Dental jaw three-dimensional model local coordinate system analysis method, device, equipment and medium

Abstract

The invention relates to the technical field of oral cavities, and discloses a dental three-dimensional model local coordinate system analysis method, device and equipment and a medium, and the method comprises the steps: carrying out the three-dimensional data scanning of a dental region, and obtaining a dental three-dimensional digital model; dividing the dental jaw three-dimensional digital model into a plurality of groups of dental crown three-dimensional digital models; establishing a global coordinate system according to the dental crown three-dimensional digital model, and calculating a centroid according to the global coordinate system; constructing an initial local coordinate system according to the centroid, and performing offset point cluster analysis on the local coordinate system to obtain an offset point cluster; and calculating a direction unit vector according to the offset point cluster, and establishing a local coordinate system according to the direction unit vector. And through automatic calculation, subjective judgment and personal errors in manual operation are effectively avoided, so that the consistency and reliability of treatment results are improved.

Description

Technical Field

[0001] The present invention relates to the field of oral technologies, and in particular to a method, apparatus, device and medium for analyzing a local coordinate system of a dental arch three-dimensional model. Background Art

[0002] In computer-aided dental diagnosis and treatment, the construction of a three-dimensional digital model is crucial, especially the setting of the local coordinate system of teeth. This process usually relies on establishing a world coordinate system and creating corresponding local coordinate systems for each tooth to accurately represent the pose of the teeth.

[0003] The existing technology mainly relies on manual intervention in the process of setting the local coordinate system of teeth. However, the operation differences of different technicians may lead to inconsistent annotation results, and the process of manually adjusting the coordinate system is time-consuming and laborious, seriously affecting work efficiency, resulting in inconsistent and inefficient processes. This not only increases the labor cost but also limits the popularization and application of the technology. Especially in large-scale diagnoses and treatments that require efficient processing, there are obvious deficiencies. Summary of the Invention

[0004] The present invention provides a method, apparatus, device and medium for analyzing a local coordinate system of a dental arch three-dimensional model. By setting the exposure time to be alternately staggered, high-energy and low-energy acquisitions are alternately realized, thereby eliminating the cross-scattering phenomenon.

[0005] In a first aspect, a method for analyzing a local coordinate system of a dental arch three-dimensional model is provided, including:

[0006] Performing three-dimensional data scanning on a dental arch area to obtain a dental arch three-dimensional digital model;

[0007] Dividing the dental arch three-dimensional digital model into multiple groups of dental crown three-dimensional digital models;

[0008] Establishing a global coordinate system according to the dental crown three-dimensional digital model and calculating the centroid according to the global coordinate system;

[0009] Constructing an initial local coordinate system according to the centroid and performing offset point cluster analysis on the local coordinate system to obtain an offset point cluster;

[0010] Calculating a direction unit vector according to the offset point cluster and establishing a local coordinate system according to the direction unit vector.

[0011] In a second aspect, a device for analyzing a local coordinate system of a dental arch three-dimensional model is provided, including:

[0012] A scanning module, configured to perform three-dimensional data scanning on a dental arch area to obtain a dental arch three-dimensional digital model;

[0013] A partitioning module, configured to partition the three-dimensional digital dental model into multiple groups of three-dimensional digital crown models;

[0014] An establishing module, configured to establish a global coordinate system according to the three-dimensional digital crown models;

[0015] A calculating module, configured to calculate the centroid according to the global coordinate system;

[0016] A constructing module, configured to construct an initial local coordinate system according to the centroid;

[0017] An analyzing module, configured to perform an offset point cluster analysis on the local coordinate system to obtain an offset point cluster;

[0018] A vector calculating module, configured to calculate a direction unit vector according to the offset point cluster;

[0019] A local coordinate system establishing module, configured to establish a local coordinate system according to the direction unit vector.

[0020] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned method for analyzing the local coordinate system of a three-dimensional dental model are implemented.

[0021] In a fourth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for analyzing the local coordinate system of a three-dimensional dental model are implemented.

[0022] In the solution implemented by the above method, device, computer equipment and storage medium for analyzing the local coordinate system of a dental jaw three-dimensional model, the present invention adopts advanced deep learning algorithms and point cloud analysis techniques to achieve the automatic processing of dental jaw three-dimensional digital models. This method effectively reduces the need for manual intervention, significantly improves the data processing speed, shortens the overall processing time, and thus enhances the work efficiency. It is particularly suitable for the rapid processing of large-scale data. For different types of teeth, including normal teeth and malformed teeth, it can effectively calculate the crown direction, and is compatible with existing oral scanners and medical imaging systems. Its design has wide adaptability and can meet various clinical needs, being applicable to different patients and treatment scenarios. The accurate crown direction data provided by the present invention provides a reliable basis for personalized treatment and restoration design. During the process of crown shaping, denture fabrication and orthodontics, the treatment plan can be optimized according to the calculation results, thereby improving the treatment effect, ensuring the balance between functionality and aesthetics for patients, and enhancing patient comfort. Through automatic calculation, this method effectively avoids subjective judgments and human errors in manual operations, thereby improving the consistency and reliability of treatment results. Compared with traditional manual measurements, this method can significantly reduce the failure rate of restoration and the probability of postoperative complications, and improve the accuracy of treatment. Based on the patient's oral scan data, the present invention can customize personalized treatment plans for each patient. The accurate crown direction data provides strong support for the treatment process, thereby enhancing the level of personalization of treatment and further improving the treatment success rate and treatment experience of patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for the description of the embodiments of the present invention. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0024] Figure 1 It is a schematic diagram of an application environment of a method for analyzing the local coordinate system of a dental jaw three-dimensional model in an embodiment of the present invention;

[0025] Figure 2 It is a schematic flowchart of a method for analyzing the local coordinate system of a dental jaw three-dimensional model in an embodiment of the present invention;

[0026] Figure 3 It is a schematic structural diagram of a device for analyzing the local coordinate system of a dental jaw three-dimensional model in an embodiment of the present invention;

[0027] Figure 4 It is a flowchart of local coordinate system calculation in an embodiment of the present invention;

[0028] Figure 5 It is a three-dimensional digital model diagram of a dental crown in an embodiment of the present invention;

[0029] Figure 6 It is a distribution diagram of the initial tooth point cloud of a single dental crown in an embodiment of the present invention;

[0030] Figure 7 It is a predicted offset point cluster of a single dental crown in an embodiment of the present invention;

[0031] Figure 8 It is a schematic structural diagram of a computer device in an embodiment of the present invention;

[0032] Figure 9 It is another schematic structural diagram of a computer device in an embodiment of the present invention. Detailed implementation manners

[0033] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0034] A method for analyzing a local coordinate system of a dental jaw three-dimensional model provided by an embodiment of the present invention can be applied, for example, in Figure 1In the application environment, the client communicates with the server through the network. The server can perform three-dimensional data scanning on the dental arch area to obtain a three-dimensional digital model of the dental arch; divide the three-dimensional digital model of the dental arch into multiple groups of three-dimensional digital models of dental crowns; establish a global coordinate system based on the three-dimensional digital model of the dental crown, and calculate the centroid according to the global coordinate system; construct an initial local coordinate system based on the centroid, and perform offset point cluster analysis on the local coordinate system to obtain an offset point cluster; calculate a direction unit vector according to the offset point cluster, and establish a local coordinate system according to the direction unit vector, and feedback the local coordinate system to the client. The present invention provides an apparatus for analyzing the local coordinate system of a three-dimensional dental arch model. For the service of constructing a local coordinate system, three-dimensional data scanning is performed on the dental arch area to obtain a three-dimensional digital model of the dental arch; the three-dimensional digital model of the dental arch is divided into multiple groups of three-dimensional digital models of dental crowns; a global coordinate system is established based on the three-dimensional digital model of the dental crown, and the centroid is calculated according to the global coordinate system; an initial local coordinate system is constructed based on the centroid, and offset point cluster analysis is performed on the local coordinate system to obtain an offset point cluster; a direction unit vector is calculated according to the offset point cluster, and a local coordinate system is established according to the direction unit vector. Through automated calculation, subjective judgment and human error in manual operations are effectively avoided, thereby improving the consistency and reliability of treatment results. Among them, the client can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The server can be implemented by an independent server or a server cluster composed of multiple servers. The present invention will be described in detail below through specific embodiments.

[0035] Please refer to Figure 2 as shown in Figure 2 which is a schematic flowchart of a method for analyzing the local coordinate system of a three-dimensional dental arch model provided by an embodiment of the present invention, and includes the following steps:

[0036] S1. Perform three-dimensional data scanning on the dental arch area to obtain a three-dimensional digital model of the dental arch.

[0037] In the embodiment of the present invention, the three-dimensional data scanning refers to the process of converting the physical shape and structure of the dental arch area into a three-dimensional digital model through specific technical means.

[0038] In the embodiment of the present invention, the dental arch area is scanned by a high-precision oral scanner or a multi-modal digital device to obtain high-resolution three-dimensional point cloud data including a complete dentition and part of the gingival tissue; in some cases, the three-dimensional digital model can be constructed by scanning the physical model (such as a plaster model) of the patient's dental arch; in addition, in some embodiments, the three-dimensional digital model of the dental arch can also be obtained by scanning the patient's bite mold.

[0039] Specifically, first, ensure the patient's oral cavity is clean to guarantee the accuracy of the scanning results. Check the device status of the oral scanner to ensure it is operating properly, such as whether the light source is working normally and whether the sensor is sensitive. According to the size and shape of the patient's oral cavity, select a suitable scanning probe and install it on the scanner. The operator gently places the scanning probe into the patient's oral cavity, usually starting from one side of the oral cavity and using a certain fixed position of the teeth (such as the first molar) as the starting point to determine the starting position and angle of the scan. Keep an appropriate distance and angle between the scanning probe and the tooth surface, and slowly and evenly move the scanning probe along the shape of the dental arch to scan each tooth and the surrounding gingival tissue in turn. The optical sensor built into the scanning probe emits light of a specific wavelength, such as blue light or infrared light. After the light irradiates the tooth and gingival surfaces, it is reflected back. The sensor captures these reflected lights and converts them into electrical signals or digital signals, which are transmitted to the computer system in real time. The computer system converts these signals into three-dimensional point cloud data through specific algorithms and software and displays the three-dimensional model of the oral area being scanned on the computer screen in real time.

[0040] Furthermore, after the scanning is completed, the operator will conduct a comprehensive inspection of the generated three-dimensional point cloud data to check for problems such as missing data, noise interference, and incomplete models. For existing problems, manual corrections can be made using the editing tools provided by the scanning software, such as filling in missing data, removing noise points, and smoothing the model surface.

[0041] S2. Divide the three-dimensional digital dental model into multiple groups of three-dimensional digital crown models.

[0042] In the embodiments of the present invention, the division means separating each tooth (crown part) in the dental model from the overall model to form an independent three-dimensional digital crown model.

[0043] Specifically, use a segmentation algorithm to process the three-dimensional digital dental model to extract the crown area and obtain the three-dimensional digital crown model corresponding to each tooth. Considering that there may be coordinate deviations in different data sources, fix the obtained three-dimensional digital crown models to a unified reference coordinate system to ensure data consistency.

[0044] In the embodiments of the present invention, the dividing the three-dimensional digital dental model into multiple groups of three-dimensional digital crown models includes:

[0045] Extract the vertices in the three-dimensional digital dental model;

[0046] Perform curvature analysis on each of the vertices one by one to obtain the curvature of each vertex;

[0047] Compare the curvature of each of the vertices with a preset threshold one by one;

[0048] If the curvature of a vertex is less than a preset threshold, it is confirmed that the area where the vertex is located belongs to the crown area;

[0049] If the curvature of a vertex is greater than or equal to the preset threshold, it is confirmed that the area where the vertex is located does not belong to the crown area;

[0050] According to the three-dimensional digital model of the dental arch, the vertices in the crown area are segmented to obtain a three-dimensional digital model of the crown.

[0051] In the embodiments of the present invention, the extraction refers to extracting specific parts or information from the three-dimensional digital model of the dental arch. The curvature analysis refers to calculating the curvature of each vertex of the three-dimensional digital model of the dental arch to describe the degree of bending of the model surface at that vertex. The comparison refers to the process of comparing the curvature value of the vertex with the size of the threshold. The area where a certain vertex is located is classified or categorized as the crown area. The segmentation refers to separately extracting the crown part from the overall digital model of the dental arch to form an independent model file, independently representing the three-dimensional shape of the crown.

[0052] Specifically, the three-dimensional digital model of the dental arch is usually stored in a specific data format, such as common formats like STL and OBJ. In the data of these formats, the model is composed of numerous triangular patches, and each triangular patch is defined by three vertices. By using a programming language and related libraries, the three-dimensional digital model file of the dental arch is read. For each vertex, its neighboring vertices are found. Then, using the selected curvature calculation method, the curvature value of the vertex is calculated based on the coordinate information of the neighboring vertices, and the calculated curvature value is associated with the corresponding vertex.

[0053] Furthermore, all vertices and their corresponding curvature values are traversed, and the curvature value of each vertex is compared with the preset threshold. After comparing the curvature of the vertex with the preset threshold, the area where the vertex is located is classified according to the comparison result. If the curvature of the vertex is less than the threshold, it is determined that the area where the vertex is located belongs to the crown area; if the curvature of the vertex is greater than or equal to the threshold, it is determined that the area where the vertex is located does not belong to the crown area. For the convenience of subsequent processing, a mark can be added to each vertex to indicate whether the area where it is located belongs to the crown area;

[0054] Furthermore, the triangular patches formed by these crown area vertices are found (the association relationship between the triangular patches and vertices in the original three-dimensional digital model of the dental arch can be referred to), and then a three-dimensional digital model of the crown is reconstructed according to these triangular patches. Relevant three-dimensional modeling libraries can be used to complete the model reconstruction work.

[0055] In the embodiments of the present invention, the complex three-dimensional model is converted into a vertex set, which is convenient for subsequent processing, reduces unnecessary information interference. By calculating the curvature, the subtle changes on the surface of the dental model can be captured, which helps to distinguish different anatomical structures. By setting thresholds and making comparisons, the vertices can be automatically divided into different categories, providing a clear judgment criterion for determining the crown area and non-crown area in the subsequent process, reducing manual intervention, improving the degree of automation of processing. At the same time, the crown area is segmented from the entire dental model, making the data more concise and independent, facilitating storage, management and transmission between different systems or software, and improving the utilization efficiency of the data.

[0056] In the embodiments of the present invention, the dental model is divided into multiple groups of crown three-dimensional digital models, which can perform individual and detailed analysis for each tooth. At the same time, different problems of different teeth may require different treatment methods. After dividing into multiple groups of crown three-dimensional digital models, doctors can customize personalized treatment plans for patients according to the specific conditions of each tooth.

[0057] S3. Establish a global coordinate system according to the crown three-dimensional digital model, and calculate the centroid according to the global coordinate system.

[0058] In the embodiments of the present invention, the establishment refers to defining a unified reference coordinate system for the crown three-dimensional digital model, and the calculation refers to calculating the geometric center of the global coordinate system through the weighted average of vertex coordinates.

[0059] Specifically, observe the crown three-dimensional digital model, select a representative plane as the reference plane of the global coordinate system. On the selected reference plane, determine the X-axis, Y-axis, and Z-axis, and select a specific point on the reference plane as the coordinate origin. Establish the global coordinate system according to the coordinate origin, the X-axis, the Y-axis, and the Z-axis. Under the established global coordinate system, traverse all vertices of the crown three-dimensional digital model, obtain the coordinates of each vertex, and calculate the centroid according to the coordinates of the vertices.

[0060] In the embodiments of the present invention, the establishment of the global coordinate system according to the crown three-dimensional digital model includes:

[0061] Adjust the normal vector of the crown three-dimensional digital model to obtain an adjusted model;

[0062] Align the coordinates of the adjusted model to obtain an aligned model;

[0063] Perform normalization processing on the aligned model to obtain a normalized model;

[0064] Establish a global coordinate system according to the normalized model.

[0065] In the embodiments of the present invention, the normal vector adjustment refers to correcting or optimizing the normal vectors of each vertex in the three-dimensional digital model of the dental crown to ensure the direction consistency and accuracy of the normal vectors. The coordinate alignment refers to adjusting the coordinate systems of the adjusted models so that they are consistent in a certain direction or directions. The normalization process refers to standardizing the geometric data of the aligned models to meet specific ranges or conditions. The establishment refers to defining a unified and fixed three-dimensional coordinate system for the model to describe the position and direction of the model in space.

[0066] Specifically, the model is represented in the form of a triangular mesh. For each vertex, calculate the average value of the normal vectors of all triangular patches sharing this vertex as the initial normal vector of this vertex. Assume that vertex P is shared by n triangular patches, and the normal vectors of these triangular patches are respectively Then the initial normal vector of vertex P Select an external direction of the model as the reference direction, for example, the direction pointing from the center of the model to the outside. For each vertex normal vector, calculate the angle θ between it and the reference direction. If θ > 90°, then reverse the normal vector to ensure that all normal vectors generally point to the outside of the model. To make the surface rendering of the model smoother, the vertex normal vectors can be further smoothed. Traverse all vertices again. For each vertex, perform a weighted average according to the normal vectors of its adjacent vertices. After these operations, the adjusted model with adjusted normal vectors is obtained.

[0067] Furthermore, determine a standard reference coordinate system, such as the coordinate system based on anatomical structures in oral medicine, whose X-axis can be the left-right direction (positive from left to right), Y-axis is the up-down direction (positive from top to bottom), and Z-axis is the front-back direction (positive from back to front); at the same time, select some feature points in the adjusted model and the reference coordinate system respectively, such as the mesial incisal angle point of the central incisor, the cusp point of the canine, the central fossa point of the molar, etc. Establish a one-to-one correspondence between the feature points on the adjusted model and the corresponding feature points in the reference coordinate system. Use the iterative closest point (ICP) algorithm or other similar methods to calculate the transformation matrix required to align the feature points on the adjusted model with the feature points in the reference coordinate system. Apply the calculated transformation matrix T to all vertices of the adjusted model, that is, for each vertex in the adjusted model Calculate The aligned model after coordinate alignment is obtained.

[0068] Furthermore, perform a size normalization operation on the aligned model. First, calculate the bounding box of the aligned model to obtain the maximum sizes L x 、L y 、L z of the model in the X, Y, and Z axis directions. Select a target size D (for example, D = 1), and calculate the scaling factor Then, for each vertex of the alignment model perform a scaling operation to obtain

[0069] Furthermore, perform a position normalization operation on the alignment model, and calculate the centroid of the model after size normalization Subtract the centroid coordinates from each vertex of the model to obtain the normalized model.

[0070] Specifically, taking a specific direction of the normalized model as a reference to determine the axis directions of the global coordinate system, and selecting a specific point on the normalized model as the coordinate origin. The centroid of the model, a specific feature point, or other points with clear anatomical significance can be selected as the origin (0, 0, 0); through the above steps, a global coordinate system based on the normalized model is established, enabling the model to have a clear position and direction in this coordinate system, facilitating subsequent operations such as analysis, measurement, and comparison.

[0071] In the embodiments of the present invention, calculating the centroid according to the global coordinate system includes:

[0072] Determine the coordinates of the vertex according to the global coordinate system;

[0073] Calculate the coordinates of the centroid based on the coordinates of the vertex, and determine the centroid according to the coordinates of the centroid.

[0074] In the embodiments of the present invention, "determine" means converting each vertex in the model from the coordinate system of the model itself to the global coordinate system to describe the position of the vertex in the global space; "calculate" means calculating the position of the geometric center through the coordinates of all vertices in the model.

[0075] Specifically, in the global coordinate system, each vertex has a uniquely determined coordinate value. By means such as measurement or directly obtaining from the model data, the position of each vertex in this coordinate system can be determined. Usually, the vertex coordinates in three-dimensional space are represented by (x, y, z), and for two-dimensional cases, they are represented by (x, y). This is the basis for subsequent calculations and provides the necessary data for obtaining the centroid coordinates.

[0076] Furthermore, after obtaining the coordinates of all vertices, the centroid coordinates can be calculated according to the centroid calculation formula. For a discrete set of vertices, if there are n vertices with coordinates (x1, y1, z1), (x2, y2, z2),...,(x n , y n , z n ), then the calculation formula for the centroid coordinates (x c , y c , z c ) is:

[0077]

[0078] After obtaining the centroid coordinates (x c , y c , z c ), the position of the centroid in the global coordinate system is determined.

[0079] In the embodiments of the present invention, adjusting the normal vector can ensure that the normal vector of the model surface accurately points to the outside, making the surface information of the model more accurate and consistent, which is beneficial to subsequent various calculations and analyses of the model surface. At the same time, aligning the coordinates of the three-dimensional digital model of the dental crown can make the position of the model in space have consistency and comparability. Normalizing the model can adjust its size to a standard range, eliminating the influence caused by different original sizes between different models. At the same time, the global coordinate system provides a unified spatial reference framework for the entire three-dimensional digital model of the dental crown, and by calculating the centroid coordinates, a characteristic value that can summarize the overall position and distribution of the model can be obtained.

[0080] In the embodiments of the present invention, establishing the global coordinate system provides a unified spatial reference framework for all geometric elements such as points, lines, and surfaces in the three-dimensional digital model of the dental crown. By calculating the centroid, a characteristic point that can summarize the overall distribution of the model can be obtained, and this point is of great significance for describing the overall shape and position of the dental crown.

[0081] S4. Construct an initial local coordinate system based on the centroid, and perform an offset point cluster analysis on the local coordinate system to obtain an offset point cluster.

[0082] In the embodiments of the present invention, the construction refers to defining an initial local coordinate system according to the centroid and the principal axis direction, and the offset point cluster refers to the process of identifying the offset point cluster by analyzing the distance between the vertex and the centroid.

[0083] Specifically, observe the shape and position of the tooth in the global coordinate system, select a vector that is roughly parallel to the long axis direction of the tooth or a representative direction as the initial reference vector for constructing the local coordinate system, determine the direction of the coordinate axes. After determining the direction of one coordinate axis, determine the directions of the other two coordinate axes perpendicular to it through cross product operations. Subsequently, unitize the determined X-axis, Y-axis, and Z-axis direction vectors so that their modulus lengths are 1. Then, with the mass point as the origin and the unitized X-axis, Y-axis, and Z-axis vectors as the coordinate axis directions, construct an initial local coordinate system based on the centroid.

[0084] In the embodiments of the present invention, the performing an offset point cluster analysis on the local coordinate system to obtain an offset point cluster includes:

[0085] Sample the vertices of the crown region to obtain sampled vertices;

[0086] Select the projection axes in the local coordinate system, and perform offset distance analysis on each of the sampled vertices one by one according to the selected projection axes to obtain the offset distance corresponding to each sampled vertex;

[0087] Update the coordinates of each sampled vertex one by one according to the offset distance corresponding to the sampled vertex to obtain the updated coordinates of each sampled vertex;

[0088] Aggregate the updated coordinates of the sampled vertices into an offset point cluster.

[0089] In the example of the present invention, the sampling refers to selecting some vertices from all the vertices of the crown region according to a certain rule or ratio. The selection refers to choosing any two of the coordinate axes in the local coordinate system as the projection axes. The offset distance analysis refers to calculating the offset distance of each sampled vertex in the direction of the projection axis. The coordinate update refers to adjusting the coordinates of the sampled vertex according to the offset distance so that it meets specific conditions in the direction of the projection axis. The aggregation refers to gathering the coordinates of the sampled vertices after coordinate update to form an offset point cluster.

[0090] Specifically, the obtained three-dimensional digital model of the crown is fixed to a unified reference coordinate system to ensure data consistency. The origin of the local coordinate system is set based on the centroid point of the three-dimensional digital model of the crown, and a corresponding local three-dimensional coordinate system is established for the three-dimensional digital model of the crown.

[0091] In detail, under the local coordinate system, perform random sampling on the three-dimensional digital model of the crown to obtain a fixed number of point sets N. Among them, the number of the point set N can be set to 1024, 2048, or 4096, etc. according to specific application requirements to support subsequent data processing and analysis. Use the three-dimensional digital model of a single crown as the input of the convolutional neural network. In this embodiment, the digital model includes point cloud data composed of multiple vertices and their initial features. The initial features include but are not limited to the three-dimensional coordinate information of the vertices, the normal vector direction information of the points, and the curvature information, etc. The grid vertices of each three-dimensional digital model of the crown are regarded as a single vertex, and its coordinates correspond to the grid vertex coordinates of the three-dimensional digital model of the crown. We can represent these vertex sets as P = {c1, c2,..., c N} ∈ R N×3 , where N represents the number of vertices in the three-dimensional digital model of the crown, C NRepresent the three-dimensional coordinates of the vertex with index N (i.e., the grid vertex coordinates associated with the three-dimensional digital model of the dental crown). The initial features of the three-dimensional digital model cover the three-dimensional coordinates of the vertex (3D vector), point normal vector (3D vector), center coordinate normalization feature (3D vector), vertex defect feature (1D vector), and the number of faces involved in the vertex (1D vector). In other words, the initial features of each vertex consist of an 11D vector. Therefore, the initial features of the vertex set can be represented as X ∈ R N×11 .

[0092] Furthermore, to optimize the video memory occupancy, a random sampling method can be used to split the vertex set to form small sets X of equal size m ∈ R N×11 , where N represents the number of vertices, and m can take different values, such as 2048, 4096, or 8192, depending on the configuration requirements of different instances. This sampling strategy helps to efficiently manage the video memory resources during the calculation process, improve the calculation efficiency, and ensure that the neural network can process large-scale data with limited calculation resources.

[0093] Specifically, the initial features X of the vertex are used as input, and after being processed by the network, a feature matrix of size N × 128 is generated. This process can be regarded as a multi-level abstraction and high-dimensional representation of the original vertex features to enhance the feature expression ability of the point cloud data. Through this architecture, features with a hierarchical structure can be effectively extracted, thus providing more discriminative input for subsequent segmentation tasks.

[0094] Among them, the direction / distance sub-networks A / B have similar network structures, both including a convolutional layer, an instance normalization layer (Instance Normalization), a dropout layer (Dropout), and an activation function layer (Leaky ReLU). Based on the N × 128 feature matrix output by the feature extraction sub-network, the sub-networks generate output features of different sizes (size N × 1 or N × 3) respectively. Among them, the direction sub-networks A / B generate a feature matrix of size N × 3, corresponding to the prediction of the unit offset direction vector v = {v1,..., v N} ∈ R N*3 of each vertex of the single dental crown relative to the projection point on the direction axis; the distance sub-networks A / B generate a feature matrix of size N × 1, corresponding to the prediction of the offset distance d = {d1,..., d N} ∈ R N*1 of each vertex of the single dental crown relative to the projection point on the direction axis. Based on the unit offset direction vector v and the offset scale d, the offset distance △xyz = {O1,..., O N} ∈ R N*3 of each vertex of the single dental crown relative to the projection point on the direction axis can be calculated. The single-point calculation formula is as follows:

[0095] o i = d i · v i

[0096] wherein, O i represents the offset distance of the i-th vertex relative to the projection point on a certain direction axis, d i represents the offset scale of the i-th vertex relative to the projection point on a certain direction axis, v i represents the unit offset direction vector of the i-th vertex relative to the projection point on a certain direction axis.

[0097] Finally, by adding the original vertex coordinates C i to the calculated offset distance Δxyz, the set of offset vertex coordinates C = {C i |C i = c i + o i , i = 1,..., N} ∈ R N*3 can be obtained. The above calculation process realizes the dynamic offset adjustment of each vertex of the single dental crown relative to the projection point on the direction axis, thereby providing more accurate positioning information in the network and improving the accuracy of subsequent tasks.

[0098] Please refer to Figure 5 , which shows the initial distribution of the single dental arch in an exemplary embodiment. As Figure 6 shown, the initial distribution of the vertices of the single dental crown in the embodiment is given. The offset distance of each vertex of the single dental crown is calculated through a convolutional neural network and superimposed on its initial position to obtain the offset vertex coordinates. As Figure 7 shown, the offset point cluster C = {c1,..., c n} ∈ R w*3 is formed after adding the predicted distance offset amount to each vertex of the single dental crown.

[0099] In the embodiment of the present invention, the step of analyzing the offset distance of each sampled vertex one by one according to the selected projection axis to obtain the offset distance corresponding to each sampled vertex includes:

[0100] Analyzing the offset unit direction vector of each sampled vertex one by one according to the selected projection axis to obtain the offset unit direction vector of the sampled vertex;

[0101] Analyzing the offset scale of each sampled vertex one by one according to the selected projection axis to obtain the offset scale of the sampled vertex;

[0102] Performing linear programming on the offset unit direction vector and the offset scale to obtain the offset distance corresponding to each sampled vertex.

[0103] In the embodiments of the present invention, the offset unit direction vector analysis refers to analyzing each sampled vertex based on the selected projection axis to determine the offset of the unit direction vector of the vertex relative to the projection axis. The offset scale measurement analysis refers to analyzing the deviation degree of each sampled vertex relative to the projection axis in position after determining the selected projection axis, and representing this deviation situation with a quantified scale measurement. The linear programming refers to the process of operating on the offset unit direction vector and the offset scale measurement.

[0104] Specifically, due to the complex curvature changes on the surface of the dental crown, directly performing regression calculation of the offset distance is susceptible to the influence of uneven data distribution, resulting in a decrease in the accuracy of offset prediction and a relatively high difficulty in regression calculation. Therefore, the technology adopts a dual-branch prediction strategy, decomposing the offset distance calculation into two parts to improve the stability and accuracy of the calculation:

[0105] The first branch predicts the offset unit direction vector v xyz , which is used to indicate the offset direction and ensure that the offset calculation conforms to the characteristics of the tooth geometry;

[0106] The second branch predicts the offset scale (displacement) d, which is used to control the offset amplitude and avoid morphological distortion caused by excessive or too small values. The calculation formula is as follows:

[0107] Δxyz = d·v xyz

[0108] where Δxyz refers to the offset distance, d refers to the offset scale, and v xyz refers to the offset unit direction vector.

[0109] In the embodiments of the present invention, in order to optimize the offset prediction result of the single dental crown vertex, an offset direction loss function and an offset distance loss function are designed. The two are combined to jointly regulate the network training process. Specifically, the offset direction loss function L d uses the cosine similarity to measure the difference between the predicted offset direction and the true offset direction, and its definition is as follows:

[0110]

[0111] where, is the unit offset vector predicted by the network, v i is the true offset vector, and N is the total number of vertices. The loss function ensures that the predicted offset direction is as consistent as possible with the true offset direction, thereby improving the direction stability of the offset estimation.

[0112] In addition, the offset distance loss function L s uses the Euclidean distance to measure the distance error between the predicted offset point and the true offset point, and its definition is as follows:

[0113]

[0114] Among them, is the offset predicted by the network, and d i is the true offset, N is the total number of vertices. This loss function is used to optimize the position accuracy of the offset points and ensure the rationality of the offset. Finally, the total loss function L is composed of a weighted combination of the direction loss and the distance loss, that is:

[0115] L = λ d L d + λ s L s

[0116] Among them, λ d and λ s are weight coefficients used to adjust the contributions of the direction loss and the distance loss to the training process.

[0117] In summary, the present invention provides a method for calculating the single crown coordinate system based on a convolutional neural network. By constructing an offset point cluster and performing spatial straight line fitting, the local coordinate system of the crown can be effectively obtained, and the rotation matrix R can be calculated therefrom. At the same time, by combining the dual optimization strategies of the direction loss and the distance loss, the accuracy and stability of the offset prediction are improved, thereby enhancing the reliability of the crown pose estimation. Experimental results show that this method can maintain high adaptability under different crown morphologies and can be widely applied to three-dimensional reconstruction and intelligent diagnosis tasks in the field of oral medicine.

[0118] In the embodiment of the present invention, by analyzing the offset unit direction vectors of the sampled vertices, the direction of each sampled vertex relative to the selected projection axis can be clearly determined. At the same time, the offset scale analysis contains detailed feature information about the relationship between the sampled vertices and the projection axis. In addition to the distance information, the direction-related metrics also provide more dimensional features for the model, which helps to more comprehensively describe the distribution of the sampled vertices in the three-dimensional model and provides a richer basis for subsequent data analysis and processing.

[0119] In the embodiment of the present invention, analyzing the offset point cluster in the local coordinate system can focus the problem on the point cluster related to the centroid, simplify the analysis of the entire data set, and at the same time, the offset point cluster analysis can highlight the offset relative to the centroid, making the local feature differences between different point clusters more obvious.

[0120] S5. Calculate the direction unit vector according to the offset point cluster, and establish a local coordinate system according to the direction unit vector.

[0121] In the embodiments of the present invention, the calculation refers to calculating a direction vector pointing from the origin of the local coordinate system to each point in the offset point cluster, and the establishment refers to constructing a new three-dimensional coordinate system by using the unit direction vector and the origin of the local coordinate system.

[0122] Specifically, singular value decomposition is performed on the offset point cluster for three-dimensional space line fitting to calculate the unit direction vector N xyz , and this vector represents the main direction of the point cluster after the displacement of the crown model. Based on this theory, new x and new y can be calculated for the two offset point clusters output by the deep learning network. Subsequently, the third direction vector new z is calculated through cross product operation. According to new x , new y , and new z , the local coordinate system can be established.

[0123] In the embodiments of the present invention, calculating the unit direction vector according to the offset point cluster includes:

[0124] Performing singular value decomposition on the offset point cluster to obtain a decomposition result;

[0125] Selecting two groups of eigenvectors from the decomposition result and respectively using the two groups of eigenvectors as two groups of direction vectors;

[0126] Performing cross product operation on the two groups of direction vectors to obtain an operation vector;

[0127] Generating a unit direction vector according to the combination of the two groups of direction vectors and the operation vector.

[0128] In the embodiments of the present invention, the singular value decomposition refers to the process of decomposing the offset point cluster into the product of three matrices. The selection refers to selecting two specific groups of eigenvectors from the set of eigenvectors obtained from the decomposition. The cross product operation refers to the process of cross multiplying two groups of direction vectors to obtain a new group of vectors.

[0129] In the present invention, singular value decomposition is performed on the offset point cluster for three-dimensional space line fitting to calculate the unit direction vector. First, when processing the offset point cluster, the coordinate data of the point cluster is usually arranged into a matrix, and then singular value decomposition is performed on this matrix to obtain information related to the data characteristics. These information are used to determine the parameters of the line, thereby realizing line fitting. After completing the three-dimensional space line fitting, it is necessary to determine the direction of the line. The unit direction vector N xyz is the unit vector N used to represent the direction of this fitted line in three-dimensional space xyz .

[0130] Based on this theory, two clusters of offset points output by the deep learning network can be used to calculate new x and new y . Subsequently, the third direction vector new z is calculated through cross product operation. By selecting a specific point in the world coordinate system as the origin of the local coordinate system and using the unit direction vector as the direction of the axes of the local coordinate system, new x , new y , and new z can be concatenated as column vectors to form the rotation matrix R, and the local coordinate transformation is completed through matrix inversion R -1 .

[0131] Specifically, taking new x , new y , and new z as the column vectors of the matrix respectively to form a 3×3 matrix R. For example, if new x =(x1, x2, x3), new y =(y1, y2, y3), and new z =(z1, z2, z3), then the rotation matrix R is:

[0132]

[0133] The unit axis vectors of the world coordinate system are transformed through the rotation matrix R to obtain the axis direction vectors of the local coordinate system, that is, the axis direction vectors of the local coordinate system.

[0134] This rotation matrix R can be used to perform rotation operations on points in space to achieve coordinate transformation. When completing the local coordinate transformation through matrix inversion, the inverse matrix R -1 corresponding to the rotation matrix R is obtained, such that R×R -1 =I (I is the identity matrix).

[0135] At this time, for any point P in the world coordinate system, its coordinate representation P l in the local coordinate system can be obtained through rotation and translation transformations. If the inverse matrix of the rotation matrix R is R -1 , and the coordinate of the origin in the world coordinate system is O, then P l =R -1 (P - O), thus realizing the conversion from the world coordinate system to the local coordinate system and establishing the local coordinate system.

[0136] Through the above steps, the rotation matrix R is obtained. This matrix can align the local coordinate system of the dental crown with the global coordinate system. By describing the rotational transformation of the dental crown in three-dimensional space, the rotation matrix R can provide accurate spatial positioning information for subsequent three-dimensional modeling and analysis. Combining the calculation of the aforementioned offset distance, this method effectively realizes the precise positioning and attitude adjustment of each vertex of the single dental crown, thus providing an important basis for the further processing and analysis of the three-dimensional digital model of the dental arch.

[0137] In the embodiment of the present invention, a complete orthogonal coordinate system can be obtained only through one cross product, which optimizes the matrix calculation process, improves the calculation efficiency and reduces numerical instability. In addition, a dental arch constraint optimization strategy is introduced to constrain the direction vector in combination with the overall tooth arrangement information to ensure the stability of the local coordinate system calculation, making it more conform to the actual shape of the teeth, and further improving the accuracy of subsequent three-dimensional shape analysis.

[0138] In the embodiment of the present invention, the establishment of the local coordinate system makes it easier to compare different offset point clusters. By converting the data into a unified local coordinate system, the differences caused by different global coordinate system selections can be eliminated, so as to more accurately compare the characteristics and attributes of different point clusters.

[0139] It can be seen that in the above solution, for the business of constructing the local coordinate system, three-dimensional data scanning is performed on the dental arch area to obtain a three-dimensional digital model of the dental arch; the three-dimensional digital model of the dental arch is divided into multiple groups of three-dimensional digital models of dental crowns; a global coordinate system is established according to the three-dimensional digital model of the dental crown, and the centroid is calculated according to the global coordinate system; an initial local coordinate system is constructed according to the centroid, and offset point cluster analysis is performed on the local coordinate system to obtain offset point clusters; a direction unit vector is calculated according to the offset point clusters, and a local coordinate system is established according to the direction unit vector. Through automated calculation, subjective judgment and human error in manual operations are effectively avoided, thereby improving the consistency and reliability of the treatment results.

[0140] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0141] In one embodiment, a device for analyzing the local coordinate system of a three-dimensional dental arch model is provided. This device for analyzing the local coordinate system of a three-dimensional dental arch model corresponds one-to-one with the method for analyzing the local coordinate system of a three-dimensional dental arch model in the above embodiment. As Figure 3As shown in the figure, the device for analyzing the local coordinate system of a dental and maxillofacial three-dimensional model includes a scanning module 101, a dividing module 102, a establishing module 103, a calculating module 104, a constructing module 105, an analyzing module 106, a vector calculating module 107, and a local coordinate system establishing module 108. The detailed description of each functional module is as follows:

[0142] The scanning module 101 is used to perform three-dimensional data scanning on the dental and maxillofacial region to obtain a three-dimensional digital model of the dental and maxillofacial region;

[0143] The dividing module 102 is used to divide the three-dimensional digital model of the dental and maxillofacial region into multiple groups of three-dimensional digital models of dental crowns;

[0144] The establishing module 103 is used to establish a global coordinate system according to the three-dimensional digital model of the dental crown;

[0145] The calculating module 104 is used to calculate the centroid according to the global coordinate system;

[0146] The constructing module 105 is used to construct an initial local coordinate system according to the centroid;

[0147] The analyzing module 106 is used to perform an offset point cluster analysis on the local coordinate system to obtain an offset point cluster;

[0148] The vector calculating module 107 is used to calculate a direction unit vector according to the offset point cluster;

[0149] The local coordinate system establishing module 108 is used to establish a local coordinate system according to the direction unit vector.

[0150] In one embodiment, when dividing the three-dimensional digital model of the dental and maxillofacial region into multiple groups of three-dimensional digital models of dental crowns, the dividing module 102 is used to:

[0151] Extract the vertices in the three-dimensional digital model of the dental and maxillofacial region;

[0152] Perform curvature analysis on each vertex one by one to obtain the curvature of each vertex;

[0153] Compare the curvature of each vertex with a preset threshold one by one;

[0154] If the curvature of the vertex is less than the preset threshold, it is confirmed that the region where the vertex is located belongs to the dental crown region;

[0155] If the curvature of the vertex is greater than or equal to the preset threshold, it is confirmed that the region where the vertex is located does not belong to the dental crown region;

[0156] Segment the vertices in the dental crown region according to the three-dimensional digital model of the dental and maxillofacial region to obtain a three-dimensional digital model of the dental crown.

[0157] In one embodiment, when establishing the global coordinate system according to the three-dimensional digital model of the dental crown, the establishment module 103 is configured to:

[0158] Adjust the normal vector of the three-dimensional digital model of the dental crown to obtain an adjusted model;

[0159] Align the coordinates of the adjusted model to obtain an aligned model;

[0160] Normalize the aligned model to obtain a normalized model;

[0161] Establish a global coordinate system according to the normalized model.

[0162] In one embodiment, when calculating the centroid according to the global coordinate system, the calculation module 104 is configured to:

[0163] Determine the coordinates of the vertex according to the global coordinate system;

[0164] Calculate the coordinates of the centroid according to the coordinates of the vertex, and determine the centroid according to the coordinates of the centroid.

[0165] In one embodiment, when the analysis module 106 performs an offset point cluster analysis on the local coordinate system to obtain an offset point cluster, it is configured to:

[0166] Sample the vertices of the dental crown region to obtain sampled vertices;

[0167] Select the projection axis in the local coordinate system, and perform an offset distance analysis on each of the sampled vertices according to the selected projection axis to obtain the offset distance corresponding to each sampled vertex;

[0168] Update the coordinates of each sampled vertex one by one according to the offset distance corresponding to the sampled vertex to obtain the updated coordinates of each sampled vertex;

[0169] Aggregate the updated coordinates of the sampled vertices into an offset point cluster.

[0170] When performing an offset distance analysis on each of the sampled vertices according to the selected projection axis to obtain the offset distance corresponding to each sampled vertex, it is configured to:

[0171] Perform an offset unit direction vector analysis on each of the sampled vertices according to the selected projection axis to obtain the offset unit direction vector of the sampled vertex;

[0172] Perform an offset scale measurement analysis on each of the sampled vertices according to the selected projection axis to obtain the offset scale measurement of the sampled vertex;

[0173] Perform linear programming on the offset unit direction vector and the offset scale measurement to obtain the offset distance corresponding to each sampled vertex.

[0174] In one embodiment, when calculating the direction unit vector according to the offset point clusters, the vector calculation module 107 is configured to:

[0175] Perform singular value decomposition on the offset point clusters to obtain a decomposition result;

[0176] Select two sets of eigenvectors from the decomposition result, and respectively use the two sets of eigenvectors as two sets of direction vectors;

[0177] Perform a cross product operation on the two sets of direction vectors to obtain an operation vector;

[0178] Generate a direction unit vector according to the combination of the two sets of direction vectors and the operation vector.

[0179] The present invention provides an apparatus for analyzing a local coordinate system of a dental jaw three-dimensional model. For the service of constructing a local coordinate system, three-dimensional data of the dental jaw region is scanned to obtain a three-dimensional digital model of the dental jaw; the three-dimensional digital model of the dental jaw is divided into multiple groups of three-dimensional digital models of dental crowns; a global coordinate system is established according to the three-dimensional digital models of the dental crowns, and the centroid is calculated according to the global coordinate system; an initial local coordinate system is constructed according to the centroid, and an offset point cluster analysis is performed on the local coordinate system to obtain an offset point cluster; a direction unit vector is calculated according to the offset point cluster, and a local coordinate system is established according to the direction unit vector. Through automated calculation, subjective judgment and human error in manual operations are effectively avoided, thereby improving the consistency and reliability of treatment results.

[0180] For the specific limitations of an apparatus for analyzing a local coordinate system of a dental jaw three-dimensional model, reference may be made to the limitations of a method for analyzing a local coordinate system of a dental jaw three-dimensional model in the foregoing text, which will not be elaborated here. Each module in the above apparatus for analyzing a local coordinate system of a dental jaw three-dimensional model can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or stored in a memory in the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the above respective modules.

[0181] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structural diagram may be as Figure 8As shown in the figure. The computer device includes a processor, a memory, a network interface, and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the server side of a method for analyzing the local coordinate system of a dental jaw three-dimensional model.

[0182] In one embodiment, a computer device is provided. The computer device can be a client, and its internal structure diagram can be as Figure 9 As shown in the figure. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the client side of a method for analyzing the local coordinate system of a dental jaw three-dimensional model.

[0183] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented:

[0184] Perform three-dimensional data scanning on the dental jaw area to obtain a three-dimensional digital model of the dental jaw;

[0185] Divide the three-dimensional digital model of the dental jaw into multiple groups of three-dimensional digital models of dental crowns;

[0186] Establish a global coordinate system according to the three-dimensional digital model of the dental crown, and calculate the centroid according to the global coordinate system;

[0187] Construct an initial local coordinate system according to the centroid, and perform offset point cluster analysis on the local coordinate system to obtain an offset point cluster;

[0188] Calculate a direction unit vector according to the offset point cluster, and establish a local coordinate system according to the direction unit vector.

[0189] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the following steps are implemented:

[0190] Perform three-dimensional data scanning on the dental and maxillofacial region to obtain a three-dimensional digital model of the dental and maxillofacial region;

[0191] Divide the three-dimensional digital model of the dental and maxillofacial region into multiple groups of three-dimensional digital models of dental crowns;

[0192] Establish a global coordinate system based on the three-dimensional digital model of the dental crown, and calculate the centroid according to the global coordinate system;

[0193] Construct an initial local coordinate system according to the centroid, and perform offset point cluster analysis on the local coordinate system to obtain an offset point cluster;

[0194] Calculate a direction unit vector according to the offset point cluster, and establish a local coordinate system according to the direction unit vector.

[0195] It should be noted that for the functions or steps that can be realized by the above-mentioned computer-readable storage medium or computer device, reference can be made to the relevant descriptions on the server side and the client side in the foregoing method embodiments. To avoid repetition, they will not be described in detail here.

[0196] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0197] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0198] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. If non-company software tools or components appear in the application embodiments, they are only used for illustrative introduction and do not represent actual use; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for analyzing a local coordinate system of a three-dimensional tooth and jaw model, characterized in that: include: Perform three-dimensional data scanning on the dental and maxillary area to obtain a three-dimensional digital model of the dental and maxillary area; Dividing the three-dimensional digital model of the tooth jaw into a plurality of groups of three-dimensional digital models of tooth crowns; Establishing a global coordinate system according to the three-dimensional digital model of the tooth crown, and calculating the center of mass according to the global coordinate system; An initial local coordinate system is constructed according to the centroid, and an offset point cluster analysis is performed on the local coordinate system to obtain an offset point cluster; A directional unit vector is calculated according to the offset point cluster, and a local coordinate system is established according to the directional unit vector.

2. The method for analyzing the local coordinate system of the three-dimensional model of the tooth and jaw according to claim 1, characterized in that: The step of dividing the three-dimensional digital model of the tooth jaw into a plurality of groups of three-dimensional digital models of tooth crowns comprises: Extracting vertices in the three-dimensional digital model of the tooth and jaw; Performing curvature analysis on the vertices one by one to obtain the curvature of each vertex; Comparing the curvature of the vertices with a preset threshold value one by one; If the curvature of the vertex is less than a preset threshold, it is confirmed that the area where the vertex is located belongs to the crown area; If the curvature of the vertex is greater than or equal to a preset threshold, it is confirmed that the area where the vertex is located does not belong to the crown area; The vertices of the tooth crown region are segmented according to the tooth jaw three-dimensional digital model to obtain a tooth crown three-dimensional digital model.

3. The method for analyzing the local coordinate system of the three-dimensional model of the tooth and jaw according to claim 1, characterized in that: The establishing of a global coordinate system according to the three-dimensional digital model of the tooth crown comprises: Adjusting the normal vector of the three-dimensional digital model of the tooth crown to obtain an adjusted model; Performing coordinate alignment on the adjustment model to obtain an alignment model; Normalizing the alignment model to obtain a normalized model; A global coordinate system is established according to the normalized model.

4. The method for analyzing the local coordinate system of the three-dimensional model of the tooth and jaw according to claim 2, characterized in that: The calculating the center of mass according to the global coordinate system comprises: Determining the coordinates of the vertices according to the global coordinate system; The coordinates of the centroid are calculated according to the coordinates of the vertices, and the centroid is determined according to the coordinates of the centroid.

5. The method for analyzing the local coordinate system of the three-dimensional model of the tooth and jaw according to claim 2, characterized in that: The performing offset point cluster analysis on the local coordinate system to obtain an offset point cluster includes: Sampling the vertices of the crown region to obtain sampling vertices; Selecting a projection axis in the local coordinate system, and performing offset distance analysis on the sampling vertices one by one according to the selected projection axis to obtain an offset distance corresponding to each sampling vertex; The coordinates of the sampling vertices are updated one by one according to the offset distance corresponding to the sampling vertices to obtain the updated coordinates of each sampling vertex; The updated coordinates of the sampled vertices are assembled into offset point clusters.

6. The method for analyzing the local coordinate system of the three-dimensional model of the tooth and jaw according to claim 5, characterized in that: The performing offset distance analysis on the sampling vertices one by one according to the selected projection axis to obtain the offset distance corresponding to each sampling vertex includes: Performing offset unit direction vector analysis on the sampling vertices one by one according to the selected projection axis to obtain the offset unit direction vector of the sampling vertex; Performing offset scale analysis on the sampling vertices one by one according to the selected projection axis to obtain the offset scale of the sampling vertices; Linear programming is performed on the offset unit direction vector and the offset scale to obtain an offset distance corresponding to each sampling vertex.

7. The method for analyzing the local coordinate system of the three-dimensional model of the tooth and jaw according to claim 1, characterized in that: The calculating the direction unit vector according to the offset point cluster comprises: Performing singular value decomposition on the offset point cluster to obtain a decomposition result; Selecting two groups of eigenvectors from the decomposition results, and using the two groups of eigenvectors as two groups of direction vectors respectively; Performing a cross multiplication operation on the two sets of direction vectors to obtain an operation vector; A direction unit vector is generated according to the combination of the two groups of direction vectors and the operation vector.

8. A device for analyzing a local coordinate system of a three-dimensional tooth and jaw model, characterized in that: include: A scanning module is used to perform three-dimensional data scanning on the tooth and jaw area to obtain a three-dimensional digital model of the tooth and jaw; A division module, used for dividing the three-dimensional digital model of the tooth jaw into a plurality of groups of three-dimensional digital models of tooth crowns; An establishing module, used for establishing a global coordinate system according to the three-dimensional digital model of the tooth crown; A calculation module, used for calculating the center of mass according to the global coordinate system; A construction module, used for constructing an initial local coordinate system according to the centroid; An analysis module, used for performing offset point cluster analysis on the local coordinate system to obtain an offset point cluster; A vector calculation module, used for calculating a direction unit vector according to the offset point cluster; The local coordinate system establishing module is used to establish a local coordinate system according to the direction unit vector.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for analyzing the local coordinate system of the three-dimensional dental model as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for analyzing the local coordinate system of a three-dimensional dental model as claimed in any one of claims 1 to 7 are implemented.

Images