obtaining is ground one's teeth in sleep, the tooth of the label and same type in three-dimensional tooth model of these standard tooths
Label it is identical, to which 16 standard tooths arrange obtain standard tooth model in sequence.
In the present embodiment, by taking upper tooth jaw three-dimensional tooth model as an example, 50 known upper tooth jaws three are chosen in the database
Tooth model is tieed up, every tooth in 50 three-dimensional tooth models is numbered, and the number of same type tooth is identical.
It by taking canine tooth as an example, is handled using 50 preceding canine teeth of identical template pair, then is averaged to 50 canine teeth before treated,
Obtain canine tooth before standard.It adopts in a like fashion, obtains other 15 standard tooths, and then establish standard three-dimensional tooth model.
It is obtained in a like fashion it should be noted that also being adopted for the standard tooth model of lower tooth jaw three-dimensional tooth model.
Then, tooth jaw plane is established to standard three-dimensional tooth model, the normal direction of tooth jaw plane is Z axis；By standard three-dimensional tooth
The tooth jaw data point of tooth model projects to tooth jaw plane and carries out ellipse fitting, determines that elliptical short axle is X-axis, elliptical long axis is
Y-axis, to establish the conventional coordinates of standard three-dimensional tooth model.
S120：The three-dimensional tooth model to be identified divided is obtained, and builds its coordinate system.
Specifically, upper tooth jaw three-dimensional tooth model or lower tooth the jaw three-dimensional tooth model to be identified divided is obtained.With
For upper tooth jaw three-dimensional tooth model to be identified, to upper tooth jaw three-dimensional tooth model foundation tooth jaw plane to be identified, tooth jaw plane
Normal direction be Z axis；The tooth jaw data point of upper tooth jaw three-dimensional tooth model to be identified is projected into tooth jaw plane and carries out ellipse fitting,
Determine that elliptical short axle is X-axis, elliptical long axis is Y-axis, to establish the coordinate system of upper tooth jaw three-dimensional tooth model to be identified.
It should be noted that three-dimensional tooth model to be identified can be obtained after the processes such as reconstruction, incisor.
S130：According to the coordinate system of conventional coordinates and three-dimensional tooth model to be identified, standard three-dimensional tooth model is determined
In every standard tooth position of centre of gravity and every tooth to be identified in three-dimensional tooth model to be identified position of centre of gravity.
Specifically, the three-dimensional tooth model to be identified obtained conventional coordinates of step S110 and step S120 obtained
Coordinate system is overlapped, and obtains overlapping coordinate system；Every standard tooth and every of the determination in the case where overlapping coordinate system are to be identified
The position of centre of gravity of tooth.That is, the coordinate system unified to standard tooth model and three-dimensional tooth model foundation to be identified, then
Determine the barycentric coodinates of the standard tooth and tooth to be identified under unified coordinate system.
In the present embodiment, by the coordinate of the standard three-dimensional tooth model obtained by 50 upper tooth jaw three-dimensional tooth models
The coordinate system of system and upper tooth jaw three-dimensional tooth model to be identified is overlapped, and obtains overlapping coordinate system, then obtain standard tooth
The position of centre of gravity of each tooth to be identified in position of centre of gravity and upper tooth jaw three-dimensional tooth model to be identified.
S140：According to the position of centre of gravity of the position of centre of gravity of standard tooth and tooth to be identified, by way of being registrated to it
Determine the type of tooth to be identified.
Specifically, by the distance of the position of centre of gravity of standard tooth and the position of centre of gravity of tooth to be identified, then will be to be identified
Tooth rotationally and/or translationally optimizes the distance of the position of centre of gravity of tooth and standard tooth to be identified, to optimal lower institute
Corresponding tooth to be identified is identical with the type of standard tooth, that is, determines the type of tooth to be identified.
As shown in Fig. 2, in one of the embodiments, according to the center of gravity of the position of centre of gravity of standard tooth and tooth to be identified
Position, be aligned be registrated by way of determine the type of tooth to be identified the step of include：
S410：According to current Mk、Rk、tk, the position of centre of gravity of standard tooth and the position of centre of gravity of tooth to be identified, determine
The current value of object function.
Wherein, M indicates matching matrix, M ∈ Zn×16, n indicates the number of tooth to be identified；R indicates rotation amount；T indicates flat
Shifting amount；K is iterations.Specifically, in one embodiment, the formula of object function is：
Wherein, PjIndicate the position of centre of gravity of jth standard tooth；QiIndicate the position of centre of gravity of i-th tooth to be identified；mijIt is in M i-th
The element of row jth row, mijIndicate that i-th tooth to be identified belongs to the matching degree of jth mark tooth；I be 1 to n in it is whole
Number；J is the integer in 1 to 16.It should be noted that object function may be the average value etc. of sum, do not limit herein.
In other words, according to current Mk、Rk、tk, the position of centre of gravity of standard tooth and the center of gravity position of tooth to be identified
It sets, the current value of object function is calculated.The determination process of initial M is as follows in one of the embodiments,：Based on overlapping
The position of centre of gravity of every standard tooth and every tooth to be identified under coordinate system calculates i-th tooth to be identified and jth
Centroidal distance between tooth standard tooth, and the initial M is determined according to centroidal distance.
Specifically, in the present embodiment, when k is 1, corresponding initial M1Determination process it is as follows：Based on step S130
Obtained coincidence coordinate system calculates the centroidal distance between i-th tooth to be identified and jth tooth standard tooth, according to this
The size of centroidal distance determines matching matrix M1, such as：The big corresponding matching degree of centroidal distance is small, then corresponding
It is small with degree value.To obtain behavior n, be classified as 16 matching matrix M1。R1And t1It can be according to for empirical value.By M1、R1And
t1Substitute into above-mentioned object function, then by the position of centre of gravity of the position of centre of gravity of i-th tooth to be identified and jth tooth standard tooth
It substitutes into, then sums, obtain target function value, that is, target function value E1。
S420：Fixed MkIt is constant, update RkAnd tkSo that the value of object function is minimum, when determining the value minimum of object function
Corresponding RkAnd tkFor Rk(min)And tk(min)。
Specifically, M is keptkIt is constant, optimize RkAnd tkSo that the value of object function is minimum, at this point, determining target function value
R when minimumk(min)And tk(min).Wherein, in one embodiment, tkMore new formula be：
RkMore new formula be：Rk=VUT；Wherein, V and U decomposes to obtain by the SVD of matrix S, and
In the present embodiment, the M that step S410 is obtained1It is constant, update R1And t1So that target function value is minimum, obtain
R1(min)And t1(min)。
S430：Fixed Rk(min)And tk(min)It is constant, update MkSo that the value of object function is minimum, determines object function
Value M corresponding when minimumkFor Mk(min)。
Specifically, the R for keeping step S420 to obtain in one of the embodiments,k(min)And tk(min)It is constant, update Mk, Mk
The more new formulas of element of the i-th row jth row be：mij=exp (- | | RkQi+tk-Pj||2).To obtain a series of target
Functional value determines M corresponding when the value minimum of object functionk(min)。
In the present embodiment, R1(min)And t1(min)It is constant, update M1, until the value of object function is minimum, determine M1(min)。
S440：According to Rk(min)、tk(min)And Mk(min), the current minimum value of calculating target function.
In the present embodiment, the R obtained according to step S4201(min)And t1(min)And the M that step S430 is obtained1(min),
Again by the position of centre of gravity generation of the position of centre of gravity of i-th tooth to be identified obtained in step S130 and jth tooth standard tooth
Enter object function, obtains the current minimum value E of object function1(min)。
S450：Judge whether the changing value of the current value of object function and the current minimum value of object function is less than threshold value.
If the changing value of the current value of object function and the current minimum value of object function is less than threshold value, S460, M are thened follow the stepsk(min)
In the type of standard tooth represented by row corresponding to maximum value per a line be that row corresponding to it indicates to be identified
The type of tooth.That is, for Mk(min)In tooth type represented by row in the i-th row corresponding to maximum value be exactly i-th
The type of tooth to be identified, the type of the two is identical, so as to identify the type of all teeth to be identified.If object function
Current value and the changing value of current minimum value of object function be more than or equal to threshold value, then return to step S410, k increase by 1, and this
When Mk+1、Rk+1、tk+1For Mk(min)、Rk(min)And tk(min).It should be noted that threshold value can be 0.01.
In the present embodiment, judge target function value E1With the current minimum value E of object function1(min)Between changing value
Size between threshold value, if target function value E1With the current minimum value E of object function1(min)Between changing value be less than threshold
It is worth, then M1(min)In tooth type represented by row in the i-th row corresponding to maximum value be exactly i-th tooth to be identified type.
If target function value E1With the current minimum value E of object function1(min)Between changing value be more than or equal to threshold value, then return to step
S410, at this point, M1min)、R1(min)And t1(min)As M2、R2、t2.According to M2、R2、t2And the center of gravity of i-th tooth to be identified
The position of centre of gravity of position and jth tooth standard tooth, obtains target function value E2.M is kept again2It is constant, update R2And t2Make
It is minimum to obtain target function value, obtains R2(min)And t2(min)；R is kept again2(min)And t2(min)It is constant, update M2, until object function
Value it is minimum, determine M2(min).Then, according to R2(min)And t2(min)And M2(min), then will be obtained in step S130 i-th
The position of centre of gravity of tooth to be identified substitutes into object function with the position of centre of gravity of jth tooth standard tooth, obtains object function
Current minimum value E2(min).Judge target function value E2With the current minimum value E of object function2(min)Between changing value and threshold value
Between size, if target function value E2With the current minimum value E of object function2(min)Between changing value be less than threshold value, then
M2(min)In tooth type represented by row in the i-th row corresponding to maximum value be exactly i-th tooth to be identified type.If mesh
Offer of tender numerical value E2With the current minimum value E of object function2(min)Between changing value be more than or equal to threshold value, then return to step S410,
At this point, M2min)、R2(min)And t2(min)As M3、R3、t3.And so on, obtain every tooth to be identified in tooth model to be identified
The type of tooth.
The recognition methods of above-mentioned tooth type by establishing three-dimensional tooth model, and builds its conventional coordinates, then obtains
The three-dimensional tooth model to be identified divided, builds its coordinate system, according to the coordinate system of the two, determines standard three-dimensional tooth model
In the position of centre of gravity of every standard tooth and the position of centre of gravity of every tooth to be identified in three-dimensional tooth model to be identified, then root
According to the position of centre of gravity of the position of centre of gravity and tooth to be identified of standard tooth, tooth to be identified is determined by way of being aligned and being registrated
Type improves accuracy, moreover it is possible to improve efficiency to realize automatic identification tooth type.
In one embodiment, as shown in figure 3, providing a kind of identification device of tooth type, which includes：
Standard three-dimensional tooth model establishes module 310, for establishing standard three-dimensional tooth model, and builds standard three-dimensional tooth
The conventional coordinates of tooth model；
Three-dimensional tooth model acquisition module 320 to be identified, for obtaining the three-dimensional tooth model to be identified divided, and structure
Build the coordinate system of three-dimensional tooth model to be identified；
Position of centre of gravity determining module 330, for the coordinate system according to conventional coordinates and three-dimensional tooth model to be identified, really
Calibrate every standard tooth in quasi- three-dimensional tooth model position of centre of gravity and three-dimensional tooth model to be identified in every wait knowing
The position of centre of gravity of other tooth；
Tooth determination type module 340 to be identified is used for the weight of the position of centre of gravity and tooth to be identified according to standard tooth
Heart position determines the type of tooth to be identified by way of being aligned and being registrated.
Position of centre of gravity determining module 330 includes in one of the embodiments,：
Module is overlapped, for overlapping the coordinate system of conventional coordinates and three-dimensional tooth model to be identified, obtains weight
Close coordinate system；
Determining module, the center of gravity for determining every standard tooth and every tooth to be identified in the case where overlapping coordinate system
Position.
Tooth determination type module 340 to be identified includes in one of the embodiments,：
Current value determining module, for according to current Mk、Rk、tk, standard tooth position of centre of gravity and tooth to be identified
Position of centre of gravity determines the current value of object function；Wherein, M indicates matching matrix, M ∈ Zn×16, the n expressions tooth to be identified
Number；R indicates rotation amount；T indicates translational movement；K is iterations；
RkAnd tkOptimization module, for fixing MkIt is constant, update RkAnd tkSo that the value of object function is minimum, determines target
Corresponding R when the value minimum of functionkAnd tkFor Rk(min)And tk(min)；
MkOptimization module, for fixing Rk(min)And tk(min)It is constant, update MkSo that the value of object function is minimum, determines mesh
Corresponding M when the value minimum of scalar functionskFor Mk(min)；
Current minimum value computing module, for according to Rk(min)、tk(min)And Mk(min), calculating target function it is current most
Small value；
Comparison module, if the variation for being used for the current value of object function and the current minimum value of object function is less than threshold value,
Then Mk(min)In the type of standard tooth represented by row corresponding to maximum value per a line be that row corresponding to it indicates
The type of tooth to be identified；If the variation of the current value of object function and the current minimum value of object function is more than or equal to threshold value,
Current value determining module is then returned to, k adds 1.
Referring to Fig. 4, Fig. 4 is the structural schematic diagram of the user terminal in an embodiment, which can be conventional
Server or any other user terminal, including memory, processor and storage are on a memory and can be on a processor
The computer program of operation, the wherein memory may include non-volatile memory medium and built-in storage, the computer journey
Sequence can be stored in the non-volatile memory medium, and processor realizes following steps when executing program：Establish standard three-dimensional tooth
Tooth model, and build the conventional coordinates of standard three-dimensional tooth model；Obtain the three-dimensional tooth model to be identified divided, and structure
Build the coordinate system of three-dimensional tooth model to be identified；According to the coordinate system of conventional coordinates and three-dimensional tooth model to be identified, determine
In the position of centre of gravity of every standard tooth in standard three-dimensional tooth model and three-dimensional tooth model to be identified every it is to be identified
The position of centre of gravity of tooth；According to the position of centre of gravity of the position of centre of gravity of standard tooth and tooth to be identified, by the side for being aligned registration
Formula determines the type of tooth to be identified.
Following steps can also be realized when processor executes program in one of the embodiments,：By conventional coordinates and
The coordinate system of three-dimensional tooth model to be identified is overlapped, and obtains overlapping coordinate system；Determine every mark in the case where overlapping coordinate system
The position of centre of gravity of quasi- tooth and every tooth to be identified.
Following steps can also be realized when processor executes program in one of the embodiments,：(1) according to current Mk、
Rk、tk, the position of centre of gravity of standard tooth and the position of centre of gravity of tooth to be identified, determine the current value of object function；Wherein, M tables
Show matching matrix, M ∈ Zn×16, n indicates the number of tooth to be identified；R indicates rotation amount；T indicates translational movement；K is iterations；
(2) fixed MkIt is constant, update RkAnd tkSo that the value of object function is minimum, determines R corresponding when the value minimum of object functionk
And tkFor Rk(min)And tk(min)；(3) fixed Rk(min)And tk(min)It is constant, update MkSo that the value of object function is minimum, determines mesh
Corresponding M when the value minimum of scalar functionskFor Mk(min)；(4) according to Rk(min)、tk(min)And Mk(min), calculating target function
Current minimum value；(5) if the variation of the current value of object function and the current minimum value of object function is less than threshold value, Mk(min)
In the type of standard tooth represented by row corresponding to maximum value per a line be that row corresponding to it indicates to be identified
The type of tooth；If the variation of the current value of object function and the current minimum value of object function is more than or equal to threshold value, return
Step (1), k adds 1.
The above-mentioned specific restriction that may refer to the recognition methods above for tooth type for the restriction of terminal, herein
It repeats no more.
Please continue to refer to Fig. 4, a kind of computer readable storage medium is also provided, is stored thereon with computer program, such as Fig. 4
Shown in non-volatile memory medium, wherein the program realizes following steps when being executed by processor：Establish standard three-dimensional tooth
Tooth model, and build the conventional coordinates of standard three-dimensional tooth model；Obtain the three-dimensional tooth model to be identified divided, and structure
Build the coordinate system of three-dimensional tooth model to be identified；According to the coordinate system of conventional coordinates and three-dimensional tooth model to be identified, determine
In the position of centre of gravity of every standard tooth in standard three-dimensional tooth model and three-dimensional tooth model to be identified every it is to be identified
The position of centre of gravity of tooth；According to the position of centre of gravity of the position of centre of gravity of standard tooth and tooth to be identified, by the side for being aligned registration
Formula determines the type of tooth to be identified.
Following steps can also be realized when processor executes program in one of the embodiments,：By conventional coordinates and
The coordinate system of three-dimensional tooth model to be identified is overlapped, and obtains overlapping coordinate system；Determine every mark in the case where overlapping coordinate system
The position of centre of gravity of quasi- tooth and every tooth to be identified.
Following steps can also be realized when processor executes program in one of the embodiments,：(1) according to current Mk、
Rk、tk, the position of centre of gravity of standard tooth and the position of centre of gravity of tooth to be identified, determine the current value of object function；Wherein, M tables
Show matching matrix, M ∈ Zn×16, n indicates the number of tooth to be identified；R indicates rotation amount；T indicates translational movement；K is iterations；
(2) fixed MkIt is constant, update RkAnd tkSo that the value of object function is minimum, determines R corresponding when the value minimum of object functionk
And tkFor Rk(min)And tk(min)；(3) fixed Rk(min)And tk(min)It is constant, update MkSo that the value of object function is minimum, determines mesh
Corresponding M when the value minimum of scalar functionskFor Mk(min)；(4) according to Rk(min)、tk(min)And Mk(min), calculating target function
Current minimum value；(5) if the variation of the current value of object function and the current minimum value of object function is less than threshold value, Mk(min)
In the type of standard tooth represented by row corresponding to maximum value per a line be that row corresponding to it indicates to be identified
The type of tooth；If the variation of the current value of object function and the current minimum value of object function is more than or equal to threshold value, return
Step (1), k adds 1.
The above-mentioned restriction for computer readable storage medium may refer to the recognition methods above for tooth type
Specific restriction, details are not described herein.
Each technical characteristic of embodiment described above can be combined arbitrarily, to keep description succinct, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, it is all considered to be the range of this specification record.
Several embodiments of the invention above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the protection of the present invention
Range.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. a kind of recognition methods of tooth type, which is characterized in that including step：
Standard three-dimensional tooth model is established, and builds the conventional coordinates of the standard three-dimensional tooth model；
The three-dimensional tooth model to be identified divided is obtained, and builds the coordinate system of the three-dimensional tooth model to be identified；
According to the coordinate system of the conventional coordinates and the three-dimensional tooth model to be identified, the standard three-dimensional tooth mould is determined
The center of gravity of every tooth to be identified in the position of centre of gravity of every standard tooth in type and the three-dimensional tooth model to be identified
Position；
It is true by way of being aligned and being registrated according to the position of centre of gravity of the position of centre of gravity of the standard tooth and the tooth to be identified
The type of the fixed tooth to be identified.
2. the recognition methods of tooth type according to claim 1, which is characterized in that determine the standard three-dimensional tooth mould
The center of gravity of every tooth to be identified in the position of centre of gravity of every standard tooth in type and the three-dimensional tooth model to be identified
The step of position includes：
The coordinate system of the conventional coordinates and the three-dimensional tooth model to be identified is overlapped, obtains overlapping coordinate system；
Determine the position of centre of gravity of the every standard tooth and every tooth to be identified under the coincidence coordinate system.
3. the recognition methods of tooth type according to claim 2, which is characterized in that according to the center of gravity of the standard tooth
The position of centre of gravity of position and the tooth to be identified determines the step of the type of the tooth to be identified by way of being aligned and being registrated
Suddenly include：
(1) according to current Mk、Rk、tk, the position of centre of gravity of the standard tooth and the position of centre of gravity of the tooth to be identified, really
Set the goal the current value of function；Wherein, M indicates matching matrix, m ∈ Zn×16, n indicates the number of the tooth to be identified；R is indicated
Rotation amount；T indicates translational movement；K is iterations；
(2) the fixed MkIt is constant, update the RkAnd tkSo that the value of the object function is minimum, determines the object function
Value minimum when corresponding RkAnd tkFor Rk(min)And tk(min)；
(3) the fixed Rk(min)And tk(min)It is constant, update the MkSo that the value of the object function is minimum, determines the mesh
Corresponding M when the value minimum of scalar functionskFor Mk(min)；
(4) according to the Rk(min)、tk(min)And Mk(min), calculate the current minimum value of the object function；
(5) described if the variation of the current value of the object function and the current minimum value of the object function is less than threshold value
Mk(min)In the type of standard tooth represented by row corresponding to maximum value per a line be institute that the row corresponding to it indicates
State the type of tooth to be identified；If the current value of the object function and the variation of the current minimum value of the object function are more than
Equal to threshold value, then return to step (1), k adds 1.
4. the recognition methods of tooth type according to claim 3, which is characterized in that the determination process of initial M is as follows：Base
In the position of centre of gravity of every standard tooth and every tooth to be identified under the coincidence coordinate system, the is calculated
Centroidal distance between standard tooth described in the i tooth to be identified and jth tooth, and determined according to the centroidal distance
The initial M；Wherein, i is the integer in 1 to n；J is the integer in 1 to 16.
5. the recognition methods of tooth type according to claim 4, which is characterized in that the formula of the object function is：AndWherein, PjIndicate the jth standard tooth
Position of centre of gravity；QiIndicate the position of centre of gravity of i-th tooth to be identified；mijFor the element that the i-th row jth in M arranges, mijTable
Show that i-th tooth to be identified belongs to the matching degree of the jth mark tooth.
6. the recognition methods of tooth type according to claim 5, which is characterized in that the tkMore new formula be：The RkMore new formula be：Rk=VUT；Wherein, V and U pass through
The SVD of matrix S decomposes to obtain, and
7. the recognition methods of tooth type according to claim 5, which is characterized in that the mkThe i-th row jth row member
Element more new formula be：mij=exp (- | | RkQi+tk-Pj||2)。
8. a kind of identification device of tooth type, which is characterized in that including：
Standard three-dimensional tooth model establishes module, for establishing standard three-dimensional tooth model, and builds the standard three-dimensional tooth
The conventional coordinates of model；
Three-dimensional tooth model acquisition module to be identified, for obtaining the three-dimensional tooth model to be identified divided, and described in structure
The coordinate system of three-dimensional tooth model to be identified；
Position of centre of gravity determining module is used for the coordinate system according to the conventional coordinates and the three-dimensional tooth model to be identified,
Determine the position of centre of gravity of every standard tooth in the standard three-dimensional tooth model and the three-dimensional tooth model to be identified
In every tooth to be identified position of centre of gravity；
Tooth determination type module to be identified is used for the weight of the position of centre of gravity and the tooth to be identified according to the standard tooth
Heart position determines the type of the tooth to be identified by way of being aligned and being registrated.
9. a kind of user terminal, including memory, processor and storage are on a memory and the calculating that can run on a processor
Machine program, which is characterized in that the processor realizes claim 1 to 7 any one the method when executing described program
Step.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The step of claim 1 to 7 any one the method is realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810417306.5A CN108776992B (en) | 2018-05-04 | 2018-05-04 | Tooth type identification method and device, user terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810417306.5A CN108776992B (en) | 2018-05-04 | 2018-05-04 | Tooth type identification method and device, user terminal and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108776992A true CN108776992A (en) | 2018-11-09 |
| CN108776992B CN108776992B (en) | 2022-08-05 |
Family
ID=64026927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810417306.5A Active CN108776992B (en) | 2018-05-04 | 2018-05-04 | Tooth type identification method and device, user terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108776992B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111276239A (en) * | 2019-11-29 | 2020-06-12 | 上海正雅齿科科技股份有限公司 | Method and device for determining tooth position of tooth model |
| CN112790879A (en) * | 2020-12-30 | 2021-05-14 | 上海正雅齿科科技股份有限公司 | Tooth axis coordinate system construction method and system of tooth model |
| CN112989954A (en) * | 2021-02-20 | 2021-06-18 | 山东大学 | Three-dimensional tooth point cloud model data classification method and system based on deep learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020180760A1 (en) * | 2001-04-13 | 2002-12-05 | Orametrix, Inc. | Method and workstation for generating virtual tooth models from three-dimensional tooth data |
| CN102083387A (en) * | 2008-01-23 | 2011-06-01 | 森瑟博科技有限公司 | Haptically enabled dental modeling system |
| US20130085591A1 (en) * | 2010-03-29 | 2013-04-04 | Degudent Gmbh | Method and arrangement for forming a dental model |
| US20140229145A1 (en) * | 2011-09-05 | 2014-08-14 | Carl Van Lierde | Method and system for 3d root canal treatment planning |
| CN105447908A (en) * | 2015-12-04 | 2016-03-30 | 山东山大华天软件有限公司 | Dentition model generation method based on oral cavity scanning data and CBCT (Cone Beam Computed Tomography) data |
| CN107230255A (en) * | 2017-06-14 | 2017-10-03 | 杭州美齐科技有限公司 | A kind of method of dental restoration based on common template |
-
2018
- 2018-05-04 CN CN201810417306.5A patent/CN108776992B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020180760A1 (en) * | 2001-04-13 | 2002-12-05 | Orametrix, Inc. | Method and workstation for generating virtual tooth models from three-dimensional tooth data |
| CN102083387A (en) * | 2008-01-23 | 2011-06-01 | 森瑟博科技有限公司 | Haptically enabled dental modeling system |
| US20130085591A1 (en) * | 2010-03-29 | 2013-04-04 | Degudent Gmbh | Method and arrangement for forming a dental model |
| US20140229145A1 (en) * | 2011-09-05 | 2014-08-14 | Carl Van Lierde | Method and system for 3d root canal treatment planning |
| CN105447908A (en) * | 2015-12-04 | 2016-03-30 | 山东山大华天软件有限公司 | Dentition model generation method based on oral cavity scanning data and CBCT (Cone Beam Computed Tomography) data |
| CN107230255A (en) * | 2017-06-14 | 2017-10-03 | 杭州美齐科技有限公司 | A kind of method of dental restoration based on common template |
Non-Patent Citations (3)
| Title |
|---|
| H. CHEN AND A. K. JAIN: "Dental Biometrics: Alignment and Matching of Dental Radiographs", 《2005 SEVENTH IEEE WORKSHOPS ON APPLICATIONS OF COMPUTER VISION (WACV/MOTION"05)》 * |
| 林有籁; 刘月华; 王冬梅; 王成焘: "CT和MRI图像融合三维重建颞下颌关节的研究", 《华西口腔医学杂志》 * |
| 陈昱; 庄天戈: "医学影像中的图像配准和融合技术研究", 《中国医疗器械杂志》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111276239A (en) * | 2019-11-29 | 2020-06-12 | 上海正雅齿科科技股份有限公司 | Method and device for determining tooth position of tooth model |
| CN112790879A (en) * | 2020-12-30 | 2021-05-14 | 上海正雅齿科科技股份有限公司 | Tooth axis coordinate system construction method and system of tooth model |
| CN112989954A (en) * | 2021-02-20 | 2021-06-18 | 山东大学 | Three-dimensional tooth point cloud model data classification method and system based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108776992B (en) | 2022-08-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108776992A (en) | Recognition methods, device, user terminal and the storage medium of tooth type | |
| US10068128B2 (en) | Face key point positioning method and terminal | |
| TWI794157B (en) | Automatic multi-threshold feature filtering method and device | |
| CN103631928B (en) | LSH (Locality Sensitive Hashing)-based clustering and indexing method and LSH-based clustering and indexing system | |
| CN107886529A (en) | A kind of point cloud registration method for three-dimensional reconstruction | |
| CN109063584B (en) | Facial feature point positioning method, device, equipment and medium based on cascade regression | |
| WO2021051526A1 (en) | Multi-view 3d human pose estimation method and related apparatus | |
| CN109242825A (en) | A kind of steel surface defect identification method and device based on depth learning technology | |
| CN110163087A (en) | A kind of human face posture recognition methods and system | |
| CN110021053A (en) | A kind of image position method, device, storage medium and equipment based on coordinate conversion | |
| US20200327726A1 (en) | Method of Generating 3D Facial Model for an Avatar and Related Device | |
| CN110009097A (en) | The image classification method of capsule residual error neural network, capsule residual error neural network | |
| CN104102836A (en) | Method for quickly estimating robust state of power system | |
| CN108290293A (en) | Link sequences mapping device, link sequences mapping method and program | |
| CN112102146B (en) | Face image processing method, device, equipment and computer storage medium | |
| CN107123138A (en) | Based on vanilla R points to rejecting tactful point cloud registration algorithm | |
| TWI514180B (en) | System and method for processing information of measurement numbers | |
| CN104537708B (en) | Method for conducting upright correction on three-dimensional lie-down craniofacial models based on geodesic lines | |
| CN110263204A (en) | A kind of component contour coding method, device and equipment | |
| CN102542565B (en) | Method for removing mismatching points of remote sensing image including complex terrains | |
| CN109087386A (en) | A kind of face three-dimensional rebuilding method and system comprising dimensional information | |
| CN108304352A (en) | Accelerated life test sample distribution method and terminal device | |
| CN104299264B (en) | A kind of three-dimensional facial reconstruction method and system based on edge graph | |
| JP2017055395A (en) | Method and device for determining plan object function | |
| US10452149B2 (en) | Method for grading spatial painting, apparatus and system for grading spatial painting |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 201210 Pudong New Area, Shanghai, 2305, A, 122, north gate, two floor. Applicant after: Zhengya Dental Technology (Shanghai) Co.,Ltd. Address before: 201210 Pudong New Area, Shanghai, 2305, A, 122, north gate, two floor. Applicant before: SHANGHAI SMARTEE DENTI-TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |