CN108776992B - Tooth type identification method and device, user terminal and storage medium - Google Patents
Tooth type identification method and device, user terminal and storage medium Download PDFInfo
- Publication number
- CN108776992B CN108776992B CN201810417306.5A CN201810417306A CN108776992B CN 108776992 B CN108776992 B CN 108776992B CN 201810417306 A CN201810417306 A CN 201810417306A CN 108776992 B CN108776992 B CN 108776992B
- Authority
- CN
- China
- Prior art keywords
- tooth
- standard
- recognized
- dimensional
- identified
- 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.)
- Active
Links
Images
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 invention relates to a tooth type identification method, a tooth type identification device, a user terminal and a storage medium. The method comprises the following steps: establishing a standard three-dimensional tooth model, and constructing a standard coordinate system of the standard three-dimensional tooth model; acquiring a segmented three-dimensional tooth model to be identified, and constructing a coordinate system of the three-dimensional tooth model to be identified; according to the standard coordinate system and the coordinate system of the three-dimensional tooth model to be recognized, determining the gravity center position of each standard tooth in the standard three-dimensional tooth model and the gravity center position of each tooth to be recognized in the three-dimensional tooth model to be recognized; and determining the type of the tooth to be recognized in an alignment registration mode according to the gravity center position of the standard tooth and the gravity center position of the tooth to be recognized. The tooth type identification method, the tooth type identification device, the user terminal and the storage medium can realize automatic tooth type identification and improve accuracy and efficiency.
Description
Technical Field
The invention relates to the technical field of orthodontics, in particular to a tooth type identification method, a tooth type identification device, a user terminal and a storage medium.
Background
The invisible tooth socket is more and more popular for people due to the advantages of beauty, convenience and the like. In the manufacturing process of the invisible tooth socket, a tooth jaw model of a patient needs to be obtained firstly, then the tooth jaw model is reconstructed, divided and the like, teeth in the tooth jaw model are separated one by one, and then tooth arrangement and treatment plan determination are carried out. However, for patients with missing teeth, it is necessary to confirm what type each tooth belongs to, such as incisors, molars, etc., after the teeth are separated. Typically, the type of each tooth is determined empirically, which is relatively error prone and inefficient.
Disclosure of Invention
In view of the above, it is necessary to provide a tooth type identification method, apparatus, user terminal and storage medium for improving the accuracy of tooth identification.
A method of identifying a type of tooth comprising the steps of:
establishing a standard three-dimensional tooth model, and constructing a standard coordinate system of the standard three-dimensional tooth model;
acquiring a segmented three-dimensional tooth model to be identified, and constructing a coordinate system of the three-dimensional tooth model to be identified;
according to the standard coordinate system and the coordinate system of the three-dimensional tooth model to be recognized, determining the gravity center position of each standard tooth in the standard three-dimensional tooth model and the gravity center position of each tooth to be recognized in the three-dimensional tooth model to be recognized;
and determining the type of the tooth to be recognized in an alignment registration mode according to the gravity center position of the standard tooth and the gravity center position of the tooth to be recognized.
In one embodiment, the step of determining the position of the center of gravity of each standard tooth in the standard three-dimensional tooth model and the position of the center of gravity of each tooth to be recognized in the three-dimensional tooth model to be recognized comprises:
the standard coordinate system is overlapped with a coordinate system of the three-dimensional tooth model to be identified to obtain an overlapped coordinate system;
and determining the gravity center position of each standard tooth and each tooth to be identified under the coincident coordinate system.
In one embodiment, the step of determining the type of the tooth to be recognized through alignment registration according to the position of the center of gravity of the standard tooth and the position of the center of gravity of the tooth to be recognized comprises:
(1) according to the current M k 、R k 、t k Determining the current value of the objective function according to the gravity center position of the standard tooth and the gravity center position of the tooth to be identified; wherein M represents a matching matrix, and M is equal to Z n×16 N represents the number of teeth to be identified; r represents the rotation amount; t represents the translation amount; k is the number of iterations;
(2) fix theM k Updating the R unchanged k And t k So as to minimize the value of the objective function, and determine the R corresponding to the minimum value of the objective function k And t k Is R k(min) And t k(min) ；
(3) Fixing the R k(min) And t k(min) Updating the M unchanged k Minimizing the value of the objective function, and determining M corresponding to the minimized value of the objective function k Is M k(min) ；
(4) According to the formula R k(min) 、t k(min) And M k(min) Calculating the current minimum value of the objective function;
(5) if the change between the current value of the objective function and the current minimum value of the objective function is less than a threshold value, M is k(min) The type of the standard tooth represented by the column corresponding to the maximum value of each row is the type of the tooth to be identified represented by the row corresponding to the standard tooth; and (4) if the change between the current value of the target function and the current minimum value of the target function is larger than or equal to a threshold value, returning to the step (1), and adding 1 to k.
In one embodiment, the process of determining the initial M is as follows: based on each standard tooth and the gravity center position of each tooth to be recognized in the coincidence coordinate system, calculating the gravity center distance between the ith tooth to be identified and the standard tooth of the jth tooth, and determining the initial M according to the gravity center distance; wherein i is an integer of 1 to n; j is an integer of 1 to 16.
In one embodiment, the formula of the objective function is:
and is
Wherein, P j Representing the position of the center of gravity of the jth standard tooth; q i Representing the gravity center position of the ith tooth to be identified; m is ij Is the element in row i and column j in M, M ij And the matching degree of the ith tooth to be identified belonging to the jth labeled tooth is represented.
In one of the embodiments, the first and second electrodes are,
t is said k The update formula of (2) is:
the R is k The update formula of (2) is: r k ＝VU T (ii) a Wherein V and U are obtained by SVD decomposition of the matrix S, and
in one embodiment, m is k The update formula of the element in the ith row and the jth column of (1) is: m is ij ＝exp(-||R k Q i +t k -P j || 2 )。
An apparatus for identifying a type of tooth, comprising:
the standard three-dimensional tooth model establishing module is used for establishing a standard three-dimensional tooth model and establishing a standard coordinate system of the standard three-dimensional tooth model;
the identification system comprises a to-be-identified three-dimensional tooth model acquisition module, a to-be-identified three-dimensional tooth model acquisition module and a to-be-identified three-dimensional tooth model acquisition module, wherein the to-be-identified three-dimensional tooth model acquisition module is used for acquiring a segmented to-be-identified three-dimensional tooth model and establishing a coordinate system of the to-be-identified three-dimensional tooth model;
the center-of-gravity position determining module is used for determining the center-of-gravity position of each standard tooth in the standard three-dimensional tooth model and the center-of-gravity position of each tooth to be recognized in the three-dimensional tooth model to be recognized according to the standard coordinate system and the coordinate system of the three-dimensional tooth model to be recognized;
and the tooth type determination module to be recognized is used for determining the type of the tooth to be recognized in an alignment and registration mode according to the gravity center position of the standard tooth and the gravity center position of the tooth to be recognized.
A user terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method when executing the program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.
According to the tooth type identification method, the device, the user terminal and the storage medium, the three-dimensional tooth model is established, the standard coordinate system of the three-dimensional tooth model is established, the segmented three-dimensional tooth model to be identified is obtained, the coordinate system of the three-dimensional tooth model to be identified is established, the gravity center position of each standard tooth in the standard three-dimensional tooth model and the gravity center position of each tooth to be identified in the three-dimensional tooth model to be identified are determined according to the coordinate systems of the three-dimensional tooth model and the standard tooth model, and the type of the tooth to be identified is determined in an alignment and registration mode according to the gravity center position of the standard tooth and the gravity center position of the tooth to be identified, so that the tooth type is automatically identified, the accuracy is improved, and the efficiency can be improved.
Drawings
FIG. 1 is a flowchart illustrating a method for identifying tooth types according to an embodiment;
FIG. 2 is a schematic flow chart illustrating the determination of the type of tooth to be identified according to one embodiment;
FIG. 3 is a schematic view of an embodiment of a tooth type identification device;
fig. 4 is a schematic structural diagram of a user terminal according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a flowchart illustrating a tooth type identification method according to an embodiment. The method specifically comprises the following steps:
s110: and establishing a standard three-dimensional tooth model and establishing a standard coordinate system of the model.
Specifically, a plurality of three-dimensional tooth models are selected from the database, the number of teeth of each three-dimensional tooth model is 16, and the type of each tooth in each three-dimensional tooth model is known, such as a left incisor, a left cuspid tooth, a left first premolar, a left first molar and the like. In addition, the 16 teeth in each three-dimensional tooth model are arranged in the order of the actual teeth of the patient, and each tooth is labeled, in turn, 1,2 … 16. So that teeth of the same type in several three-dimensional tooth models are labeled the same. It should be noted that the three-dimensional tooth model described herein refers to an upper jaw three-dimensional tooth model or a lower jaw three-dimensional tooth model.
And (3) independently separating each tooth in the plurality of three-dimensional tooth models, and respectively processing each type of tooth to obtain the standard tooth of the type of tooth. Specifically, in one embodiment, taking incisors as an example, the anterior incisors in each three-dimensional tooth model are processed with the template so as to unify points on each anterior incisor, and then the positions of the points of all the anterior incisors are averaged, and the obtained average value is used as the points of the standard anterior incisors, and the points constitute the standard anterior incisors. Similarly, in the same manner, standard molars and the like are obtained, and the standard teeth are labeled with the same labels as those of the same type of teeth in the three-dimensional tooth model, so that 16 standard teeth are arranged in order to obtain a standard tooth model.
In this embodiment, taking the three-dimensional tooth model of the upper jaw as an example, 50 known three-dimensional tooth models of the upper jaw are selected from the database, and each tooth in the 50 three-dimensional tooth models is numbered, and the numbers of the same type of teeth are the same. Taking the cuspid tooth as an example, 50 anterior cuspid teeth are processed by using the same template, and then the 50 processed anterior cuspid teeth are averaged to obtain the standard anterior cuspid tooth. And obtaining other 15 standard teeth by adopting the same mode, and further establishing a standard three-dimensional tooth model. It should be noted that a standard tooth model for the three-dimensional tooth model of the lower jaw is obtained in the same manner.
Secondly, establishing a dental plane for the standard three-dimensional tooth model, wherein the normal direction of the dental plane is a Z axis; and projecting the dental data points of the standard three-dimensional tooth model to the dental plane for ellipse fitting, and determining the short axis of the ellipse as the X axis and the long axis of the ellipse as the Y axis so as to establish a standard coordinate system of the standard three-dimensional tooth model.
S120: and acquiring the segmented three-dimensional tooth model to be identified, and constructing a coordinate system of the segmented three-dimensional tooth model.
Specifically, a segmented upper jaw three-dimensional tooth model or a lower jaw three-dimensional tooth model to be identified is obtained. Taking the upper jaw three-dimensional tooth model to be identified as an example, establishing a jaw plane of the upper jaw three-dimensional tooth model to be identified, wherein the normal direction of the jaw plane is a Z axis; and projecting the dental jaw data points of the three-dimensional dental model of the upper dental jaw to be identified to a dental plane for ellipse fitting, and determining the short axis of the ellipse as the X axis and the long axis of the ellipse as the Y axis so as to establish the coordinate system of the three-dimensional dental model of the upper dental jaw to be identified. It should be noted that the three-dimensional tooth model to be recognized can be obtained through processes such as reconstruction and incisor.
S130: and determining the gravity center position of each standard tooth in the standard three-dimensional tooth model and the gravity center position of each tooth to be recognized in the three-dimensional tooth model to be recognized according to the standard coordinate system and the coordinate system of the three-dimensional tooth model to be recognized.
Specifically, the standard coordinate system obtained in step S110 and the coordinate system of the three-dimensional tooth model to be recognized obtained in step S120 are overlapped to obtain an overlapped coordinate system; and determining the gravity center position of each standard tooth and each tooth to be identified under the coincident coordinate system. Namely, a unified coordinate system is established for the standard tooth model and the three-dimensional tooth model to be recognized, and then the barycentric coordinates of the standard tooth and the tooth to be recognized under the unified coordinate system are determined.
In this embodiment, a coordinate system of a standard three-dimensional tooth model obtained by 50 upper jaw three-dimensional tooth models is overlapped with a coordinate system of an upper jaw three-dimensional tooth model to be recognized to obtain an overlapped coordinate system, and then a barycentric position of the standard tooth and a barycentric position of each tooth to be recognized in the upper jaw three-dimensional tooth model to be recognized are obtained.
S140: and determining the type of the tooth to be recognized by registering the standard tooth according to the gravity center position of the tooth and the gravity center position of the tooth to be recognized.
Specifically, the distance between the center of gravity position of the standard tooth and the center of gravity position of the tooth to be recognized is optimized by rotating and/or translating the tooth to be recognized, so that the optimal type of the corresponding tooth to be recognized is the same as that of the standard tooth, namely the type of the tooth to be recognized is determined.
As shown in fig. 2, in one embodiment, the step of determining the type of the tooth to be recognized by aligning and registering according to the position of the center of gravity of the standard tooth and the position of the center of gravity of the tooth to be recognized includes:
s410: according to the current M k 、R k 、t k The center of gravity position of the standard tooth and the center of gravity position of the tooth to be identified, and determining the current value of the objective function.
Wherein M represents a matching matrix, and M is equal to Z n×16 N represents the number of teeth to be identified; r represents the rotation amount; t represents the translation amount; k is the number of iterations. Specifically, in one embodiment, the formula of the objective function is:
wherein, P j Representing the position of the center of gravity of the jth standard tooth; q i Representing the gravity center position of the ith tooth to be identified; m is ij Is the element in row i and column j in M, M ij The matching degree of the ith tooth to be identified belonging to the jth marked tooth is represented; i is an integer of 1 to n; j is an integer of 1 to 16. The objective function may be an average value of sums or the like, and is not limited herein.
In other words, according to the current M k 、R k 、t k And calculating the current value of the objective function according to the gravity center position of the standard tooth and the gravity center position of the tooth to be recognized. In one embodiment, the process of determining the initial M is as follows: and calculating the barycentric distance between the ith tooth to be identified and the jth tooth standard tooth based on the barycentric positions of each standard tooth and each tooth to be identified in the coincident coordinate system, and determining the initial M according to the barycentric distance.
Specifically, in the present embodiment, when k is 1, the corresponding initial M 1 The determination process of (2) is as follows: based on the coincidence coordinate system obtained in step S130, the barycentric distance between the ith tooth to be identified and the jth tooth standard tooth is calculated, and the matching matrix M is determined according to the barycentric distance 1 For example: the matching degree corresponding to the large gravity center distance is small, and the corresponding matching degree value is small. Thereby obtaining a matching matrix M with rows n and columns 16 1 。R 1 And t 1 May be based on empirical values. Will M 1 、R 1 And t 1 Substituting the target function, substituting the center of gravity position of the ith tooth to be identified and the center of gravity position of the jth tooth standard tooth, and summing to obtain a target function value, namely a target function value E 1 。
S420: fixed M k Unchanged, update R k And t k So as to minimize the value of the objective function, and determine the R corresponding to the minimum value of the objective function k And t k Is R k(min) And t k(min) 。
Specifically, holding M k Invariant, optimized R k And t k So that the value of the objective function is minimized, and at this time, R at which the value of the objective function is minimized is determined k(min) And t k(min) . Wherein, in one embodiment, t k The update formula of (2) is:
R k the update formula of (2) is: r k ＝VU T (ii) a Wherein V and U are obtained by SVD decomposition of the matrix S, and
in this embodiment, M obtained in step S410 1 Unchanged, update R 1 And t 1 Minimize the value of the objective function to obtain R 1(min) And t 1(min) 。
S430: fixing R k(min) And t k(min) Unchanged, update M k Minimizing the value of the objective function, and determining M corresponding to the minimized value of the objective function k Is M k(min) 。
Specifically, in one embodiment, R obtained in step S420 is maintained k(min) And t k(min) Constant, update M k ，M k The update formula of the element in the ith row and the jth column of (1) is: m is ij ＝exp(-||R k Q i +t k -P j || 2 ). So as to obtain a series of objective function values, and defining M correspondent to the minimum value of objective function k(min) 。
In this embodiment, R 1(min) And t 1(min) Constant, update M 1 Until the value of the objective function is minimized, M is determined 1(min) 。
S440: according to R k(min) 、t k(min) And M k(min) And calculating the current minimum value of the objective function.
In the present embodiment, R is obtained according to step S420 1(min) And t 1(min) And M obtained in step S430 1(min) Substituting the barycentric position of the ith tooth to be identified and the barycentric position of the jth tooth standard tooth obtained in the step S130 into the objective function to obtain the current minimum value E of the objective function 1(min) 。
S450: and judging whether the change value of the current value of the target function and the current minimum value of the target function is smaller than a threshold value. If the variation value between the current value of the objective function and the current minimum value of the objective function is smaller than the threshold, go to step S460, M k(min) The type of the standard tooth represented by the column corresponding to the maximum value of each row in the system is the type of the tooth to be identified represented by the row corresponding to the standard tooth. That is, for M k(min) The tooth type represented by the column corresponding to the maximum value in the ith row is the type of the ith tooth to be recognized, and the types of the ith tooth to be recognized are the same, so that all the types of the teeth to be recognized can be recognized. If the current value of the objective function and the current minimum value of the objective functionIs greater than or equal to the threshold value, the process returns to step S410, k is increased by 1, and M is present k+1 、R k+1 、t k+1 Is M k(min) 、R k(min) And t k(min) . Note that the threshold may be 0.01.
In this embodiment, the objective function value E is judged 1 With the current minimum value E of the objective function 1(min) The magnitude between the change value and the threshold value, if the objective function value E 1 With the current minimum value E of the objective function 1(min) Is less than the threshold value, M 1(min) The tooth type represented by the column corresponding to the maximum value in the ith row is the type of the ith tooth to be recognized. If the value of the objective function E 1 With the current minimum value E of the objective function 1(min) If the variation value is greater than or equal to the threshold value, the process returns to step S410, and at this time, M is 1min) 、R 1(min) And t 1(min) As M 2 、R 2 、t 2 . According to M 2 、R 2 、t 2 And the center of gravity position of the ith tooth to be marked and the center of gravity position of the jth tooth standard tooth to obtain an objective function value E 2 . Retainment of M 2 Unchanged, update R 2 And t 2 Minimize the value of the objective function to obtain R 2(min) And t 2(min) (ii) a Retainment of R 2(min) And t 2(min) Constant, update M 2 Until the value of the objective function is minimized, M is determined 2(min) . Then, according to R 2(min) And t 2(min) And M 2(min) Substituting the barycentric position of the ith tooth to be identified and the barycentric position of the jth tooth standard tooth obtained in the step S130 into the objective function to obtain the current minimum value E of the objective function 2(min) . Judging the value of the objective function E 2 With the current minimum value E of the objective function 2(min) The magnitude between the change value and the threshold value, if the objective function value E 2 With the current minimum value E of the objective function 2(min) Is less than the threshold value, M 2(min) The tooth type represented by the column corresponding to the maximum value in the ith row is the type of the ith tooth to be recognized. If the objective functionValue E 2 With the current minimum value E of the objective function 2(min) If the variation value is greater than or equal to the threshold value, the process returns to step S410, and at this time, M is 2min) 、R 2(min) And t 2(min) As M 3 、R 3 、t 3 . And by parity of reasoning, obtaining the type of each tooth to be recognized in the tooth model to be recognized.
According to the tooth type identification method, the three-dimensional tooth model is established, the standard coordinate system of the three-dimensional tooth model is established, the segmented three-dimensional tooth model to be identified is obtained, the coordinate system of the three-dimensional tooth model is established, the gravity center position of each standard tooth in the standard three-dimensional tooth model and the gravity center position of each tooth to be identified in the three-dimensional tooth model to be identified are determined according to the coordinate systems of the three-dimensional tooth model and the standard tooth, and the type of the tooth to be identified is determined in an alignment and registration mode according to the gravity center position of the standard tooth and the gravity center position of the tooth to be identified, so that the tooth type is automatically identified, the accuracy is improved, and the efficiency is also improved.
In one embodiment, as shown in fig. 3, there is provided a tooth type identification device, including:
a standard three-dimensional tooth model establishing module 310, configured to establish a standard three-dimensional tooth model and construct a standard coordinate system of the standard three-dimensional tooth model;
the module 320 for acquiring the three-dimensional tooth model to be recognized is used for acquiring the segmented three-dimensional tooth model to be recognized and constructing a coordinate system of the three-dimensional tooth model to be recognized;
the center-of-gravity position determining module 330 is configured to determine a center-of-gravity position of each standard tooth in the standard three-dimensional tooth model and a center-of-gravity position of each tooth to be recognized in the three-dimensional tooth model to be recognized according to the standard coordinate system and the coordinate system of the three-dimensional tooth model to be recognized;
and the tooth type to be recognized determining module 340 is used for determining the type of the tooth to be recognized in an alignment and registration mode according to the gravity center position of the standard tooth and the gravity center position of the tooth to be recognized.
In one embodiment, the center of gravity position determining module 330 comprises:
the coincidence module is used for coinciding the standard coordinate system with the coordinate system of the three-dimensional tooth model to be identified to obtain a coincidence coordinate system;
and the determining module is used for determining the gravity center position of each standard tooth and each tooth to be recognized under the coincident coordinate system.
In one embodiment, the tooth type to be recognized determining module 340 includes:
a current value determination module for determining a current value according to the current M k 、R k 、t k Determining the current value of the objective function according to the center of gravity position of the standard tooth and the center of gravity position of the tooth to be identified; wherein M represents a matching matrix, and M is equal to Z n×16 N represents the number of teeth to be identified; r represents the rotation amount; t represents the translation amount; k is the number of iterations;
R k and t k Optimization module for fixing M k Unchanged, update R k And t k Minimizing the value of the objective function, and determining the R corresponding to the minimized value of the objective function k And t k Is R k(min) And t k(min) ；
M k Optimization module for fixing R k(min) And t k(min) Unchanged, update M k Minimizing the value of the objective function, and determining M corresponding to the minimized value of the objective function k Is M k(min) ；
A current minimum value calculation module for calculating a current minimum value according to R k(min) 、t k(min) And M k(min) Calculating the current minimum value of the objective function;
a comparison module for M if the change between the current value of the objective function and the current minimum value of the objective function is less than a threshold value k(min) The type of the standard tooth represented by the column corresponding to the maximum value of each row is the type of the tooth to be identified represented by the corresponding row; and if the change between the current value of the target function and the current minimum value of the target function is larger than or equal to the threshold value, returning to the current value determining module, and adding 1 to k.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a user terminal in an embodiment, where the user terminal may be a conventional server or any other user terminal, and includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the memory may include a nonvolatile storage medium and an internal memory, the computer program may be stored in the nonvolatile storage medium, and the processor executes the program to implement the following steps: establishing a standard three-dimensional tooth model, and constructing a standard coordinate system of the standard three-dimensional tooth model; acquiring a segmented three-dimensional tooth model to be identified, and constructing a coordinate system of the three-dimensional tooth model to be identified; determining the gravity center position of each standard tooth in the standard three-dimensional tooth model and the gravity center position of each tooth to be recognized in the three-dimensional tooth model to be recognized according to the standard coordinate system and the coordinate system of the three-dimensional tooth model to be recognized; and determining the type of the tooth to be recognized in an alignment registration mode according to the position of the center of gravity of the standard tooth and the position of the center of gravity of the tooth to be recognized.
In one embodiment, the processor when executing the program may further implement the following steps: superposing the standard coordinate system and the coordinate system of the three-dimensional tooth model to be identified to obtain a superposed coordinate system; and determining the gravity center position of each standard tooth and each tooth to be identified under the coincident coordinate system.
In one embodiment, the processor when executing the program may further implement the following steps: (1) according to the current M k 、R k 、t k Determining the current value of the objective function according to the center of gravity position of the standard tooth and the center of gravity position of the tooth to be identified; wherein M represents a matching matrix, and M is equal to Z n×16 N represents the number of teeth to be identified; r represents the rotation amount; t represents the translation amount; k is the number of iterations; (2) fixed M k Unchanged, update R k And t k Minimizing the value of the objective function, and determining the R corresponding to the minimized value of the objective function k And t k Is R k(min) And t k(min) (ii) a (3) Fixing R k(min) And t k(min) Unchanged, update M k Minimizing the value of the objective function, and determining M corresponding to the minimized value of the objective function k Is M k(min) (ii) a (4) According to R k(min) 、t k(min) And M k(min) Calculating the current minimum value of the objective function; (5) if the change between the current value of the objective function and the current minimum value of the objective function is less than the threshold value, M k(min) The type of the standard tooth represented by the column corresponding to the maximum value of each row is the type of the tooth to be identified represented by the corresponding row; and (5) if the change between the current value of the target function and the current minimum value of the target function is larger than or equal to the threshold value, returning to the step (1), and adding 1 to k.
The above definition of the terminal can be referred to the above specific definition of the tooth type identification method, and is not described herein again.
With continuing reference to fig. 4, there is also provided a computer readable storage medium having stored thereon a computer program, such as the non-volatile storage medium shown in fig. 4, wherein the program when executed by a processor implements the steps of: establishing a standard three-dimensional tooth model, and constructing a standard coordinate system of the standard three-dimensional tooth model; acquiring a segmented three-dimensional tooth model to be identified, and constructing a coordinate system of the three-dimensional tooth model to be identified; determining the gravity center position of each standard tooth in the standard three-dimensional tooth model and the gravity center position of each tooth to be recognized in the three-dimensional tooth model to be recognized according to the standard coordinate system and the coordinate system of the three-dimensional tooth model to be recognized; and determining the type of the tooth to be recognized in an alignment registration mode according to the position of the center of gravity of the standard tooth and the position of the center of gravity of the tooth to be recognized.
In one embodiment, the processor when executing the program may further implement the following steps: superposing the standard coordinate system and the coordinate system of the three-dimensional tooth model to be identified to obtain a superposed coordinate system; and determining the gravity center position of each standard tooth and each tooth to be identified under the coincident coordinate system.
In one embodiment, the processor when executing the program may further implement the following steps: (1) according to the current M k 、R k 、t k Determining the current value of the objective function according to the center of gravity position of the standard tooth and the center of gravity position of the tooth to be identified; wherein M represents a matching matrix, and M is equal to Z n×16 N denotes the number of teeth to be markedMesh; r represents the rotation amount; t represents the translation amount; k is the number of iterations; (2) fixed M k Unchanged, update R k And t k Minimizing the value of the objective function, and determining the R corresponding to the minimized value of the objective function k And t k Is R k(min) And t k(min) (ii) a (3) Fixing R k(min) And t k(min) Unchanged, update M k Minimizing the value of the objective function, and determining M corresponding to the minimized value of the objective function k Is M k(min) (ii) a (4) According to R k(min) 、t k(min) And M k(min) Calculating the current minimum value of the objective function; (5) if the change between the current value of the objective function and the current minimum value of the objective function is less than the threshold value, M k(min) The type of the standard tooth represented by the column corresponding to the maximum value of each row is the type of the tooth to be identified represented by the corresponding row; and (5) if the change between the current value of the target function and the current minimum value of the target function is larger than or equal to the threshold value, returning to the step (1), and adding 1 to k.
The above definition of the computer-readable storage medium can be referred to the above specific definition of the tooth type identification method, and will not be described herein again.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (8)
1. A method of identifying a type of tooth, comprising the steps of:
establishing a standard three-dimensional tooth model, and constructing a standard coordinate system of the standard three-dimensional tooth model;
acquiring a segmented three-dimensional tooth model to be identified, and constructing a coordinate system of the three-dimensional tooth model to be identified;
according to the standard coordinate system and the coordinate system of the three-dimensional tooth model to be recognized, determining the gravity center position of each standard tooth in the standard three-dimensional tooth model and the gravity center position of each tooth to be recognized in the three-dimensional tooth model to be recognized;
determining the type of the tooth to be recognized in an alignment registration mode according to the gravity center position of the standard tooth and the gravity center position of the tooth to be recognized;
wherein the step of determining the position of the center of gravity of each standard tooth in the standard three-dimensional tooth model and the position of the center of gravity of each tooth to be recognized in the three-dimensional tooth model to be recognized comprises:
the standard coordinate system is overlapped with a coordinate system of the three-dimensional tooth model to be identified to obtain an overlapped coordinate system;
determining the gravity center position of each standard tooth and each tooth to be recognized under the coincident coordinate system;
wherein the step of determining the type of the tooth to be recognized through alignment registration according to the position of the center of gravity of the standard tooth and the position of the center of gravity of the tooth to be recognized comprises the following steps:
(1) according to the current M k 、R k 、t k Determining the current value of the objective function according to the center of gravity position of the standard tooth and the center of gravity position of the tooth to be identified; wherein M represents a matching matrix, and M is equal to Z n×16 N represents the number of teeth to be identified; r represents the rotation amount; t represents the translation amount; k is the number of iterations;
(2) fixing the M k Updating the R unchanged k And t k So as to minimize the value of the objective function, and determine the R corresponding to the minimum value of the objective function k And t k Is R k(min) And t k(min) ；
(3) Fixing the R k(min) And t k(min) Updating the M unchanged k Minimizing the value of the objective function, and determining M corresponding to the minimized value of the objective function k Is M k(min) ；
(4) According to the formula R k(min) 、t k(min) And M k(min) Calculating the current minimum value of the objective function;
(5) if the change between the current value of the objective function and the current minimum value of the objective function is less than a threshold value, M is k(min) The type of the standard tooth represented by the column corresponding to the maximum value of each row is the type of the tooth to be identified represented by the row corresponding to the standard tooth; if the change between the current value of the target function and the current minimum value of the target function is larger than or equal to the threshold value, the step (1) is returned, k is added with 1, and M at the moment k+1 、R k+1 、t k+1 Is M k(min) 、R k(min) And t k(min) 。
2. The method for identifying a type of tooth according to claim 1, wherein the determination of the initial M is as follows: calculating the barycentric distance between the ith tooth to be recognized and the jth standard tooth based on the barycentric positions of each standard tooth and each tooth to be recognized in the coincidence coordinate system, and determining the initial M according to the barycentric distance; wherein i is an integer of 1 to n; j is an integer of 1 to 16.
3. The method for identifying a type of tooth according to claim 2, wherein the formula of the objective function is:
and is
Wherein, P j Indicating the jth standard toothThe position of the center of gravity of the tooth; qi represents the position of the center of gravity of the ith tooth to be identified; m is ij Is the element in row i and column j in M, M ij And the matching degree of the ith tooth to be recognized belonging to the jth standard tooth is represented.
4. The method for identifying a tooth type according to claim 3, wherein said t is k The update formula of (2) is:
the R is k The update formula of (2) is: r k ＝VU T (ii) a Wherein V and U are obtained by SVD decomposition of the matrix S, and
5. the method for identifying a tooth type according to claim 3, wherein M is k The update formula of the element in the ith row and the jth column of (1) is: m is ij ＝exp(-||R k Q i +t k -P j || 2 )。
6. A tooth type identification device, comprising:
the standard three-dimensional tooth model establishing module is used for establishing a standard three-dimensional tooth model and establishing a standard coordinate system of the standard three-dimensional tooth model;
the identification system comprises a to-be-identified three-dimensional tooth model acquisition module, a to-be-identified three-dimensional tooth model acquisition module and a to-be-identified three-dimensional tooth model acquisition module, wherein the to-be-identified three-dimensional tooth model acquisition module is used for acquiring a segmented to-be-identified three-dimensional tooth model and establishing a coordinate system of the to-be-identified three-dimensional tooth model;
the center-of-gravity position determining module is used for determining the center-of-gravity position of each standard tooth in the standard three-dimensional tooth model and the center-of-gravity position of each tooth to be recognized in the three-dimensional tooth model to be recognized according to the standard coordinate system and the coordinate system of the three-dimensional tooth model to be recognized;
the tooth type determination module to be recognized is used for determining the type of the tooth to be recognized in an alignment and registration mode according to the gravity center position of the standard tooth and the gravity center position of the tooth to be recognized;
wherein the tooth type determination module to be identified is specifically configured to:
the standard coordinate system is overlapped with a coordinate system of the three-dimensional tooth model to be identified to obtain an overlapped coordinate system;
determining the gravity center position of each standard tooth and each tooth to be recognized under the coincident coordinate system;
wherein the content of the first and second substances,
(1) according to the current M k 、R k 、t k Determining the current value of the objective function according to the gravity center position of the standard tooth and the gravity center position of the tooth to be identified; wherein M represents a matching matrix, and M is equal to Z n×16 N represents the number of teeth to be identified; r represents the rotation amount; t represents the translation amount; k is the number of iterations;
(2) fixing the M k Updating the R unchanged k And t k So as to minimize the value of the objective function, and determine the R corresponding to the minimum value of the objective function k And t k Is R k(min) And t k(min) ；
(3) Fixing the R k(min) And t k(min) Updating the M unchanged k Minimizing the value of the objective function, and determining M corresponding to the minimized value of the objective function k Is M k(min) ；
(4) According to the formula R k(min) 、t k(min) And M k(min) Calculating the current minimum value of the objective function;
(5) if the change between the current value of the objective function and the current minimum value of the objective function is less than a threshold value, M is k(min) The type of the standard tooth represented by the column corresponding to the maximum value of each row is the type of the tooth to be identified represented by the row corresponding to the standard tooth; if the current value of the objective function is equal to the objectiveIf the change of the current minimum value of the function is more than or equal to the threshold value, the step (1) is returned, k is added with 1, and M at the moment k+1 、R k+1 、t k+1 Is M k(min) 、R k(min) And t k(min) 。
7. A user terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 5 are implemented when the processor executes the program.
8. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
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 CN108776992A (en) | 2018-11-09 |
| CN108776992B true 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) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111276239B (en) * | 2019-11-29 | 2023-06-27 | 正雅齿科科技(上海)有限公司 | Method and device for determining tooth position of tooth model |
| CN112790879B (en) * | 2020-12-30 | 2022-08-30 | 正雅齿科科技(上海)有限公司 | Tooth axis coordinate system construction method and system of tooth model |
| CN112989954B (en) * | 2021-02-20 | 2022-12-16 | 山东大学 | Three-dimensional tooth point cloud model data classification method and system based on deep learning |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102083387A (en) * | 2008-01-23 | 2011-06-01 | 森瑟博科技有限公司 | Haptically enabled dental modeling system |
| 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 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7080979B2 (en) * | 2001-04-13 | 2006-07-25 | Orametrix, Inc. | Method and workstation for generating virtual tooth models from three-dimensional tooth data |
| DE102010036436A1 (en) * | 2010-03-29 | 2011-09-29 | Degudent Gmbh | Method and arrangement for forming a dental model |
| GB201115265D0 (en) * | 2011-09-05 | 2011-10-19 | Materialise Dental Nv | A method and system for 3d root canal treatment planning |
-
2018
- 2018-05-04 CN CN201810417306.5A patent/CN108776992B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102083387A (en) * | 2008-01-23 | 2011-06-01 | 森瑟博科技有限公司 | Haptically enabled dental modeling system |
| 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 |
|---|
| Dental Biometrics: Alignment and Matching of Dental Radiographs;H. Chen and A. K. Jain;《2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION"05)》;20051231;第316-321页 * |
| 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》.2008, * |
| 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》.1999, * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108776992A (en) | 2018-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108776992B (en) | Tooth type identification method and device, user terminal and storage medium | |
| US11443494B2 (en) | Method for estimating at least one of shape, position and orientation of a dental restoration | |
| US20170329785A1 (en) | Application recommendation method, server, and computer readable medium | |
| US20230068041A1 (en) | Method and apparatus for generating orthodontic teeth arrangement shape | |
| WO2018228218A1 (en) | Identification method, computing device, and storage medium | |
| JP2009157767A (en) | Face image recognition apparatus, face image recognition method, face image recognition program, and recording medium recording this program | |
| JP2017529919A5 (en) | ||
| JP2017529919A (en) | A method for aligning an intraoral digital 3D model | |
| CN111178280A (en) | Human body sitting posture identification method, device, equipment and storage medium | |
| CN111784754A (en) | Tooth orthodontic method, device, equipment and storage medium based on computer vision | |
| CN112790879B (en) | Tooth axis coordinate system construction method and system of tooth model | |
| CN109686440B (en) | Online intelligent diagnosis cloud platform, operation method thereof and readable storage medium | |
| CN109165663B (en) | Tooth feature identification method and device, user terminal and storage medium | |
| CN112541900B (en) | Detection method and device based on convolutional neural network, computer equipment and storage medium | |
| Zhuang et al. | Robust hybrid learning for automatic teeth segmentation and labeling on 3D dental models | |
| JP2018089161A (en) | Target person recognition method, device, system, and program | |
| CN116246762A (en) | Prescription dose optimization method, device, equipment and medium based on artificial intelligence | |
| CN113377116A (en) | Gait planning method and device of robot, processing equipment and medium | |
| Kim et al. | Automatic tooth segmentation of dental mesh using a transverse plane | |
| CN110008812B (en) | Website login system based on iris recognition | |
| Ingole et al. | Medical image registration using genetic algorithm | |
| KR101584857B1 (en) | System and method for aligning genome sequnce | |
| US20240161431A1 (en) | Tooth point correspondence detection | |
| CN115830287B (en) | Tooth point cloud fusion method, device and medium based on laser mouth scanning and CBCT reconstruction | |
| CN116934821B (en) | Personalized denture three-dimensional image model registration method and system |
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 |