Recognition method and device of maxillofacial scanning rod and storage medium
By obtaining the occlusal model in dentistry, and automatically identifying the maxillofacial scanning rod using the target direction and density clustering algorithm, the time-consuming and labor-intensive problem of traditional manual separation is solved, and the recognition efficiency and accuracy are improved.
Patent Information
- Application Number
- CN202411124578.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-16
- Publication Date
- 2024-12-27
AI Technical Summary
In dental restoration, the separation of the maxillofacial scanning rod and gingival tissue in traditional methods requires manual operation, which is time-consuming and labor-intensive and prone to errors, affecting the accurate positioning of the implant and the final repair effect.
By obtaining the user's occlusal model, determining the target direction, cropping according to the seed points in the mesh model, filtering target grid objects that meet preset conditions to automatically identify the maxillofacial scanning rod, and improving using density clustering algorithm and normal vector analysis Identification efficiency.
It realizes automatic identification of the maxillofacial scanning rod, shortens data separation and analysis time, reduces the tedious process of manual operation, and improves identification efficiency and accuracy.
Smart Images
Figure CN119205625A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the technical field of dental restoration, and in particular to a method, device and storage medium for identifying a maxillofacial scanning rod. Background Art
[0002] In modern dental restoration, dental implant technology has become one of the main means to solve the problem of missing teeth. When a tooth is damaged and falls out, the dentist will remove the bone under the damaged tooth and then plant an implant at the bottom to replace the missing tooth. The successful implantation of the implant and the accuracy of subsequent tooth restoration directly affect the patient's chewing function and oral health.
[0003] In order to ensure the accurate positioning of the implant, dentists usually use a scanning rod to obtain the position, angle and depth information of the implant. This scanning rod is generally inserted into the implant, and the image data obtained by scanning can help dentists determine the specific situation of the implant. However, in related technologies, the separation between the scanning rod and the gum tissue is still a thorny problem. Traditional scanning data processing methods mainly rely on manual separation, which is not only time-consuming and labor-intensive, but also prone to errors, affecting the final implant effect. Summary of the invention
[0004] One purpose of the embodiments of the present application is to provide a method, device and storage medium for identifying a maxillofacial scanning rod, so as to solve the technical problem in the related art that manual separation of the maxillofacial scanning rod is time-consuming, labor-intensive and prone to errors.
[0005] In a first aspect, an embodiment of the present application provides a method for identifying a maxillofacial scanning rod, comprising:
[0006] Acquire an occlusion model of the user, where the occlusion model is a grid model;
[0007] Based on the occlusion model, determining a target direction;
[0008] Determining a seed point in the grid model according to the target direction;
[0009] According to the seed point, cutting is performed in the mesh model to determine a target mesh object;
[0010] Determine whether the target mesh object meets a preset condition to determine whether the target mesh object is a maxillofacial scanning rod.
[0011] In combination with the first aspect, in a feasible embodiment, the target direction includes at least one of an occlusal direction, a buccal direction and a central direction. The occlusal direction is the movement direction of the upper and lower jaws when they occlude each other in the occlusal model, the buccal direction is the direction close to the cheek in the occlusal model, and the central direction is the central axis direction of the maxillary face in the occlusal model.
[0012] In combination with the first aspect, in a feasible implementation manner, determining a seed point in the grid model according to the target direction includes:
[0013] According to the target direction, traverse the mesh model in order to extract each vertex in the mesh model;
[0014] Screening among the vertices according to preset conditions to determine the target point, wherein the preset conditions include at least one of: the Gaussian curvature of the current vertex, the angle between the normal vector of the current vertex and the normal vector of a preset plane, the angle between the normal vector of the current vertex and the normal vector of a neighboring vertex, and whether the reverse normal ray of the current vertex intersects with the grid;
[0015] Based on the target point, the seed point is determined.
[0016] In combination with the first aspect, in a feasible implementation manner, determining the seed point based on the target point includes:
[0017] Determining whether the number of the target points is less than a preset first threshold;
[0018] If yes, the target point is expanded by a density clustering algorithm;
[0019] Determine the projection height of each target point, and sort the target points according to the projection height to obtain a target point set;
[0020] A clipping and screening process is performed on the target point set to determine the seed point.
[0021] In combination with the first aspect, in a feasible implementation manner, the expanding the target point by using a density clustering algorithm includes:
[0022] Through radius query, determine the neighborhood points of each target point and judge whether it is a core object;
[0023] If so, for each core object, find the density-reaching point and expand the cluster;
[0024] All found clusters are sorted according to size, and the target point is expanded according to the sorting result.
[0025] In combination with the first aspect, in a feasible implementation manner, performing clipping and screening processing in the target point set to determine the seed point includes:
[0026] Determine target points in the target point set as core points in sequence, and cut the core points according to a preset scanning radius to obtain a target grid;
[0027] If the depth of the target grid is within a preset second threshold, determining the core point as the seed point to obtain a seed point set;
[0028] The seed point set is rescreened to remove seed points whose spacing is less than a preset second threshold in the seed point set.
[0029] In combination with the first aspect, in a feasible implementation manner, the step of performing clipping in the mesh model according to the seed point to determine the target mesh object includes:
[0030] Determine the normal vector of each seed point to obtain a normal vector set of the seed points;
[0031] According to a preset radius, traverse the neighborhood vertices of each of the seed points;
[0032] The mesh model is clipped according to the normal vector set and the neighborhood vertices to obtain the target mesh object.
[0033] In combination with the first aspect, in a feasible implementation manner, determining whether the target mesh object meets a preset condition to judge whether the target mesh object is a maxillofacial scanning rod includes:
[0034] Filtering target vertices with upward normals and positive curvature in the target mesh object;
[0035] A cross section is made at a middle position in the target mesh object, wherein the vertex normal of the cross section point points to the outside of the mesh model;
[0036] Dividing the grid model into a preset number of quadrants, each of the quadrants including the target vertex, and determining an average radius of the quadrants;
[0037] The average radius is compared with a preset radius to determine whether the target mesh object is the maxillofacial scanning rod.
[0038] In a second aspect, an embodiment of the present application provides an electronic device, comprising a memory and a processor, wherein the memory is connected to the processor, and the processor is used to execute one or more computer programs stored in the memory. When the processor executes the one or more computer programs, the electronic device implements a method as described in any one of the first aspects above.
[0039] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes any of the methods described above.
[0040] The embodiments of the present application can achieve the following technical effects:
[0041] Based on the method proposed in the embodiment of the present application, when identifying the maxillofacial scanning rod, the user's occlusion model is first obtained, and the occlusion model is a grid model; and based on the occlusion model, the target direction is determined; according to the target direction, the seed point is determined in the grid model; according to the seed point, the grid model is cropped to determine the target grid object; and finally, it is determined whether the target grid object meets the preset conditions to determine whether the target grid object is a maxillofacial scanning rod. Through the above steps, the method performs multiple scanning and cropping processes in the three-dimensional grid model, thereby extracting the target grid object that meets the preset conditions as a maxillofacial scanning rod. The fully automated processing flow greatly shortens the time for data separation and analysis, reduces the tedious process of manual operation, and improves the recognition efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0043] Figure 1 A schematic diagram of a flow chart of a maxillofacial scanning rod recognition method provided in an embodiment of the present application;
[0044] Figure 2 It is a structural schematic diagram of a maxillofacial scanning rod recognition device provided in an embodiment of the present application;
[0045] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0046] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.
[0047] It should be noted that, if there is no conflict, the various features in the embodiments of the present application can be combined with each other, all within the scope of protection of the present application. In addition, although the functional module division is performed in the device schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a sequence different from the module division in the device or the flow chart. Furthermore, the words "first", "second", "third", etc. used in this application do not limit the data and execution order, but only distinguish the same items or similar items with basically the same functions and effects.
[0048] In the first place, see Figure 1 The present application embodiment provides a method for identifying a maxillofacial scanning rod, the method comprising:
[0049] Step S11, obtaining the user's occlusion model, wherein the occlusion model is a grid model;
[0050] It should be noted that the occlusal model referred to in this embodiment is a three-dimensional mesh model established through medical imaging and digital technology to indicate the relationship between teeth and jaws. The model can be obtained by various intraoral scanning devices and organized through three-dimensional modeling software.
[0051] As a feasible implementation method, intraoral scanning equipment or cone beam computed tomography (CBCT) technology can be used to scan the user's oral cavity to obtain the original image data of the user's upper and lower jaws. After obtaining the original image data, professional 3D processing software can be used to identify the maxillofacial scanning rod and generate a mesh model. For example, CAD and other software can be used. During the reconstruction process, the software will use algorithms to analyze and splice images at different levels to finally form a complete 3D mesh model.
[0052] Step S12, determining a target direction based on the occlusion model;
[0053] In this embodiment, the target direction includes at least one of the occlusal direction, the buccal direction and the central direction. The occlusal direction is the movement direction of the upper and lower jaws when they occlude with each other in the occlusal model. The buccal direction is the direction close to the cheek in the occlusal model. The central direction is the central axis direction of the maxillary face in the occlusal model.
[0054] It is easy to understand that by analyzing and calculating the geometric features of the maxillofacial mesh model (this embodiment does not limit the specific calculation process), the above-mentioned occlusal direction, buccal direction and center direction can be obtained, ensuring that in subsequent processing steps, more accurate selection and cropping operations can be performed based on these directions, effectively guiding the subsequent seed point screening, region selection and mesh cropping processes, thereby improving the accuracy and efficiency of the entire processing flow.
[0055] Step S13, determining a seed point in the grid model according to the target direction;
[0056] Specifically, in this embodiment, the mesh model is traversed in sequence according to the target direction to extract each vertex in the mesh model; according to preset conditions, screening is performed among the vertices to determine the target point, and the preset conditions include: at least one of: the Gaussian curvature of the current vertex, the angle between the normal vector of the current vertex and the normal vector of a preset plane, the angle between the normal vector of the current vertex and the normal vector of the neighboring vertex, and whether the reverse normal ray of the current vertex intersects with the mesh; based on the target point, the seed point is determined.
[0057] The mesh model is screened to determine the target point, which is a vertex in the mesh model that meets the requirements. The specific screening process includes: checking whether the vertex has been visited; checking whether the Gaussian curvature of the vertex is less than 0; checking whether the angle between the vertex normal vector and the given plane normal vector is less than 90 degrees; checking whether the angle between the normal vector of the neighboring vertex and the normal vector of the current vertex is greater than 45 degrees; checking whether the reverse normal ray of the vertex intersects the mesh, until all vertices are checked and the target point that meets the requirements is screened out.
[0058] Furthermore, in the above embodiment, based on the target point, the seed point is determined, including: determining whether the number of the target points is less than a preset first threshold; if so, expanding the target points through a density clustering algorithm; determining the projection height of each target point, and sorting each target point according to the projection height to obtain a target point set; and performing cropping and screening processing in the target point set to determine the seed point.
[0059] It is easy to understand that if the initial number of target points is insufficient, it needs to be expanded through a density clustering algorithm to improve accuracy and avoid omissions.
[0060] Furthermore, the target point is expanded through a density clustering algorithm, including: determining the neighborhood points of each target point through radius query, and judging whether it is a core object; if so, for each core object, finding the density direct point and expanding the cluster; sorting all the found clusters according to size, and expanding the target point according to the sorting result.
[0061] More specifically, a clipping and screening process is performed in the target point set to determine the seed point, including: sequentially determining the target points in the target point set as core points, clipping the core points by a preset scanning radius to obtain a target grid; if the depth of the target grid is within a preset second threshold, determining the core point as the seed point to obtain a seed point set; and performing a re-screening on the seed point set to remove seed points in the seed point set whose spacing is less than the preset second threshold.
[0062] Specifically, during complex screening, each seed point is used as the core and clipped using a regular scanning radius. If the clipped mesh depth is between 0.8 and 2.0, it is considered as a seed point candidate.
[0063] In addition, if the distance between the seed points is too close or the two seed points are at different heights on the same scanning rod, one of the seed points (can be any one of the two seed points) is removed and the other is retained.
[0064] Step S14, cutting out the mesh model according to the seed point to determine the target mesh object;
[0065] Specifically, in this embodiment, the step of clipping in the mesh model includes: determining the normal vector of each seed point to obtain a normal vector set of the seed point; traversing the neighborhood vertices of each seed point according to a preset radius; and clipping the mesh model according to the normal vector set and the neighborhood vertices to obtain the target mesh object.
[0066] More specifically, in this embodiment, a series of operations are performed on each seed point to identify and process the specific area corresponding to each seed point, including:
[0067] 1. Initialization:
[0068] Create a vector list topNorList that stores the normal direction; for each seed point seed, perform the subsequent steps in sequence.
[0069] 2. Clear the selection state of the initial mesh; traverse all vertices in the mesh and clear their access flags (ClearV); call SelectFilter::clearSelect to clear the selection state.
[0070] 3. Breadth-first search (BFS): Create a queue selectP, add the seed point seed to the queue and mark it as visited and selected (SetV, SetS); use BFS to traverse the vertices around the seed point, select vertices within the specified radius queryRadius_, and mark them as visited and selected.
[0071] 4. Select faces: Call SelectFilter::selectFacesFromVertices to select the corresponding faces from the selected vertices.
[0072] 5. Create a new mesh object per_mesh: Copy the selected vertices and faces to the new mesh object per_mesh, and create a vertex attribute isSeed to mark the seed point.
[0073] 6. Detect and process boundaries: Use the FillHole object to detect holes in the mesh and find the hole with the largest radius; calculate the boundary center boundaryCenter and the mesh center meshCenter, and determine the center direction center_dir.
[0074] 7. Region growing: Starting from the seed point, the vertices of the top region are selected through BFS, and the top vertex (topPts) is selected according to the normal angle and position conditions.
[0075] 8. Calculate the top center and normal: If the top vertex set is empty, calculate the top center topCenter and normal topNor by projection; if the top vertex set is not empty, calculate topCenter and topNor by accumulating the position and normal of the top vertex, and visualize the top center and normal (if the node node_ exists).
[0076] 9. Store the normal direction: store the calculated normal direction topNor in the list topNorList.
[0077] 10. Second Breadth First Search (BFS): Clear the selection state of the grid; starting from the seed point, select vertices within the specified distance and normal angle range through BFS, and mark them as visited and selected.
[0078] 11. Create a second new mesh object per_mesh2: Copy the selected vertices and faces to the new mesh object per_mesh2, and create a vertex attribute isSeed to mark the seed point.
[0079] 12. Traverse and clip boundaries from the boundary: Use the FillHole object to detect holes in the mesh and find the bottom-most boundary; select the bottom-most boundary vertex based on the calculated height.
[0080] 13. Region growing and vertex deletion: Starting from the boundary vertices, select eligible vertices through BFS and add these vertices to the deletion list; delete these vertices from the mesh and compress and clean the mesh.
[0081] 14. Save the results: Add the processed mesh object per_mesh2 to the result mesh list resultMeshList.
[0082] Step S15, determining whether the target mesh object meets a preset condition to determine whether the target mesh object is a maxillofacial scanning rod.
[0083] In this embodiment, each target mesh object is further checked to determine whether it is a maxillofacial scanning rod, specifically including:
[0084] Target vertices with upward normals and positive curvature are selected from the target mesh object; a cross section is made at the middle position of the target mesh object, with the vertex normals of the cross section points pointing to the outside of the mesh model; the mesh model is divided into a preset number of quadrants, each of which includes the target vertex, and an average radius of the quadrant is determined; the average radius is compared with a preset radius to determine whether the target mesh object is the maxillofacial scanning rod.
[0085] The value of the preset radius can be set according to the maxillofacial scanning rod to be separated.
[0086] It should be noted that, in each of the above-mentioned embodiments, there is not necessarily a certain order between the above-mentioned steps. A person skilled in the art can understand, based on the description of the embodiments of the present application, that in different embodiments, the above-mentioned steps may have different execution orders, that is, they may be executed in parallel, may be executed interchangeably, and so on.
[0087] As another aspect of the embodiment of the present application, the embodiment of the present application provides a maxillofacial scanning rod recognition device. The maxillofacial scanning rod recognition device can be a software module, which includes several instructions stored in a memory, and the processor can access the memory and call the instructions for execution to complete the maxillofacial scanning rod recognition method described in the above embodiments.
[0088] In some embodiments, the maxillofacial scanning rod recognition device can also be constructed by hardware devices. For example, the maxillofacial scanning rod recognition device can be constructed by one or more chips, and each chip can work in coordination with each other to complete the maxillofacial scanning rod recognition method described in each of the above embodiments. For another example, the maxillofacial scanning rod recognition device can also be constructed by various logic devices, such as a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, or any combination of these components.
[0089] See also Figure 2 This embodiment provides a maxillofacial scanning rod recognition device 200, comprising:
[0090] A data acquisition module 210 is used to acquire an occlusion model of the user, wherein the occlusion model is a grid model;
[0091] A first processing module 220, for determining a target direction based on the occlusion model;
[0092] A second processing module 230 is used to determine a seed point in the grid model according to the target direction;
[0093] A third processing module 240 is used to perform clipping in the mesh model according to the seed point to determine a target mesh object;
[0094] The fourth processing module 250 is used to determine whether the target mesh object meets a preset condition, so as to determine whether the target mesh object is a maxillofacial scanning rod.
[0095] It should be noted that the above-mentioned maxillofacial scanning rod recognition device can execute the maxillofacial scanning rod recognition method provided in the embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not fully described in the embodiment of the maxillofacial scanning rod recognition device, please refer to the maxillofacial scanning rod recognition method provided in the embodiment of the present application.
[0096] See also Figure 3 , Figure 3 1 is a schematic diagram of the structure of an electronic device 300 provided in an embodiment of the present application, wherein the electronic device 300 is a processing device in the above-mentioned maxillofacial scanning rod recognition system. The electronic device 300 includes one or more processors 31 and a memory 32. The memory 32 is connected to the one or more processors 31, for example, connected to the processor 31 via a bus.
[0097] The processor 31 is configured to support the electronic device 300 to perform the corresponding functions in the method in the above method embodiment. The processor 31 can be a central processing unit (CPU), a network processor (NP), a hardware chip or any combination thereof. The above hardware chip can be an application specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The above PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.
[0098] The memory 32 is used to store program codes, etc. The memory may include a volatile memory (VM), such as a random access memory (RAM); the memory may also include a non-volatile memory (NVM), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); the memory 32 may also include a combination of the above-mentioned types of memory.
[0099] The memory 32 can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the maxillofacial scanning rod recognition method in the embodiment of the present application. The processor 31 executes various functional applications and data processing of the maxillofacial scanning rod recognition method and the maxillofacial scanning rod recognition device by running the non-volatile software programs, instructions and modules stored in the memory 32, that is, realizes the functions of each module or unit of the maxillofacial scanning rod recognition method and the maxillofacial scanning rod recognition device provided in the above method embodiment.
[0100] The memory 32 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function. The data storage area may store data created according to the use of the maxillofacial scanning rod recognition device, etc. In some embodiments, the memory 32 may optionally include a memory remotely arranged relative to the processor 31, and these remote memories may be connected to the maxillofacial scanning rod recognition device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0101] One or more modules are stored in the memory 32. When executed by one or more processors 31, the maxillofacial scanning rod recognition method in any of the above method embodiments is executed, for example, the method steps described in the above method embodiments are executed to realize the functions of the modules described in the above device embodiments.
[0102] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. The computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the method of the aforementioned embodiment.
[0103] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.
[0104] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.
Claims
1. A method for identifying a maxillofacial scanning rod, characterized in that: The method comprises: Acquire an occlusion model of the user, where the occlusion model is a grid model; Based on the occlusion model, determining a target direction; Determining a seed point in the grid model according to the target direction; According to the seed point, cutting is performed in the mesh model to determine a target mesh object; Determine whether the target mesh object meets a preset condition to determine whether the target mesh object is a maxillofacial scanning rod.
2. The method according to claim 1, characterized in that The target direction includes at least one of an occlusal direction, a buccal direction and a central direction. The occlusal direction is the direction of movement of the upper and lower jaws when they occlude with each other in the occlusal model. The buccal direction is the direction close to the cheek in the occlusal model. The central direction is the direction of the central axis of the maxillary face in the occlusal model.
3. The method according to claim 1, characterized in that Determining a seed point in the grid model according to the target direction includes: According to the target direction, traverse the mesh model in order to extract each vertex in the mesh model; Screening among the vertices according to preset conditions to determine the target point, wherein the preset conditions include at least one of: the Gaussian curvature of the current vertex, the angle between the normal vector of the current vertex and the normal vector of a preset plane, the angle between the normal vector of the current vertex and the normal vector of a neighboring vertex, and whether the reverse normal ray of the current vertex intersects with the grid; Based on the target point, the seed point is determined.
4. The method according to claim 3, characterized in that: The step of determining the seed point based on the target point includes: Determining whether the number of the target points is less than a preset first threshold; If yes, the target point is expanded by a density clustering algorithm; Determine the projection height of each target point, and sort the target points according to the projection height to obtain a target point set; A clipping and screening process is performed on the target point set to determine the seed point.
5. The method according to claim 4, characterized in that The step of expanding the target point by using a density clustering algorithm includes: Through radius query, determine the neighborhood points of each target point and judge whether it is a core object; If so, for each core object, find the density-reaching point and expand the cluster; All found clusters are sorted according to size, and the target point is expanded according to the sorting result.
6. The method according to claim 4, characterized in that The clipping and screening process is performed in the target point set to determine the seed point, including: Determine target points in the target point set as core points in sequence, and cut the core points according to a preset scanning radius to obtain a target grid; If the depth of the target grid is within a preset second threshold, determining the core point as the seed point to obtain a seed point set; The seed point set is rescreened to remove seed points whose spacing is less than a preset second threshold in the seed point set.
7. The method according to claim 1, characterized in that The step of clipping the mesh model according to the seed point to determine the target mesh object includes: Determine the normal vector of each seed point to obtain a normal vector set of the seed points; According to a preset radius, traverse the neighborhood vertices of each of the seed points; The mesh model is clipped according to the normal vector set and the neighborhood vertices to obtain the target mesh object.
8. The method according to claim 1, characterized in that The step of determining whether the target mesh object meets a preset condition to judge whether the target mesh object is a maxillofacial scanning rod comprises: Filtering target vertices with upward normals and positive curvature in the target mesh object; A cross section is made at a middle position in the target mesh object, wherein the vertex normal of the cross section point points to the outside of the mesh model; Dividing the grid model into a preset number of quadrants, each of the quadrants including the target vertex, and determining an average radius of the quadrants; The average radius is compared with a preset radius to determine whether the target mesh object is the maxillofacial scanning rod.
9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory is connected to the processor, and the processor is used to execute one or more computer programs stored in the memory, and when the processor executes the one or more computer programs, the electronic device implements the method according to any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 8.