Method, computer-readable storage medium and device for identifying occlusal surface of tooth crown

By identifying the occlusal surface of the crown, the pre-entered tooth attribute data and grid model are used to extract feature points and fit planes, and the occlusal surface recognition problem in the complex case of crown morphology is solved, and the occlusal surface of the crown is realized Accurate identification and effective generation of connectors.

CN116091478BActive Publication Date: 2024-11-22SHENZHEN UP3D TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310172226.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-02-17
Publication Date
2024-11-22
Estimated Expiration
2043-02-17

AI Technical Summary

Technical Problem

The prior art is difficult to accurately identify the occlusal surface of the dental crown, especially when the dental crowns of different shapes and irregular shapes, resulting in difficulty in generating the connector.

Method used

By pre-entering tooth attribute data, determine the crown type and tooth position number, obtain the set of alternative points in the crown mesh model, select detection points, establish fitting plane, extract feature points, and follow the insertion direction and the angle of feature points. If less than 45°, obtain the occlusal area, gradually eliminate non-feature points, and form the identified crown occlusal area.

Benefits of technology

Accurate and effective identification of the crown occlusal surface is achieved, interference is reduced, and the accuracy of connecting body generation is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116091478B_ABST
    Figure CN116091478B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of crown occlusal surface recognition, and in particular to a method, computer-readable storage medium and device for recognizing crown occlusal surface. The method for recognizing crown occlusal surface is to determine the type and tooth position number of the crown according to pre-entered tooth attribute data, then obtain the position of the occlusal surface, and then obtain a candidate point set, select detection points from the candidate point set, and then establish a fitting plane and extract feature points; take the intersection of the insertion direction and the top surface of the crown model as the top surface center, and the average distance from all points in the candidate point set to the top surface center as the radius, traverse the grid model, and take the angle between the normal of the feature point and the insertion direction less than 45° as a constraint condition, obtain the occlusal surface point set from the feature points, and form the recognized occlusal surface through the occlusal surface point set. By gradually eliminating non-feature points, the final occlusal surface point set is obtained, and the recognized crown occlusal surface is formed through the occlusal surface point set. In this way, the occlusal surface of the crown is accurately and effectively recognized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of tooth crown occlusal surface recognition, and in particular to a method for recognizing a tooth crown occlusal surface, a computer-readable storage medium and a device. Background Art

[0002] In clinical practice, connectors are required to fix the crowns of complete dentures and partial dentures. The shape range of connectors is different for the "occlusal surface" of crowns of different shapes (canines, incisors, molars) and the contact surface with adjacent teeth. Connectors cannot be on the buccal and lingual sides of teeth or in the occlusal direction. Therefore, the generation of connectors requires the occlusal surface identification of crowns to constrain the range of connectors. Crowns of different shapes (inner crowns, inner crown bridges, full crowns, full crown bridges, cut-back crowns, cut-back crown bridges) and shapes are irregular, which adds a lot of interference to the identification of occlusal surfaces.

[0003] It can be seen that how to accurately and effectively identify the occlusal surface of the crown is a technical problem that needs to be solved urgently. Summary of the invention

[0004] In order to solve the technical problem of how to accurately and effectively identify the occlusal surface of a tooth crown, the present invention proposes a method for identifying the occlusal surface of a tooth crown, comprising the following steps:

[0005] Determine the type and tooth position number of the crown according to the pre-entered tooth attribute data;

[0006] The position of the occlusal surface in the current direction is obtained by inserting the direction;

[0007] Obtaining a candidate point set in the tooth crown mesh model;

[0008] Select a detection point from the candidate point set;

[0009] Establishing a fitting plane according to the neighboring points of the detection point;

[0010] Extracting feature points by referring to the Euclidean distances between the detection point and the neighboring points of the detection point and the fitting plane;

[0011] Taking the intersection of the insertion direction and the top surface of the crown model as the top surface center, and the average distance from all points in the candidate point set to the top surface center as the radius, traverse the grid model to obtain the occlusal surface range;

[0012] Taking the angle between the normal of the feature point and the insertion direction being less than 45° as a constraint condition, an occlusal surface point set is obtained from the feature points within the occlusal surface range, and the identified crown occlusal surface is formed by the occlusal surface point set.

[0013] Furthermore, the step of obtaining a candidate point set in the tooth crown mesh model further includes the following steps:

[0014] Calculate the curvature Kn of all points in the grid model;

[0015] Calculate the average curvature Ks based on the curvatures of all points;

[0016] The set of points whose curvature Kn is greater than the average curvature Ks is selected as the candidate point set.

[0017] Furthermore, the step of calculating the curvature Kn of all points in the grid model further comprises the following steps:

[0018] determining a normal to the point;

[0019] Making a plurality of cutting planes through the normal line, each of the cutting planes intersects with the curved surface of the mesh model to form an intersection line;

[0020] Calculate the curvature km of the point on each of the intersection lines, and select the maximum value ka and the minimum value kb of the curvature;

[0021] The curvature of the point is Kn=(ka+kb) / 2.

[0022] Furthermore, in the step of selecting a detection point from a candidate point set, each point in the candidate point set can be used as the detection point.

[0023] Furthermore, in the step of establishing a fitting plane according to neighboring points of the detection point, the fitting plane is established by using a least square method.

[0024] Furthermore, the steps of extracting the feature points are as follows:

[0025] Find each neighboring point of the detection point as a query point;

[0026] Selecting a candidate point from among the detection points;

[0027] Calculate the eigenvalue T of each candidate point, and calculate the average eigenvalue t of the eigenvalues ​​of all candidate points based on the eigenvalue;

[0028] The candidate points whose eigenvalues ​​T are greater than the average eigenvalue t are selected as feature points.

[0029] Furthermore, the step of selecting a candidate point from the detection points further comprises the following steps:

[0030] Calculating the Euclidean distance di from the detection point to the fitting plane;

[0031] Calculating the Euclidean distance dn from each query point to the fitting plane;

[0032] Calculate the average value μ of the Euclidean distances dn from all the query points to the fitting plane;

[0033] The difference Δd between di and μ is calculated, and the detection point with a positive Δd is selected as the candidate point.

[0034] Furthermore, the step of calculating the eigenvalue T of each candidate point, and calculating the average eigenvalue t of the eigenvalues ​​of all candidate points according to the eigenvalue, further comprises the following steps:

[0035] Calculate the standard deviation σ of the Euclidean distance between the query point and the fitting plane, and determine the degree of dispersion of the query point by the standard deviation σ;

[0036] Calculate the absolute value of the Euclidean distance between the candidate point and the fitting plane |di|;

[0037] Calculating the curvature kv of the candidate point;

[0038] The calculation formula of the eigenvalue T is, T=σ×|di|×kv.

[0039] On the other hand, the present application also proposes a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned method for identifying the occlusal surface of a dental crown when the program is executed by a processor.

[0040] On the other hand, the present application also proposes a device, comprising: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the device executes the above-mentioned method for identifying the occlusal surface of a dental crown.

[0041] The technical effects of the present invention are as follows: the present invention provides a method for identifying the occlusal surface of a crown, determining the type and tooth position number of the crown according to the pre-entered tooth attribute data; obtaining the position of the occlusal surface in the current direction through the insertion direction; obtaining a candidate point set in the crown mesh model; selecting a detection point in the candidate point set; establishing a fitting plane according to the neighboring points of the detection point; extracting feature points by referring to the Euclidean distance between the detection point of the mesh model and the neighboring points of the detection point of the mesh model to the fitting plane of the mesh model; taking the intersection of the insertion direction and the top surface of the crown model as the top surface center, and the average distance from all points in the candidate point set to the top surface center as the radius, traversing the mesh model to obtain the range of the occlusal surface; taking the angle between the normal of the feature point and the insertion direction less than 45° as a constraint condition, obtaining the occlusal surface point set from the feature points within the occlusal surface range, and forming the identified crown occlusal surface through the occlusal surface point set. By gradually eliminating non-feature points, the final occlusal surface point set is obtained, and the identified crown occlusal surface is formed through the occlusal surface point set. In this way, the occlusal surface of the crown is accurately and effectively identified. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of the process of the method for identifying the occlusal surface of a tooth crown provided by the present invention;

[0043] Figure 2 A schematic diagram of the distribution of candidate point sets in a tooth digital model in the method for identifying the occlusal surface of a tooth crown provided by the present invention;

[0044] Figure 3 A schematic diagram of the distribution of candidate points in a digital tooth model in the method for identifying the occlusal surface of a tooth crown provided by the present invention;

[0045] Figure 4 A schematic diagram of the distribution of the occlusal surface point set in the tooth digital model in the method for identifying the occlusal surface of a tooth crown provided by the present invention;

[0046] Figure 5 A schematic diagram of identifying the occlusal surface of a full crown in the method for identifying the occlusal surface of a tooth crown provided by the present invention;

[0047] Figure 6 A schematic diagram of identifying the occlusal surface of an inner crown in the method for identifying the occlusal surface of a dental crown provided by the present invention;

[0048] Figure 7 A schematic diagram of identifying the occlusal surface of a bridge in the method for identifying the occlusal surface of a tooth crown provided by the present invention;

[0049] Figure 8 A schematic diagram of a fitting plane of a detection point and its neighboring points in the method for identifying the occlusal surface of a tooth crown provided by the present invention, wherein Pi is a detection point, Pi' is a projection of the detection point on the fitting plane, and Pi1', Pi2', Pi3', Pi4', Pi5', and Pi6' are projections of the neighboring points of the detection point on the fitting plane;

[0050] Fig. 9 This is a schematic diagram of the projection of the detection point and its neighboring points onto the fitting plane in the method for identifying the occlusal surface of a tooth crown provided by the present invention, wherein Pi is the detection point, and Pi1, Pi2, Pi3, Pi4, Pi5, and Pi6 are the neighboring points of the detection point. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] See also Figures 1 to 9 The present invention provides a method for identifying the occlusal surface of a tooth crown, comprising the following steps:

[0053] Determine the type and tooth position number of the crown according to the pre-entered tooth attribute data;

[0054] The position of the occlusal surface in the current direction is obtained by inserting the direction;

[0055] Obtaining a candidate point set in the tooth crown mesh model;

[0056] Select a detection point from the candidate point set;

[0057] Establish a fitting plane based on the neighboring points of the detection point;

[0058] Extract feature points by referring to the Euclidean distance between the detection point and the neighboring points of the detection point and the fitting plane;

[0059] The intersection of the insertion direction and the top surface of the crown model is taken as the center of the top surface, and the average distance from all points in the candidate point set to the center of the top surface is taken as the radius. The grid model is traversed to obtain the occlusal surface range. The angle between the normal of the feature point and the insertion direction is less than 45° as a constraint condition, and the occlusal surface point set is obtained from the feature points within the occlusal surface range. The occlusal surface of the recognized crown is formed through the occlusal surface point set.

[0060] It is understandable that the ini file of the operation program records the attribute file of each tooth, including the type of crown and tooth position number. The attribute data of the tooth is entered into the ini file in advance. When the occlusal surface of the crown is identified, the attribute data of the corresponding tooth is retrieved from the ini file to determine the type of crown and tooth position number, and the type and model of the connector are preliminarily determined based on the type of crown and tooth position number.

[0061] The growth direction of the tooth is the insertion direction, and the approximate position of the occlusal surface in the current direction can be obtained based on the insertion direction. When the insertion direction is downward, the occlusal surface of the crown is downward; when the insertion direction is upward, the occlusal surface of the crown is upward.

[0062] The occlusal surface is uneven. According to the characteristics of the occlusal surface, the candidate point set that may form the occlusal surface is determined in the mesh model of the crown, and the points in the mesh model that do not have the conditions to form the occlusal surface are eliminated to narrow the recognition range of the calculation program. Among them, the curvature of all points in the mesh model can be used to determine whether the points in the mesh model have the conditions to form the occlusal surface. The larger the curvature, the sharper the surface, the more uneven the surface, and the more obvious its characteristics.

[0063] Points in the candidate point set are selected as detection points, and feature points are extracted by comparing the detection points with their neighboring points. When comparing, a fitting plane is established based on the neighboring points of the detection point, and the Euclidean distances from the detection point and all its neighboring points to the fitting plane corresponding to the detection point are calculated, and feature points are extracted by referring to the Euclidean distances from the detection point and its neighboring points to the fitting plane.

[0064] The intersection of the insertion direction and the top surface of the crown model is taken as the center of the top surface, and the top surface center is used as the starting point to diffusely access the feature points in the surrounding patches. The average distance from all points in the candidate point set to the top surface center is taken as the radius. If the distance from the accessed feature point to the top surface center is less than this radius, it can be judged that the accessed feature point is within the occlusal surface range. Taking the angle between the normal of the feature point in the occlusal surface and the insertion direction less than 45° as a constraint condition, the feature points in the occlusal surface are further extracted. It should be pointed out that if the distance from the accessed feature point to the top surface center is greater than the average distance from all points in the candidate point set to the top surface center, it means that the accessed feature point is outside the occlusal surface range, that is, the feature points covered by the circular range formed by taking the average distance from all points in the candidate point set to the top surface center as the radius and the top surface center as the center of the circle can be regarded as within the occlusal surface range.

[0065] Since the orientation of the occlusal surface should be close to the insertion direction of the tooth, the angle is limited to 45°. Points suitable for forming the occlusal surface are obtained from the extracted feature points, and an occlusal surface point set is formed. The identified occlusal surface is formed through the occlusal surface point set. It should be pointed out that when the angle between the normal direction of the feature point in the occlusal surface and the insertion direction is greater than 45°, it means that this point is located on the side of the tooth.

[0066] In this way, by gradually eliminating non-feature points, the final occlusal surface point set is obtained, and the identified crown occlusal surface is formed by the occlusal surface point set, thereby accurately and effectively identifying the occlusal surface of the crown.

[0067] In some embodiments of the present application, the step of obtaining a candidate point set in the tooth crown mesh model further includes the following steps:

[0068] Calculate the curvature Kn of all points in the mesh model;

[0069] Calculate the average curvature Ks based on the curvatures of all points;

[0070] A set of points whose curvature Kn is greater than the average curvature Ks is selected as the candidate point set.

[0071] It can be understood that curvature can characterize the degree of curvature of a curve. The greater the curvature, the more curved the curve is, indicating that the surface here is sharper. The characteristic of the occlusal surface is that the patch of the occlusal surface is not flat on the surface, so the set of points with larger curvature of the curve passing through the points in the grid model is selected as the candidate point set. If the curvature Kn of a point is greater than the average curvature Ks of all points, it means that the flatness of the patch where this point is located is low, and there is a greater possibility that it is located in the occlusal surface, so the set of points with curvature Kn of the point greater than the average curvature Ks is selected as the candidate point set.

[0072] In some embodiments of the present application, the step of calculating the curvature Kn of all points in the mesh model further includes the following steps:

[0073] Determine the normal of a point;

[0074] Make several cutting planes through the normal line, each cutting plane intersects with the surface of the mesh model and forms an intersection line;

[0075] Calculate the curvature km of the point on each intersection line, and select the maximum value ka and the minimum value kb of the curvature;

[0076] The curvature of a point is Kn = (ka + kb) / 2.

[0077] It can be understood that when calculating the curvature of a point in the tooth mesh model, the normal of this point is first determined. There can be an infinite number of cutting planes through this normal, and each cutting plane intersects with the curved surface of the mesh model. The intersection line is a plane curve; the curvature km of this point on each curve is calculated, and the maximum value ka and the minimum value kb of the curvature are selected. Then the curvature of this point is the average curvature Kn = (ka + kb) / 2. Among them, the calculation formula of curvature is: curvature = length of curve rotation / angle of curve rotation.

[0078] In some embodiments of the present application, in the step of selecting a detection point from a candidate point set, each point in the candidate point set can be used as a detection point.

[0079] It can be understood that the larger the curvature, the more curved the curve is, which means the surface here is sharper, that is, the surface at this point in the grid model is more uneven. Therefore, the point with a larger curvature of the curve passing through the point in the grid model is selected as the detection point in the candidate point set, and the feature point is extracted by comparing the detection point with the neighboring points of this detection point.

[0080] See also Figures 8 to 9 In some embodiments of the present application, in the step of establishing a fitting plane based on the neighboring points of the detection point, the fitting plane is established using the least squares method.

[0081] It can be understood that the least squares method makes the fitting object closer and closer to the final object by minimizing the sum of squares of errors. Fitting a plane by the least squares method is to find a plane where the Euclidean distance of all the neighboring points of this detection point to the fitting plane is the smallest. Using this fitting plane as a reference, calculate the distance between the detection point and its neighboring points. The farther the detection point is from the fitting plane, the farther the detection point is from its neighboring points, which means that the triangular patch formed by this detection point and its neighboring points is narrower and longer. Therefore, it can be judged that the patch is more uneven on the surface, and unevenness is one of the characteristics of the occlusal surface, so this detection point has a higher probability of being a feature point.

[0082] When making a preliminary judgment on a feature point, you can compare the Euclidean distance from the detection point to the fitting plane with the Euclidean distance from its neighboring points to the fitting plane. If the Euclidean distance from this detection point to the fitting plane is greater than the Euclidean distance from all its neighboring points to the fitting plane, then this detection point is likely to be a feature point. You can also compare the Euclidean distance from the detection point to the fitting plane with the average of the Euclidean distances from all of its neighboring points to the fitting plane. If the Euclidean distance from this detection point to the fitting plane is greater than the average of the Euclidean distances from its neighboring points to the fitting plane, then this detection point is likely to be a feature point. Fig. 9 As shown in (b), if the Euclidean distance from this detection point to the fitting plane is less than the average value of the Euclidean distances from its neighboring points to the fitting plane, it means that the detection point is intertwined with its neighboring points and cannot be defined as a feature point. The standard deviation of the Euclidean distances from the neighboring points of this detection point to the fitting plane can also be calculated. The discreteness of the neighboring points of this detection point can be judged by the calculated standard deviation. The larger the calculated standard deviation, the greater the discreteness, indicating that the distribution difference of the neighboring points of the detection point is large. The large difference in the distribution of the neighboring points indicates that this point is far away from its neighboring points. The narrower and longer the triangular patch formed with the neighboring points, the more uneven the patch is on the surface. Unevenness is one of the characteristics of the occlusal surface, so this detection point has a higher possibility of being a feature point.

[0083] In some embodiments of the present application, the step of extracting feature points by referring to the Euclidean distance between the detection point and the neighboring point of the detection point and the fitting plane further includes the following steps:

[0084] Find each neighboring point of the detection point as a query point;

[0085] Select candidate points from the detection points;

[0086] Calculate the eigenvalue T of each candidate point, and calculate the average eigenvalue t of the eigenvalues ​​of all candidate points based on the eigenvalue;

[0087] The candidate points whose eigenvalue T is greater than the average eigenvalue t are selected as feature points.

[0088] It can be understood that the curvature of all points in the grid model is calculated, and the average curvature of all points is calculated. The curvature of the detection point is greater than the average curvature of all points. All or part of the neighboring points of the detection point are used as query points, and a fitting plane is generated through the selected query points. The average value of the Euclidean distance from the query point to the fitting plane is calculated, and the average value of the Euclidean distance from the detection point to the fitting plane is compared with the average value of the Euclidean distance from the query point to the fitting plane. If the Euclidean distance from the detection point to the fitting plane is greater than the average value of the Euclidean distance from the query point to the fitting plane, then this detection point is a candidate point, and the eigenvalue T of this candidate point can be calculated, wherein the eigenvalue T of the candidate point is proportional to the standard deviation of the distance from the query point to the fitting plane, the absolute value of the distance from the candidate point to the plane, and the curvature of the candidate point. The eigenvalue T and the average eigenvalue t of all candidate points are calculated, and the candidate points whose eigenvalue T is greater than the average eigenvalue t are selected as feature points.

[0089] In some embodiments of the present application, the step of selecting a candidate point from the detection points further includes the following steps:

[0090] Calculate the Euclidean distance di from the detection point to the fitting plane;

[0091] Calculate the Euclidean distance dn from each query point to the fitting plane;

[0092] Calculate the average value μ of the Euclidean distance dn from all query points to the fitting plane;

[0093] Calculate the difference Δd between di and μ, and select the detection point with a positive value of Δd as the candidate point.

[0094] It can be understood that, by comparing the Euclidean distance di from the detection point to the fitting plane with the average value μ of the Euclidean distances of all the neighboring points of this detection point to the fitting plane, if the Euclidean distance di from this detection point to the fitting plane is greater than the average value μ of the Euclidean distances of its neighboring points to the fitting plane, that is, di-μ=□d, Δd>0, then this detection point has a greater possibility of being a feature point, and this detection point can be selected as a candidate point. If the Euclidean distance di from this detection point to the fitting plane is less than or equal to the average value μ of the Euclidean distances of its neighboring points to the fitting plane, that is, di-μ=□d, Δd≤0, it means that the detection point is intertwined with its neighboring points and cannot be defined as a feature point.

[0095] In some embodiments of the present application, the step of calculating the eigenvalue T of each candidate point, and calculating the average eigenvalue t of the eigenvalues ​​of all candidate points according to the eigenvalue, further includes the following steps:

[0096] Calculate the standard deviation σ of the Euclidean distance from the query point to the fitting plane, and use the standard deviation σ to determine the degree of dispersion of the query point;

[0097] Calculate the absolute value of the Euclidean distance from the candidate point to the fitting plane |di|;

[0098] Calculate the curvature kv of the candidate point;

[0099] The calculation formula of the eigenvalue T is, T = σ × | di | × kv.

[0100] It can be understood that the larger the standard deviation σ of the Euclidean distance from the query point to the fitting plane, the greater the degree of dispersion of the candidate point's neighboring points, indicating that the distribution difference of the candidate point's neighboring points is large. The large difference in the distribution of neighboring points indicates that this candidate point is far away from its neighboring points, and the narrower and longer the triangular patch formed with the neighboring points is, the more uneven the patch is on the surface. The larger the absolute value |di| of the Euclidean distance from the candidate point to the fitting plane, the farther the candidate point is from the fitting plane, the sharper the surface formed by the candidate point and its neighboring points, and the more uneven the surface at this candidate point is. The larger the curvature of the candidate point, the more the curve is curved, indicating that the surface here is sharper, that is, the surface at this point in the mesh model is more uneven. Therefore, the eigenvalue T of the candidate point is proportional to the standard deviation σ of the distance from the query point to the fitting plane, the absolute value |di| of the distance from the candidate point to the plane, and the curvature kv of the candidate point. Let eigenvalue T = σ×|di|×kv, then the eigenvalue T of all candidate points can be calculated, and the average eigenvalue t can be calculated based on the eigenvalue T of all candidate points. Compare the eigenvalue T of the candidate point with the average eigenvalue t, and select the candidate point whose eigenvalue T is greater than the average eigenvalue t as the feature point. The feature points are further screened by the set constraints, and finally the occlusal surface point set is obtained, and then the identified occlusal surface is formed by the occlusal surface point set.

[0101] In this way, by gradually eliminating non-feature points, the final occlusal surface point set is obtained, and the identified crown occlusal surface is formed by the occlusal surface point set, thereby accurately and effectively identifying the occlusal surface of the crown.

[0102] In addition, in some embodiments of the present application, the present application further proposes a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the method for identifying the occlusal surface of a dental crown proposed in the present application is implemented.

[0103] In addition, in some embodiments of the present application, the present application also proposes a device, including: a processor and a memory; the memory is used to store computer programs, and the processor is used to execute the computer programs stored in the memory, so that the device executes the method for identifying the occlusal surface of a crown proposed in the present application.

[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not drive the essence of the corresponding technical solutions away from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying the occlusal surface of a tooth crown, characterized in that: The steps include: Determine the type and tooth position number of the crown according to the pre-entered tooth attribute data; The position of the occlusal surface in the current direction is obtained by inserting the direction; Obtaining a candidate point set in the tooth crown mesh model; Select a detection point from the candidate point set; Establishing a fitting plane according to the neighboring points of the detection point; Extracting feature points by referring to the Euclidean distances between the detection point and the neighboring points of the detection point and the fitting plane; Taking the intersection of the insertion direction and the top surface of the crown model as the top surface center, and the average distance from all points in the candidate point set to the top surface center as the radius, traverse the grid model to obtain the occlusal surface range; Taking the angle between the normal of the feature point and the insertion direction being less than 45° as a constraint condition, an occlusal surface point set is obtained from the feature points within the occlusal surface range, and the identified crown occlusal surface is formed by the occlusal surface point set.

2. The method for identifying the occlusal surface of a tooth crown according to claim 1, characterized in that: The step of obtaining a candidate point set in the tooth crown mesh model further includes the following steps: Calculate the curvature Kn of all points in the grid model; Calculate the average curvature Ks based on the curvatures of all points; The set of points whose curvature Kn is greater than the average curvature Ks is selected as the candidate point set.

3. The method for identifying the occlusal surface of a tooth crown according to claim 2, characterized in that: The step of calculating the curvature Kn of all points in the grid model further comprises the following steps: determining a normal to the point; Making a plurality of cutting planes through the normal line, each of the cutting planes intersects with the curved surface of the mesh model to form an intersection line; Calculate the curvature km of the point on each of the intersection lines, and select the maximum value ka and the minimum value kb of the curvature; The curvature of the point is Kn=(ka+kb) / 2.

4. The method for identifying the occlusal surface of a tooth crown according to claim 1, characterized in that: In the step of selecting a detection point from a candidate point set, each point in the candidate point set can be used as the detection point.

5. The method for identifying the occlusal surface of a tooth crown according to claim 1, characterized in that: The step is to establish a fitting plane according to the neighboring points of the detection point, and to establish the fitting plane using the least square method.

6. The method for identifying the occlusal surface of a tooth crown according to claim 1, characterized in that: The step of extracting feature points by referring to the Euclidean distances between the detection point and the neighboring points of the detection point and the fitting plane further comprises the following steps: Selecting a candidate point from among the detection points; Calculate the eigenvalue T of each candidate point, and calculate the average eigenvalue t of the eigenvalues ​​of all candidate points based on the eigenvalue; The candidate points whose eigenvalues ​​T are greater than the average eigenvalue t are selected as feature points.

7. The method for identifying the occlusal surface of a tooth crown according to claim 6, characterized in that: The step of selecting a candidate point from the detection points further comprises the following steps: Find each neighboring point of the detection point as a query point; Calculating the Euclidean distance di from the detection point to the fitting plane; Calculating the Euclidean distance dn from each query point to the fitting plane; Calculate the average value μ of the Euclidean distances dn from all the query points to the fitting plane; Calculate the difference between di and μ Δ d, select Δ The detection point that is upright is the candidate point.

8. The method for identifying the occlusal surface of a tooth crown according to claim 6, characterized in that: The step calculates the eigenvalue T of each candidate point, and calculates the average eigenvalue t of the eigenvalues ​​of all candidate points according to the eigenvalue, further comprising the following steps: Find each neighboring point of the detection point as a query point; Calculate the standard deviation σ of the Euclidean distance between the query point and the fitting plane, and determine the degree of dispersion of the query point by the standard deviation σ; Calculate the absolute value of the Euclidean distance between the candidate point and the fitting plane |di|; Calculating the curvature kv of the candidate point; The calculation formula of the eigenvalue T is, T=σ×|di|×kv.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for identifying the occlusal surface of a tooth crown as claimed in any one of claims 1 to 8 is implemented.

10. A device, characterized in that: include: Processor and memory; The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the device executes the method for identifying the occlusal surface of a tooth crown as claimed in any one of claims 1 to 8.