Dental model processing method, storage medium and electronic device

Abstract

Disclosed in the present disclosure are a dental model processing method, a storage medium and an electronic device. The method comprises: acquiring a dental model to be processed, wherein the dental model to be processed is a three-dimensional digital model generated on the basis of three-dimensional scanning data; performing tooth separation on the dental model to be processed, so as to obtain a dental model which has been subjected to tooth separation; trimming the dental model which has been subjected to tooth separation, so as to obtain a trimmed dental model; and adding a base to the trimmed dental model, so as to obtain a target dental model. The present disclosure solves the technical problems of a poor processing effect and a low accuracy of a dental model caused by tooth model processing methods provided in the related art performing model trimming on the basis of a gingival line recognition method.

Description

Dental model processing method, storage medium and electronic device

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on January 23, 2024, with application number 202410099324.9 and invention name “Dental model processing method, storage medium and electronic device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present disclosure relates to the technical field of digital dentures, and in particular to a dental model processing method, a storage medium, and an electronic device. Background Art

[0003] At present, in the field of digital denture technology, oral scanning technology is usually used to obtain the customer's full-jaw oral scan data, and then the whole process of restoration, base addition, marking, etc. is carried out. The processed model is exported locally or pushed to the chairside, and connected to other dental production systems, such as pre-processing tools for typesetting and slicing to obtain slice files, and finally 3D printing is performed according to the slice file to obtain the restored dental mold.

[0004] However, in the prior art, during the construction of dental casts, the gum line recognition method is usually used to scan and crop the dental model (referred to as the dental model). This cropping method is difficult to accurately identify the position and edge of each tooth, resulting in poor cropping effects and low accuracy of the dental model obtained after processing.

[0005] From the above analysis, it can be seen that the tooth model processing method provided by the above-mentioned related technologies performs model cutting based on the gum line recognition method, resulting in poor processing effect and low accuracy of the dental model. No effective solution has been proposed so far. Summary of the Invention

[0006] The embodiments of the present disclosure provide a dental model processing method, a storage medium, and an electronic device to at least solve the technical problem that the dental model processing method provided by the related art performs model cutting based on the gum line recognition method, resulting in poor processing effect and low dental model accuracy.

[0007] According to one aspect of an embodiment of the present disclosure, a method for processing a dental model is provided, comprising:

[0008] Obtain a dental model to be processed, wherein the dental model to be processed is a three-dimensional digital model generated based on three-dimensional scanning data; separate the teeth of the dental model to be processed to obtain a dental model after separation; crop the dental model after separation to obtain a cropped dental model; add a base to the cropped dental model to obtain a target dental model.

[0009] In some embodiments, before the dental model to be processed after tooth separation is separated, the above-mentioned dental model processing method also includes: calculating the normal vector and facet area of ​​any triangular facet of the dental model to be processed to obtain the normal weight of any triangular facet; calculating the total facet area of ​​multiple triangular facets and the sum of the normal weights of multiple triangular facets to obtain the total normal weight; calculating the total normal weight and the unit vector of the target transformation direction to obtain the target transformation matrix; transforming the dental model to be processed according to the target transformation matrix to obtain the straightened dental model.

[0010] In some embodiments, the dental model to be processed is segmented to obtain the segmented dental model, including: performing tooth recognition and marking on the aligned dental model based on target recognition technology to obtain a marking result, wherein the marking result is used to determine the surface area corresponding to any tooth; expanding any surface area based on the marking result to obtain multiple dental models; sorting and aligning the multiple dental models to obtain the segmented dental model, wherein the arrangement order of the multiple dental models is determined by the marking result.

[0011] In some embodiments, cropping the dental model after tooth separation to obtain the cropped dental model includes: determining a target enclosing area of ​​the tooth model in the dental model after tooth separation; performing distance detection on the triangular facets on the dental model after tooth separation according to a preset distance threshold and the target enclosing area to determine redundant triangular facets in the dental model after tooth separation, wherein the redundant triangular facets are triangular facets whose distance from the target enclosing area is greater than the preset distance threshold; removing the redundant triangular facets in the dental model after tooth separation to obtain the cropped dental model.

[0012] In some embodiments, determining the target enclosing area of ​​the tooth model in the dental model after tooth separation includes: generating a corresponding convex hull based on the joint patch area of ​​multiple adjacent tooth models in the dental model after tooth separation, wherein the joint patch area is determined by the three-dimensional grid units of multiple adjacent tooth models; and splicing multiple convex hulls to obtain the target enclosing area of ​​the dental model after tooth separation.

[0013] In some embodiments, a distance detection is performed on the triangular facets on the dental model after tooth separation according to a preset distance threshold and a target enclosing area to determine redundant triangular facets in the dental model after tooth separation, including: detecting the distance between a first edge point and a second edge point, wherein the first edge point is a lingual edge point or a labial edge point of the dental model after tooth separation, and the second edge point is a corresponding point of the first edge point on the target enclosing area; comparing the preset distance threshold with the distance to obtain a comparison result, wherein the comparison result is used to determine whether the first edge point is an edge noise point; in response to the comparison result, determining that the first edge point is an edge noise point, determining the triangular facet where the first edge point on the dental model after tooth separation is located as a redundant triangular facet.

[0014] In some embodiments, the above-mentioned dental model processing method also includes: taking the center of each dental model as the center of the sphere and the point on the dental model that is the largest distance from the center of the sphere as the radius to generate a spherical area for each dental model; combining the spherical areas of all dental models to obtain a combined spherical area, and retaining the triangular facets belonging to the combined spherical area on the dental model after tooth separation.

[0015] In some embodiments, the above-mentioned dental model processing method also includes: performing warping detection on the cropped dental model to obtain a warping detection result, wherein the warping detection result is used to determine whether the cropped dental model has warping, and the warping is a triangular facet corresponding to the raised noise point in the cropped dental model; in response to the warping detection result, it is determined that the cropped dental model has warping, and the warping in the cropped dental model is removed to obtain a first cropped model.

[0016] In some embodiments, warping detection is performed on the cropped dental model to obtain the warping detection result, including: constructing a target data structure corresponding to the cropped dental model, wherein the target data structure is used to describe the association relationship between any point, any face, and any edge in the cropped dental model; determining the edge point in the cropped dental model based on the association relationship; performing a height judgment on the patch area where any edge point is located to obtain a judgment result, wherein the judgment result is used to determine whether the patch area where any edge point is located is the highest point in the target direction; in response to the judgment result, determining that the patch area where any edge point is located is the highest point, and determining multiple triangular patches connected to any edge point in the cropped dental model as warped edges.

[0017] In some embodiments, adding a base to the cropped dental model to obtain a target dental model includes: adding a virtual base to the cropped dental model to obtain an initial base model; determining the target edge of the initial base model based on multiple triangular facets of the initial base model; constructing an initial voxel model based on the target edge; performing boundary interpolation and smoothing on the initial voxel model to obtain a target voxel model; performing intersection detection on the triangular facets in the first candidate area and the triangular facets in the second candidate area to obtain an intersection detection result, wherein the first candidate area is the candidate area in the initial base model, and the second candidate area is the candidate area in the target voxel model, and the intersection detection result is used to determine the intersection candidate facets in the second candidate area; performing region division and region marking on the target voxel model based on the intersection candidate facets to obtain a marked tooth model; and smoothing the marked tooth model to obtain a target dental model.

[0018] In some embodiments, the dental model processing method further includes: performing flash trimming on the target dental model to obtain a second trimmed model, wherein the flash trimming is used to remove closed flash and open flash in the target dental model; performing global repair on the second trimmed model to obtain a repaired target model.

[0019] In some embodiments, the dental model processing method further includes: calculating the wall thickness of any three-dimensional grid unit in the target dental model using a target projection method to obtain a calculation result; and performing regional segmentation on the target dental model according to the calculation result using a regional segmentation algorithm to obtain a closed burr.

[0020] In some embodiments, the above-mentioned dental model processing method also includes: using a ray detection method to detect any triangular facet of the target dental model to obtain a detection result, wherein the detection result is used to determine the number of intersections between the target ray and any triangular facet; in response to the number of intersections meeting a preset condition, determining that any triangular facet is an open burr.

[0021] In some embodiments, the global repair includes at least: repairing the inverted normals of the second cropped model, removing the noise shells in the second cropped model, repairing the defects in the second cropped model, repairing the self-intersecting shells of the second cropped model, merging the intersecting shells of the second cropped model, and removing the shells nested inside any shell.

[0022] According to another aspect of the present disclosure, there is provided a dental model processing device, comprising:

[0023] An acquisition module is configured to acquire a dental model to be processed, wherein the dental model to be processed is a three-dimensional digital model generated based on three-dimensional scanning data; a tooth separation module is configured to separate the teeth of the dental model to be processed to obtain a dental model after separation; a cutting module is configured to cut the dental model after separation to obtain a cut dental model; and a base adding module is configured to add a base to the cut dental model to obtain a target dental model.

[0024] In some embodiments, before the dental model to be processed after tooth separation is separated, the above-mentioned dental model processing device also includes: a calculation module, which is configured to calculate the normal vector and facet area of ​​any triangular facet of the dental model to be processed to obtain the normal weight of any triangular facet; calculate the total facet area of ​​multiple triangular facets and the sum of the normal weights of multiple triangular facets to obtain the total normal weight; calculate the total normal weight and the unit vector of the target transformation direction to obtain the target transformation matrix; transform the dental model to be processed according to the target transformation matrix to obtain the straightened dental model.

[0025] In some embodiments, the above-mentioned tooth separation module is further configured to: separate the teeth of the dental model to be processed to obtain the dental model after separation, including: performing tooth identification and marking on the straightened dental model based on target recognition technology to obtain a marking result, wherein the marking result is used to determine the surface area corresponding to any tooth; expanding any surface area based on the marking result to obtain multiple tooth models; sorting and straightening the multiple tooth models to obtain the dental model after separation, wherein the arrangement order of the multiple tooth models is determined by the marking result.

[0026] In some embodiments, the above-mentioned cropping module is further configured to: crop the dental model after tooth separation, and obtaining the cropped dental model includes: determining the target enclosing area of ​​the tooth model in the dental model after tooth separation; performing distance detection on the triangular faces on the dental model after tooth separation according to a preset distance threshold and the target enclosing area to determine the redundant triangular faces in the dental model after tooth separation, wherein the redundant triangular faces are triangular faces whose distance from the target enclosing area is greater than the preset distance threshold; removing the redundant triangular faces in the dental model after tooth separation to obtain the cropped dental model.

[0027] In some embodiments, the above-mentioned cropping module is further configured to: determine the target enclosing area of ​​the tooth model in the dental model after tooth separation, including: generating a corresponding convex hull based on the joint patch area of ​​multiple adjacent tooth models in the dental model after tooth separation, wherein the joint patch area is determined by the three-dimensional grid units of multiple adjacent tooth models; splicing multiple convex hulls to obtain the target enclosing area of ​​the dental model after tooth separation.

[0028] In some embodiments, the above-mentioned cropping module is further configured to: perform distance detection on the triangular facets on the dental model after tooth separation according to a preset distance threshold and a target enclosing area to determine redundant triangular facets in the dental model after tooth separation, including: detecting the distance between a first edge point and a second edge point, wherein the first edge point is the lingual edge point or the labial edge point of the dental model after tooth separation, and the second edge point is the corresponding point of the first edge point on the target enclosing area; comparing the preset distance threshold with the distance to obtain a comparison result, wherein the comparison result is used to determine whether the first edge point is an edge noise point; in response to the comparison result, determining that the first edge point is an edge noise point, determining the triangular facet where the first edge point on the dental model after tooth separation is located as a redundant triangular facet.

[0029] In some embodiments, the above-mentioned dental model processing device also includes: a generation module, which is configured to use the center of each dental model as the center of the sphere and the point on the dental model that is the largest distance from the center of the sphere as the radius to generate a spherical area for each dental model; the spherical areas of all dental models are combined to obtain a combined spherical area, and the triangular facets belonging to the combined spherical area on the dental model after tooth separation are retained.

[0030] In some embodiments, the above-mentioned dental model processing device also includes: a warping edge cutting module, which is configured to perform warping edge detection on the cropped dental model to obtain a warping edge detection result, wherein the warping edge detection result is used to determine whether there is warping edge in the cropped dental model, and the warping edge is a triangular facet corresponding to the raised noise point in the cropped dental model; in response to the warping edge detection result, it is determined that there is warping edge in the cropped dental model, the warping edge in the cropped dental model is removed to obtain a first cropped model.

[0031] In some embodiments, the above-mentioned warping and trimming module is further configured to: perform warping detection on the cropped dental model, and obtain the warping detection result including: constructing a target data structure corresponding to the cropped dental model, wherein the target data structure is used to describe the association relationship between any point, any face, and any edge in the cropped dental model; determining the edge point in the cropped dental model based on the association relationship; performing a height judgment on the patch area where any edge point is located to obtain a judgment result, wherein the judgment result is used to determine whether the patch area where any edge point is located is the highest point in the target direction; in response to the judgment result, determining that the patch area where any edge point is located is the highest point, and determining multiple triangular patches connected to any edge point in the cropped dental model as warped edges.

[0032] In some embodiments, the above-mentioned base adding module is further configured to: add a base to the cropped dental model to obtain a target dental model, including: adding a virtual base to the cropped dental model to obtain an initial base adding model; determining the target edge of the initial base adding model based on multiple triangular facets of the initial base adding model; constructing an initial voxel model based on the target edge; performing boundary interpolation and smoothing on the initial voxel model to obtain a target voxel model; performing intersection detection on the triangular facets in the first candidate area and the triangular facets in the second candidate area respectively to obtain an intersection detection result, wherein the first candidate area is the candidate area in the initial base adding model, and the second candidate area is the candidate area in the target voxel model, and the intersection detection result is used to determine the intersection candidate facets in the second candidate area; performing region division and region marking on the target voxel model based on the intersection candidate facets to obtain a marked tooth model; smoothing the marked tooth model to obtain a target dental model.

[0033] In some embodiments, the dental model processing device further includes: a flash trimming module configured to perform flash trimming on the target dental model to obtain a second trimmed model, wherein the flash trimming is used to remove closed flash and open flash in the target dental model; and perform global repair on the second trimming model to obtain a repaired target model.

[0034] In some embodiments, the dental model processing device further includes: a first detection module, configured to calculate the wall thickness of any three-dimensional grid unit in the target dental model using a target projection method to obtain a calculation result; and to perform regional segmentation on the target dental model according to the calculation result using a regional segmentation algorithm to obtain a closed burr.

[0035] In some embodiments, the dental model processing device further includes: a second detection module, configured to use a ray detection method to detect any triangular facet of the target dental model to obtain a detection result, wherein the detection result is used to determine the number of intersections between the target ray and any triangular facet; in response to the number of intersections meeting a preset condition, determining that any triangular facet is an open burr.

[0036] In some embodiments, the above-mentioned flash trimming module is also configured to: global repair includes at least: repairing the inverted normals of the second trimming model, removing the noise shells in the second trimming model, repairing defects in the second trimming model, repairing the self-intersecting shells of the second trimming model, merging the intersecting shells of the second trimming model, and removing the shells nested inside any shell.

[0037] According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, which includes a stored executable program, wherein when the executable program runs, the device where the computer-readable storage medium is located is controlled to execute any one of the aforementioned dental model processing methods.

[0038] According to another aspect of the embodiments of the present disclosure, an electronic device is provided, including: a memory storing an executable program; and a processor for running the executable program, wherein the executable program executes any one of the aforementioned dental model processing methods when running.

[0039] In the embodiment of the present disclosure, a dental model to be processed is first obtained, wherein the dental model to be processed is a three-dimensional digital model generated based on three-dimensional scanning data, then the teeth of the dental model to be processed are separated to obtain a dental model after separation, and then the dental model after separation is cropped to obtain a cropped dental model, and finally, a base is added to the cropped dental model to obtain a target dental model, and the purpose of accurately constructing a digital denture is achieved by sequentially separating, cropping and adding a base to the dental model to be processed, thereby realizing the technical effect of improving the cropping effect of the dental model and improving the accuracy of the target dental model by using the method of separating the teeth first and then cropping, thereby solving the technical problem that the tooth model processing method provided by the related technology is based on the gum line recognition method for model cropping, resulting in poor processing effect and low accuracy of the dental model. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of the present disclosure. The exemplary embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation of the present disclosure. In the drawings:

[0041] FIG1 is a hardware structure block diagram of a mobile terminal for an optional dental model processing method according to an embodiment of the present disclosure;

[0042] FIG2 is a flow chart of a dental model processing method according to an embodiment of the present disclosure;

[0043] FIG3 is a schematic diagram of a dental model to be processed according to an embodiment of the present disclosure;

[0044] FIG4 is a schematic diagram of a straightened dental model according to an embodiment of the present disclosure;

[0045] FIG5 is a schematic diagram of a tooth recognition result according to an embodiment of the present disclosure;

[0046] FIG6 is a schematic diagram of a tooth separation result according to an embodiment of the present disclosure;

[0047] FIG7 is a top view of a convex hull bounding box of a dental model after tooth separation according to an embodiment of the present disclosure;

[0048] FIG8 is a schematic diagram of a convex hull bounding box of a plurality of adjacent tooth models according to an embodiment of the present disclosure;

[0049] FIG9 is a schematic diagram of an overall enclosing area of ​​a first cropping model according to an embodiment of the present disclosure;

[0050] FIG10 is a schematic diagram of a joint spherical area corresponding to a tooth area in a dental model after tooth separation according to an embodiment of the present disclosure;

[0051] FIG11 is a schematic diagram of a trimmed dental model according to an embodiment of the present disclosure;

[0052] FIG12 is a schematic diagram of an initial voxel model according to an embodiment of the present disclosure;

[0053] FIG13 is a schematic diagram of a boundary interpolation process according to an embodiment of the present disclosure;

[0054] FIG14 is a schematic diagram of intersecting facets in a tooth model according to an embodiment of the present disclosure;

[0055] FIG15 is a schematic diagram of a tooth model with a base added according to an embodiment of the present disclosure;

[0056] FIG16 is a structural block diagram of a dental model processing device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0057] In order to enable those skilled in the art to better understand the solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present disclosure.

[0058] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0059] According to an embodiment of the present disclosure, a method embodiment of a dental model processing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0060] FIG1 is a block diagram of the hardware structure of a mobile terminal for an optional dental model processing method according to an embodiment of the present disclosure. As shown in FIG1 , the mobile terminal 10 (or mobile device 10) may include one or more processors 102 (the processor 102 may include, but is not limited to, a processing device such as a microcontroller unit (MCU) or a programmable logic device (FPGA)), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display device 110, an input / output device 108 (i.e., an I / O device), a universal serial bus (USB) port (which may be included as one of the ports of a computer bus, not shown in the figure), a network interface (not shown in the figure), a power supply (not shown in the figure), and / or a camera (not shown in the figure). It will be understood by those skilled in the art that the structure shown in FIG1 is merely illustrative and does not limit the structure of the mobile terminal 10 described above. For example, the mobile terminal 10 may also include more or fewer components than shown in FIG1 , or have a configuration different from that shown in FIG1 .

[0061] It should be noted that the one or more processors 102 and / or other data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuit may be a single independent processing module, or may be fully or partially integrated into any of the other components of the mobile terminal 10 (or mobile device).

[0062] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the dental model processing method in the embodiment of the present disclosure. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the above-mentioned dental model processing method. The memory 104 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the mobile terminal 10 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.

[0063] The transmission device 106 is configured to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the telecommunications provider of the mobile terminal 10. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is configured to communicate with the Internet wirelessly.

[0064] In the above operating environment, the embodiment of the present disclosure provides a dental model processing method as shown in FIG2 . FIG2 is a flow chart of a dental model processing method according to an embodiment of the present disclosure. As shown in FIG2 , the method includes the following implementation steps:

[0065] Step S201, obtaining a dental model to be processed, wherein the dental model to be processed is a three-dimensional digital model generated based on three-dimensional scanning data;

[0066] Step S202, dividing the dental model to be processed to obtain a divided dental model;

[0067] Step S203, cutting the dental model after tooth separation to obtain a cut dental model;

[0068] Step S204: adding a base to the cropped dental model to obtain a target dental model.

[0069] The dental model can be a three-dimensional digital model obtained by processing and converting three-dimensional scan data. The three-dimensional scan data can include, but is not limited to, the following information or data: the shape and position of teeth, the size and proportions of teeth, the shape and position of gums, the color and texture of teeth, the overall structure and morphology of the oral cavity, and information about oral soft tissues (e.g., the position and morphology of the tongue). For example, the three-dimensional scan data can be obtained by scanning the user's oral cavity with a three-dimensional scanning device, or by scanning a dental impression model. This disclosure does not limit the method of data acquisition.

[0070] The tooth separation operation can be used to determine the position of each tooth in the target oral cavity, as well as the relative position and order of all teeth in the dental model to be processed. The cropping operation can be used to remove unnecessary parts (e.g., warped edges) other than necessary parts such as teeth and gums based on the information of each tooth obtained from the tooth separation operation, to facilitate the subsequent construction of a denture that matches the tooth structure in the target oral cavity. The base addition operation is used to add a base to the cropped dental model to facilitate 3D printing of the target dental model obtained after base addition.

[0071] In the embodiment of the present disclosure, a dental model to be processed is first obtained, wherein the dental model to be processed is a three-dimensional digital model generated based on three-dimensional scanning data, then the teeth of the dental model to be processed are separated to obtain a dental model after separation, and then the dental model after separation is cropped to obtain a cropped dental model, and finally, a base is added to the cropped dental model to obtain a target dental model, and the purpose of accurately constructing a digital denture is achieved by sequentially separating, cropping and adding a base to the dental model to be processed, thereby realizing the technical effect of improving the cropping effect of the dental model and improving the accuracy of the target dental model by using the method of separating the teeth first and then cropping, thereby solving the technical problem that the tooth model processing method provided by the related technology is based on the gum line recognition method for model cropping, resulting in poor processing effect and low accuracy of the dental model.

[0072] The above method of the embodiment of the present disclosure is further introduced below.

[0073] In an optional embodiment, before separating the teeth of the dental model to be processed, the dental model processing method further includes:

[0074] Step S251, calculating the normal vector and the area of ​​any triangular facet of the dental model to be processed to obtain the normal weight of any triangular facet;

[0075] Step S252, calculating the total area of ​​the plurality of triangular facets and the sum of the normal weights of the plurality of triangular facets to obtain a total normal weight;

[0076] Step S253, calculating the total normal weight and the unit vector of the target transformation direction to obtain a target transformation matrix;

[0077] Step S254: transform the dental model to be processed according to the target transformation matrix to obtain a straightened dental model.

[0078] In the technical solution provided by the present disclosure, since the direction of the imported dental model to be processed is uncertain, it is necessary to fix the placement posture of the dental model to be processed. Therefore, the tooth surface of the dental model to be processed (the bold part of the line as shown in Figure 3) can be turned up based on the normal vector of the dental model to be processed. The specific method can be: the normal vector of the i-th triangle of the dental model to be processed is recorded as normal i (x i ,y i ,z i ), the patch area is recorded as area i , calculate the product of the normal vector of the i-th triangle and the area of ​​the patch to get the normal weight of the i-th triangle (denoted as w i ) can be expressed as the following formula (1): i =normali ×area i Formula (1)

[0079] Next, the total number of facets of the dental model to be processed is recorded as N, and the sum of the normal weights of all triangular facets of the dental model to be processed is calculated as Total area of ​​the patch The total normal weight W (as shown by the arrow in FIG3 ) is calculated as shown in the following formula (2):

[0080] In some embodiments, assuming that the target transformation type is rotation, the target transformation direction is the z direction, and the unit vector in the z direction is (0, 0, 1), the total normal weight and the unit vector are calculated to obtain the target rotation matrix, and then the dental model to be processed is rotated according to the target rotation matrix to obtain the rotated dental model as shown in Figure 4, in which the tooth surface of the rotated dental model faces upward.

[0081] In an optional embodiment, in step S202, the dental model to be processed is divided into teeth to obtain the divided dental model, which includes:

[0082] Step S221 , performing tooth recognition and marking on the straightened dental model based on target recognition technology to obtain a marking result, wherein the marking result is used to determine the surface area corresponding to any tooth;

[0083] Step S222: expanding any patch region based on the labeling result to obtain multiple tooth models;

[0084] Step S223 , sorting and aligning the multiple tooth models to obtain a dental model after tooth separation, wherein the arrangement order of the multiple tooth models is determined by the marking result.

[0085] The target recognition technology mentioned above may include, but is not limited to, computer vision technology, deep learning technology, and machine learning technology. In the technical solution provided herein, the marking result after tooth recognition and marking using the target recognition technology may be as shown in FIG5 , where a rectangular frame is used to mark the surface area of ​​each tooth in the straightened dental model.

[0086] After teeth are identified and marked, the results are projected onto the aligned dental model. Rays are used to filter the bottom points of the model, and the remaining top points are expanded. During the expansion process, a curvature value of -0.5 can be set as the end condition. Furthermore, the expansion area of ​​the model can be limited using mask expansion or border expansion. It should also be noted that to prevent teeth from expanding into the gums, areas outside the teeth can be marked in advance.

[0087] After the tooth expansion is completed, the teeth are sorted. The specific method can be: first, the center of a single tooth model is projected into two dimensions, and the center point of the single tooth model is calculated. Multiple vectors are constructed with the center point of each tooth model as the starting point and the center point as the focus to obtain a vector set. Then, any vector is used as the starting vector, and the vector closest to the vector is searched in a counterclockwise direction, and the angle between any two vectors closest to the vector is calculated. In some embodiments, the two vectors with the largest angle in the calculation result are used as the two endpoints, and the midpoint of the two endpoints is calculated. Each tooth model is sorted with the midpoint to the center point of each tooth model as a reference, and then the sorted expanded tooth model is subjected to overlapping area judgment and elimination processing. Finally, based on the recognition result, a grid area of ​​each tooth is generated to obtain the tooth separation result, and then all teeth are spliced ​​and rearranged in order to obtain the dental model after tooth separation as shown in Figure 6.

[0088] It should be noted that the dental model after tooth separation can be horizontally adjusted. Specifically: first obtain the oriented bounding box (OBB) of the dental model after tooth separation, and combine the normal of the model triangle facets and the direction of the maximum face of the oriented bounding box to generate the corresponding alignment direction so that the maximum face of the oriented bounding box is aligned with the target axis (such as the z-axis).

[0089] In an optional embodiment, in step S203, the dental model after separation is trimmed to obtain the trimmed dental model, including:

[0090] Step S231, determining a target enclosing area of ​​the tooth model in the dental model after tooth separation;

[0091] Step S232: performing distance detection on the triangular facets on the dental model after tooth separation according to a preset distance threshold and the target enclosing area to determine redundant triangular facets in the dental model after tooth separation, wherein the redundant triangular facets are triangular facets whose distance from the target enclosing area is greater than the preset distance threshold;

[0092] Step S233 , removing the redundant triangular facets in the dental model after tooth separation to obtain the trimmed dental model.

[0093] Wherein, in step S231, determining the target enclosing area of ​​the tooth model in the dental model after tooth separation includes:

[0094] Step S2311, generating a corresponding convex hull according to a joint patch area of ​​a plurality of adjacent tooth models in the dental model after tooth separation, wherein the joint patch area is determined by three-dimensional grid cells of the plurality of adjacent tooth models;

[0095] Step S2312: splicing multiple convex hulls to obtain a target enclosing area of ​​the dental model after tooth separation.

[0096] And, in step S232, distance detection is performed on the triangular facets on the dental model after tooth separation according to a preset distance threshold and the target enclosing area to determine redundant triangular facets in the dental model after tooth separation, including:

[0097] Step S2321: Detecting the distance between a first edge point and a second edge point, wherein the first edge point is a lingual edge point or a labial edge point of the dental model after tooth separation, and the second edge point is a corresponding point of the first edge point on the target enclosed area; comparing the preset distance threshold with the distance to obtain a comparison result, wherein the comparison result is used to determine whether the first edge point is an edge noise point;

[0098] Step S2322: In response to the comparison result, determining that the first edge point is the edge noise point, determining the triangular facet where the first edge point is located on the post-teeth separation dental model as the redundant triangular facet.

[0099] In the technical solution provided by the present invention, a convex hull bounding box can be generated based on the grid area of ​​all teeth obtained after tooth separation, and a top view of the convex hull bounding box can be obtained. As shown in Figure 7, the arched part with thickened lines is the lingual area, the points on the edge of the arched part are the lingual edge points, the irregular part around the arched part is the labial area, and the points on the edge of the irregular part are the labial edge points.

[0100] In some embodiments, based on the grid area of ​​each tooth in the dental model after tooth separation, the grid areas of multiple adjacent teeth are spliced ​​together, and the corresponding convex hull bounding box is generated according to the spliced ​​grid area (as shown in Figure 8), and then multiple different convex hull bounding boxes are spliced ​​together in sequence to obtain the target enclosing area of ​​all tooth models in the dental model after tooth separation (as shown in Figure 9). In some embodiments, a data structure of the point set on the overall enclosing area is constructed. It should be noted here that the data structure can be a Kd tree (K-dimensional tree), and the points on the overall enclosing area can be quickly searched based on the Kd tree.

[0101] In some embodiments, the distance between any lingual edge point or any labial edge point in the dental model after tooth separation and the corresponding point (or mapping point) on the target enclosing area is detected. When the distance is greater than a preset distance threshold, the lingual edge point or labial edge point corresponding to the distance is determined to be a noise point (or redundant point) in the dental model after tooth separation. Then, the triangular facet where the lingual edge point or labial edge point in the dental model after tooth separation is located (i.e., the redundant triangular facet) is removed to obtain the cropped dental model.

[0102] In an optional embodiment, the dental model processing method further includes:

[0103] Step S261, using the center of gravity of each tooth model as the center of the sphere and the point on the tooth model that is the largest distance from the center of the sphere as the radius, to generate a spherical area for each tooth model;

[0104] Step S262: The spherical regions of all tooth models are united to obtain a united spherical region, and the triangular facets belonging to the united spherical region on the dental model after tooth separation are retained.

[0105] In the technical solution provided by the present disclosure, in order to avoid incomplete tooth recognition during identification marking, which may lead to erroneous cutting of triangular facets in the tooth area during the cutting process, before performing the above-mentioned cutting, the center of gravity of each tooth model in the dental model after tooth separation is used as the center of the sphere, and the point on the tooth model that is at the maximum distance from the center of the sphere is used as the radius to generate a spherical area for each tooth model, and then the spherical areas of all tooth models are combined to obtain a combined spherical area as shown in Figure 10, and then the triangular facets belonging to the combined spherical area on the dental model after tooth separation are retained.

[0106] In an optional embodiment, the dental model processing method further includes:

[0107] Step S271: performing warping detection on the cropped dental model to obtain a warping detection result, wherein the warping detection result is used to determine whether the cropped dental model has warping edges, and the warping edges are triangular facets corresponding to raised noise points in the cropped dental model;

[0108] Step S272 : In response to the warping detection result, it is determined that the trimmed dental model has the warping edge, and the warping edge in the trimmed dental model is removed to obtain a first trimmed model.

[0109] In step S271, warping detection is performed on the cropped dental model to obtain a warping detection result, including:

[0110] Step S2711, constructing a target data structure corresponding to the cropped dental model, wherein the target data structure is used to describe the association relationship between any point, any surface, and any edge in the cropped dental model;

[0111] Step S2712, determining edge points in the cropped dental model according to the association relationship;

[0112] Step S2713, performing a height judgment on the patch area where any edge point is located to obtain a judgment result, wherein the judgment result is used to determine whether the patch area where the any edge point is located is the highest point in the target direction;

[0113] Step S2713: In response to the judgment result, the facet region where the arbitrary edge point is located is determined as the highest point, and a plurality of triangular facets connected to the arbitrary edge point in the cropped dental model are determined as the warped edges.

[0114] The above-mentioned target data structure can be a half-edge data structure. Based on the constructed target data structure corresponding to the cropped dental model, the edges of all triangular facets on the cropped dental model are traversed. When a certain edge belongs to a triangular facet, the edge is confirmed to be an edge edge of the cropped dental model and the point on the edge edge is an edge point. In some embodiments, it is determined whether the triangular facet area where each edge point is located belongs to the highest point of the cropped dental model in the target direction (such as the z direction). When this condition is met, the edge point is determined to be a point on the warped edge, and all triangular facets on the cropped dental model that are connected to the points on the warped edge are removed to obtain the first cropped model (as shown in FIG11 ).

[0115] In an optional embodiment, in step S204, adding a base to the cropped dental model to obtain a target dental model includes:

[0116] Step S241, adding a base to the cut dental model to obtain a tooth model after adding a base;

[0117] Step S242, performing flash trimming on the tooth model after the base is added to obtain a third trimmed model, wherein the flash trimming is used to remove the flash in the tooth model after the base is added;

[0118] Step S243: Perform global repair on the third cropped model to obtain a target dental model.

[0119] In step S241, a base is added to the cut dental model to obtain the tooth model after the base is added, which includes:

[0120] Step S2411, adding a virtual base to the cropped dental model to obtain an initial base-added model;

[0121] Step S2412, determining the target edge of the initial base model based on the multiple triangular facets of the initial base model;

[0122] Step S2413, constructing an initial voxel model based on the target edge;

[0123] Step S2414, performing boundary interpolation and smoothing processing on the initial voxel model to obtain a target voxel model;

[0124] Step S2415: performing intersection detection on the triangular facets in the first candidate region and the triangular facets in the second candidate region to obtain an intersection detection result, wherein the first candidate region is the candidate region in the initial base model, and the second candidate region is the candidate region in the target voxel model. The intersection detection result is used to determine the intersecting candidate facets in the second candidate region;

[0125] Step S2416, performing region division and region labeling on the target voxel model based on the intersecting candidate facets to obtain a labeled tooth model;

[0126] Step S2416: Smoothing the marked tooth model to obtain a target dental model.

[0127] It is easy to understand that the cropped dental model does not have a bottom facet. Therefore, the cropped dental model cannot be used directly for 3D printing. The cropped dental model needs to be processed with a bottom. The specific method can be: construct multiple virtual triangular facets at the bottom of the cropped dental model based on the bounding box, then find the maximum outer edge of the mesh of the original cropped dental model (i.e., the target edge), and combine the constructed virtual triangular facets to construct a closed loop at the maximum outer edge boundary to obtain the size of the voxel generation space (virtual bottom), then merge the original cropped dental model with the virtual bottom, and calculate the size and other parameters of the layered depth normal image (LDNI) based on the bounding volume of the model mesh, and then generate the boundary interpolation points of the image according to the image resolution and edge points, and then fill the internal area of ​​the boundary to obtain the initial voxel model (as shown in Figure 12).

[0128] In some embodiments, based on the mesh boundary surface of the original cropped dental model, the corresponding boundary surface at the boundary of the initial voxel model is removed. Then, according to the boundary points of the initial voxel model after removing the boundary surface, the outermost circle boundary of the voxel model is found, and the boundary interpolation is performed on the outermost circle boundary according to the side length and resolution of the outermost circle boundary (as shown in Figure 13). The voxels after boundary interpolation are then converted into a grid, and the converted grid model is preliminarily smoothed as a whole to obtain the target voxel model.

[0129] In some embodiments, intersection detection is performed on the triangular facets on the target voxel model. Specifically: for the original cropped dental model, the boundary surface of the candidate area grid is expanded inward a preset number of times (for example, 15 times). For the target voxel model, the bottom surface area is removed based on the height filtering method, and the middle filling area is removed based on the edge filtering method. Then, a specific data structure of the remaining area of ​​the target voxel model is established. The specific data structure can be a Kd tree structure based on the surface area heuristic (SAH). The edges of the original cropped dental model are used as rays. When the collision length of the ray is less than or equal to the edge length in the Kd tree structure based on SAH, the two models are considered to intersect. Then, the grid points are marked according to the relationship between the grid and the points on the voxel model, and the corresponding points on the voxel model are searched based on the unknown points on the grid to obtain the intersecting facets (as shown in Figure 14).

[0130] After determining the intersecting facets, the original cropped dental model and the target voxel model are divided and marked based on the intersecting facets. The specific method can be: mark the surface outside the candidate area of ​​the original cropped dental model as the external area, and mark the intersecting area based on the face normal and edge direction of the intersecting facets; mark the bottom area of ​​the target voxel model as the external area, mark the upper plane of the middle area as the internal area, and mark the intersecting area based on the face normal and edge direction of the intersecting facets to obtain the marked dental model. In some embodiments, the sides and bottom of the marked dental model are smoothed, and the bottom facet can be simplified to obtain the target dental model, as shown in Figure 15. The diagonal filled part is the bottom area, and the original cropped dental model is above the bottom area.

[0131] In an optional embodiment, the dental model processing method further includes:

[0132] Step S281, performing flash trimming on the target dental model to obtain a second trimmed model, wherein the flash trimming is used to remove closed flash and open flash in the target dental model;

[0133] Step S282: Perform global repair on the second cropped model to obtain a repaired target model.

[0134] As an optional implementation, in order to further improve the accuracy of the printed dental model, the target dental model obtained after adding the base can be subjected to fringe trimming and global repair processing. Before fringe trimming, the target dental model needs to be subjected to fringe detection. The fringe detection process is shown in the following steps S2811 to S2814.

[0135] In an optional embodiment, the dental model processing method further includes:

[0136] Step S2811, calculating the wall thickness of any three-dimensional grid cell in the target dental model using a target projection method to obtain a calculation result;

[0137] Step S2812: Using a region segmentation algorithm, the target dental model is segmented according to the calculation result to obtain closed burrs.

[0138] Since the target dental model is prone to flash with small wall thickness and sudden wall thickness changes, while the wall thickness of the normal tooth model is greater than the flash wall thickness and the wall thickness changes evenly, the flash belongs to the noise area of ​​the target dental model and needs to be detected and removed. The specific method can be: for closed flash, the wall thickness of the target dental model can be calculated using point projection, ray projection and other methods, and then the watershed algorithm can be used to perform regional segmentation on the target dental model according to the wall thickness calculation results to segment out the closed flash, and then the closed flash can be removed from the target dental model.

[0139] In an optional embodiment, the dental model processing method further includes:

[0140] Step S2813, using a ray detection method to detect any triangular facet of the target dental model to obtain a detection result, wherein the detection result is used to determine the number of intersections between the target ray and any triangular facet;

[0141] Step S2814: In response to the number of intersection points satisfying a preset condition, determining that any triangle facet is an open burr.

[0142] For open burrs, since their wall thickness detection is inaccurate or cannot be detected, the wall thickness of the open burr can be pre-set as a target value (for example: 0.1mm). Then, for any triangular facet, take the center point of the triangle, offset it in the opposite direction of the face normal by a preset distance, and emit rays with the offset point as the starting point and the opposite direction of the face normal as the direction. Calculate the number of intersections between the ray and the target dental model. When the number of intersections is an even number, determine that the triangular facet is an open burr, and thus remove the open burr from the target dental model.

[0143] In an optional embodiment, in step S282, the global repair includes at least: repairing the inverted normal of the second cropping model, removing the noise shell in the second cropping model, repairing the defects in the second cropping model, repairing the self-intersecting shells of the second cropping model, merging the intersecting shells of the second cropping model, and removing the shells nested inside any shell.

[0144] Defects in the second cut model can be small shells, holes, and other parts within the model. By performing a global repair on the second cut model after removing closed and open fins, model errors are significantly reduced, which in turn helps improve the fit of the denture built based on the model and the target user's mouth, enhancing the user experience.

[0145] The dental model processing method provided in the above embodiment of the present disclosure first constructs an initial dental model based on the scanned oral data, and then performs processing operations such as alignment, tooth separation, preliminary cropping (referring to the aforementioned removal of redundant triangular facets in the dental model after tooth separation), edge trimming, bottoming, flash trimming, and global restoration on the initial dental model, achieving the following technical effects:

[0146] (1) During the tooth separation process, the position of each tooth in the dental model is identified and marked based on artificial intelligence methods such as computer vision. This method determines the tooth position with high accuracy, making the tooth position in the dental model more accurate after tooth separation;

[0147] (2) The dental model after tooth separation was subjected to multiple fine-tuning operations, including preliminary cutting and edge cutting, to remove edge noise and edge warping on the model, further improving the accuracy of the model;

[0148] (3) During the model base addition process, the adaptability of the base addition area to the original tooth model is improved by constructing the corresponding voxel model, boundary processing, intersection detection, region marking, boundary interpolation, smoothing and other processing operations, and the error of the intersection between the base addition area and the original tooth model is reduced, which helps to generate accurate dentures and improve the user's dental diagnosis and treatment experience;

[0149] (4) The target dental model obtained after adding the base is subjected to flash cutting and global repair operations. In the flash cutting process, both closed flash and open flash are effectively detected and cut, and various flashes in the model are effectively removed. The global repair operation repairs various defects of the second cutting model obtained by flash cutting, thereby further improving the accuracy of the printed denture.

[0150] In this embodiment, a dental model processing device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments. Details already described will not be repeated here. As used below, a "module" refers to a combination of software and / or hardware that can implement a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0151] FIG16 is a structural block diagram of a dental model processing device according to an embodiment of the present disclosure. As shown in FIG16 , the device includes:

[0152] An acquisition module 1601 is configured to acquire a dental model to be processed, wherein the dental model to be processed is a three-dimensional digital model generated based on three-dimensional scanning data;

[0153] The teeth separation module 1602 is configured to separate the teeth of the dental model to be processed to obtain a dental model after separation;

[0154] A cutting module 1603 is configured to cut the dental model after tooth separation to obtain a cut dental model;

[0155] The base adding module 1604 is configured to add a base to the cropped dental model to obtain a target dental model.

[0156] In some embodiments, before the dental model to be processed after tooth separation is separated, the above-mentioned dental model processing device also includes: a calculation module 1605 (not shown in the figure), which is configured to calculate the normal vector and facet area of ​​any triangular facet of the dental model to be processed to obtain the normal weight of any triangular facet; calculate the total facet area of ​​multiple triangular facets and the sum of the normal weights of multiple triangular facets to obtain the total normal weight; calculate the total normal weight and the unit vector of the target transformation direction to obtain the target transformation matrix; transform the dental model to be processed according to the target transformation matrix to obtain the straightened dental model.

[0157] In some embodiments, the above-mentioned tooth separation module 1602 is also configured to: separate the teeth of the dental model to be processed to obtain the dental model after separation, including: performing tooth recognition and marking on the straightened dental model based on target recognition technology to obtain a marking result, wherein the marking result is used to determine the surface area corresponding to any tooth; expanding any surface area based on the marking result to obtain multiple tooth models; sorting and straightening the multiple tooth models to obtain the dental model after separation, wherein the arrangement order of the multiple tooth models is determined by the marking result.

[0158] In some embodiments, the above-mentioned cropping module 1603 is also configured to: crop the dental model after tooth separation, and the cropped dental model obtained includes: determining the target enclosing area of ​​the tooth model in the dental model after tooth separation; performing distance detection on the triangular faces on the dental model after tooth separation according to the preset distance threshold and the target enclosing area to determine the redundant triangular faces in the dental model after tooth separation, wherein the redundant triangular faces are triangular faces whose distance from the target enclosing area is greater than the preset distance threshold; removing the redundant triangular faces in the dental model after tooth separation to obtain the cropped dental model.

[0159] In some embodiments, the above-mentioned cropping module 1603 is also configured to: determine the target enclosing area of ​​the tooth model in the dental model after tooth separation, including: generating a corresponding convex hull based on the joint patch area of ​​multiple adjacent tooth models in the dental model after tooth separation, wherein the joint patch area is determined by the three-dimensional grid units of multiple adjacent tooth models; splicing multiple convex hulls to obtain the target enclosing area of ​​the dental model after tooth separation.

[0160] In some embodiments, the above-mentioned cropping module 1603 is also configured to: perform distance detection on the triangular facets on the dental model after tooth separation according to a preset distance threshold and a target enclosing area to determine redundant triangular facets in the dental model after tooth separation, including: detecting the distance between a first edge point and a second edge point, wherein the first edge point is the lingual edge point or the labial edge point of the dental model after tooth separation, and the second edge point is the corresponding point of the first edge point on the target enclosing area; comparing the preset distance threshold with the distance to obtain a comparison result, wherein the comparison result is used to determine whether the first edge point is an edge noise point; in response to the comparison result, determining that the first edge point is an edge noise point, determining the triangular facet where the first edge point on the dental model after tooth separation is located as a redundant triangular facet.

[0161] In some embodiments, the above-mentioned dental model processing device also includes: a generation module 1606 (not shown in the figure), which is configured to use the center of each dental model as the center of the sphere and the point on the dental model that is the largest distance from the center of the sphere as the radius to generate a spherical area for each dental model; the spherical areas of all dental models are combined to obtain a combined spherical area, and the triangular facets belonging to the combined spherical area on the dental model after tooth separation are retained.

[0162] In some embodiments, the above-mentioned dental model processing device also includes: a warping edge cutting module 1607 (not shown in the figure), which is configured to perform warping edge detection on the cropped dental model to obtain a warping edge detection result, wherein the warping edge detection result is used to determine whether there is warping edge in the cropped dental model, and the warping edge is a triangular facet corresponding to the raised noise point in the cropped dental model; in response to the warping edge detection result, it is determined that there is warping edge in the cropped dental model, the warping edge in the cropped dental model is removed to obtain a first cropped model.

[0163] In some embodiments, the above-mentioned warping and trimming module 1607 is also configured to: perform warping detection on the cropped dental model, and obtain the warping detection result including: constructing a target data structure corresponding to the cropped dental model, wherein the target data structure is used to describe the association relationship between any point, any face, and any edge in the cropped dental model; determining the edge point in the cropped dental model based on the association relationship; performing a height judgment on the patch area where any edge point is located to obtain a judgment result, wherein the judgment result is used to determine whether the patch area where any edge point is located is the highest point in the target direction; in response to the judgment result, determining that the patch area where any edge point is located is the highest point, and determining multiple triangular patches connected to any edge point in the cropped dental model as warped edges.

[0164] In some embodiments, the above-mentioned base adding module 1604 is also configured to: add a base to the cropped dental model to obtain a target dental model, including: adding a virtual base to the cropped dental model to obtain an initial base adding model; determining the target edge of the initial base adding model based on multiple triangular facets of the initial base adding model; constructing an initial voxel model based on the target edge; performing boundary interpolation and smoothing on the initial voxel model to obtain a target voxel model; performing intersection detection on the triangular facets in the first candidate area and the triangular facets in the second candidate area respectively to obtain an intersection detection result, wherein the first candidate area is the candidate area in the initial base adding model, and the second candidate area is the candidate area in the target voxel model, and the intersection detection result is used to determine the intersection candidate facets in the second candidate area; performing region division and region marking on the target voxel model based on the intersection candidate facets to obtain a marked tooth model; smoothing the marked tooth model to obtain a target dental model.

[0165] In some embodiments, the above-mentioned dental model processing device also includes: a flash cutting module 1608 (not shown in the figure), which is configured to perform flash cutting on the target dental model to obtain a second cutting model, wherein the flash cutting is used to remove closed flash and open flash in the target dental model; and perform global repair on the second cutting model to obtain a repaired target model.

[0166] In some embodiments, the above-mentioned dental model processing device also includes: a first detection module 1609 (not shown in the figure), which is configured to use the target projection method to calculate the wall thickness of any three-dimensional grid unit in the target dental model to obtain a calculation result; and use the region segmentation algorithm to perform region segmentation on the target dental model according to the calculation result to obtain a closed flash.

[0167] In some embodiments, the above-mentioned dental model processing device also includes: a second detection module 1610 (not shown in the figure), which is configured to use a ray detection method to detect any triangular facet of the target dental model to obtain a detection result, wherein the detection result is used to determine the number of intersections between the target ray and any triangular facet; in response to the number of intersections meeting a preset condition, any triangular facet is determined to be an open burr.

[0168] In some embodiments, the above-mentioned flash trimming module 1608 is also configured to: global repair includes at least: repairing the inverted normal of the second trimming model, removing the noise shell in the second trimming model, repairing the defects in the second trimming model, repairing the self-intersecting shell of the second trimming model, merging the intersecting shells of the second trimming model, and removing the shells nested inside any shell.

[0169] It should be noted that the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0170] According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, which includes a stored executable program, wherein when the executable program runs, the device where the computer-readable storage medium is located is controlled to execute any one of the aforementioned dental model processing methods.

[0171] In some embodiments, in this embodiment, the above-mentioned storage medium may be configured to store a computer program for performing the following steps:

[0172] Step S1, obtaining a dental model to be processed, wherein the dental model to be processed is a three-dimensional digital model generated based on three-dimensional scanning data;

[0173] Step S2, dividing the dental model to be processed to obtain a divided dental model;

[0174] Step S3, cutting the dental model after tooth separation to obtain a cut dental model;

[0175] Step S4: adding a base to the cropped dental model to obtain a target dental model.

[0176] In some embodiments, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0177] According to another aspect of the embodiments of the present disclosure, an electronic device is provided, including: a memory storing an executable program; and a processor for running the executable program, wherein the executable program executes any one of the aforementioned dental model processing methods when running.

[0178] In some embodiments, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0179] Step S1, obtaining a dental model to be processed, wherein the dental model to be processed is a three-dimensional digital model generated based on three-dimensional scanning data;

[0180] Step S2, dividing the dental model to be processed to obtain a divided dental model;

[0181] Step S3, cutting the dental model after tooth separation to obtain a cut dental model;

[0182] Step S4: adding a base to the cropped dental model to obtain a target dental model.

[0183] In some embodiments, specific examples in this embodiment can refer to the examples described in the above embodiment and its optional implementation manners, and this embodiment will not be repeated here.

[0184] The serial numbers of the above-mentioned embodiments of the present disclosure are for description only and do not represent the advantages or disadvantages of the embodiments.

[0185] In the above embodiments of the present disclosure, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0186] In the several embodiments provided in the present disclosure, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0187] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0188] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0189] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0190] The above is only a preferred embodiment of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present disclosure. These improvements and modifications should also be regarded as within the scope of protection of the present disclosure. Industrial Applicability

[0191] The present disclosure relates to the technical field of digital dentures. In an embodiment of the present application, a method is adopted to obtain a dental model to be processed, wherein the dental model to be processed is a three-dimensional digitized model generated based on three-dimensional scanning data. Then, the dental model to be processed is divided into teeth to obtain a dental model after division, and then the dental model after division is cropped to obtain a cropped dental model. Finally, a base is added to the cropped dental model to obtain a target dental model. By sequentially dividing, cropping and adding a base to the dental model to be processed, the purpose of accurately constructing a digital denture is achieved, thereby realizing the technical effect of improving the cropping effect of the dental model and improving the accuracy of the target dental model by using the method of dividing the teeth first and then cropping, thereby solving the technical problem that the tooth model processing method provided by the related technology performs model cropping based on the gum line recognition method, resulting in poor processing effect and low accuracy of the dental model.

Claims

1. A method for processing a dental model, comprising: Obtaining a dental model to be processed, wherein the dental model to be processed is a three-dimensional digital model generated based on three-dimensional scan data; Splitting the dental model to be processed to obtain a split dental model; Trimming the split dental model to obtain a trimmed dental model; Adding a base to the trimmed dental model to obtain a target dental model.

2. The dental model processing method according to claim 1, wherein, Before splitting the dental model to be processed, the method further comprises: Calculating the normal vector and the surface area of any triangular facet of the dental model to be processed to obtain the normal weight of any triangular facet; Calculating the total surface area of multiple triangular facets and the sum of the normal weights of the multiple triangular facets to obtain the total normal weight; Calculating the total normal weight and the unit vector of the target transformation direction to obtain a target transformation matrix; Transforming the dental model to be processed according to the target transformation matrix to obtain an aligned dental model.

3. The dental model processing method according to claim 2, wherein, Splitting the dental model to be processed to obtain the split dental model includes: Identifying and marking teeth on the aligned dental model based on target recognition technology to obtain a marking result, wherein the marking result is used to determine the facet region corresponding to any tooth; Expanding any facet region based on the marking result to obtain multiple tooth models; Sorting and aligning the multiple tooth models to obtain a split dental model, wherein the arrangement order of the multiple tooth models is determined by the marking result.

4. The dental model processing method according to claim 1, wherein, Trimming the split dental model to obtain the trimmed dental model includes: Determining the target bounding region of the tooth models in the split dental model; Performing distance detection on the triangular facets on the split dental model according to a preset distance threshold and the target bounding region to determine the redundant triangular facets in the split dental model, wherein the redundant triangular facets are triangular facets whose distance from the target bounding region is greater than the preset distance threshold; Removing the redundant triangular facets in the split dental model to obtain the trimmed dental model.

5. The dental model processing method according to claim 4, wherein, Determining the target bounding region of the tooth models in the split dental model includes: Generating a corresponding convex hull according to the combined facet region of multiple adjacent tooth models in the split dental model, wherein the combined facet region is determined by the three-dimensional grid cells of the multiple adjacent tooth models; Stitching multiple convex hulls to obtain the target bounding region of the split dental model.

6. The dental model processing method according to claim 4, wherein, Performing distance detection on the triangular facets on the split dental model according to the preset distance threshold and the target bounding region to determine the redundant triangular facets in the split dental model, includes: Detect the distance between the first edge point and the second edge point, where the first edge point is the lingual or labial edge point of the dental model after tooth separation, and the second edge point is the corresponding point of the first edge point on the target enclosing area; compare the size of the preset distance threshold and the distance to obtain a comparison result, where the comparison result is used to determine whether the first edge point is an edge noise point; In response to the comparison result determining that the first edge point is the edge noise point, determine the triangular patch where the first edge point is located on the dental model after tooth separation as the redundant triangular patch.

7. The dental model processing method according to claim 4, wherein, The method further includes: Taking the centroid of each tooth model as the center of the sphere and the point with the maximum distance from the center of the sphere on the tooth model as the radius, generate the spherical area of each tooth model; Combine the spherical areas of all tooth models to obtain a combined spherical area, and retain the triangular patches on the dental model after tooth separation that belong to the combined spherical area.

8. The dental model processing method according to claim 4, wherein, The method further includes: Perform warping detection on the trimmed dental model to obtain a warping detection result, where the warping detection result is used to determine whether there is warping in the trimmed dental model, and the warping is the triangular patch corresponding to the raised noise point in the trimmed dental model; In response to the warping detection result determining that the trimmed dental model has the warping, remove the warping in the trimmed dental model to obtain a first trimmed model.

9. The dental model processing method according to claim 8, wherein, Performing warping detection on the trimmed dental model to obtain the warping detection result includes: Construct a target data structure corresponding to the trimmed dental model, where the target data structure is used to describe the association relationship between any point, any face, and any edge in the trimmed dental model; Determine the edge points in the trimmed dental model according to the association relationship; Perform height judgment on the patch area where any edge point is located to obtain a judgment result, where the judgment result is used to determine whether the patch area where any edge point is located is the highest point in the target direction; In response to the judgment result determining that the patch area where any edge point is located is the highest point, determine the multiple triangular patches connected to the any edge point in the trimmed dental model as the warping.

10. The dental model processing method according to claim 1, wherein, Adding a bottom to the trimmed dental model to obtain the target dental model includes: Add a virtual bottom to the trimmed dental model to obtain an initial bottom-added model; Determine the target edge of the initial bottom-added model according to the multiple triangular patches of the initial bottom-added model; Construct an initial voxel model according to the target edge; Perform boundary interpolation and smoothing processing on the initial voxel model to obtain a target voxel model; Perform intersection detection on the triangular patches in the first candidate area and the triangular patches in the second candidate area respectively to obtain an intersection detection result, where the first candidate area is the candidate area in the initial bottom-added model, the second candidate area is the candidate area in the target voxel model, and the intersection detection result is used to determine the intersecting candidate patches in the second candidate area; Based on the intersecting candidate patches, perform region division and region marking on the target voxel model to obtain the marked tooth model; Perform smoothing processing on the marked tooth model to obtain the target dental model.

11. The dental model processing method according to claim 10, wherein, The method further includes: Perform flash trimming on the target dental model to obtain a second trimmed model, where the flash trimming is used to remove the closed flash and open flash in the target dental model; Perform global repair on the second trimmed model to obtain the repaired target model.

12. The dental model processing method according to claim 11, wherein, The method further includes: Use the target projection method to calculate the wall thickness of any three-dimensional grid cell in the target dental model to obtain the calculation result; Use the region segmentation algorithm to perform region segmentation on the target dental model according to the calculation result to obtain the closed flash.

13. The dental model processing method according to claim 11, wherein, The method further includes: Use the ray detection method to detect any triangular patch of the target dental model to obtain the detection result, where the detection result is used to determine the number of intersection points between the target ray and the any triangular patch; In response to the number of intersection points satisfying a preset condition, determine the any triangular patch as the open flash.

14. The dental model processing method according to claim 11, wherein, The global repair at least includes: repairing the reversed normal of the second trimmed model, removing the noise shell in the second trimmed model, repairing the defects in the second trimmed model, repairing the self-intersecting shell of the second trimmed model, merging the intersecting shells of the second trimmed model, and removing the shell nested inside any shell.

15. A computer-readable storage medium, the computer-readable storage medium comprising a stored executable program, wherein, When the executable program runs, control the device where the computer-readable storage medium is located to execute the dental model processing method according to any one of claims 1 to 14.

16. An electronic device, comprising: A memory storing an executable program; A processor for running the executable program, where when the executable program runs, it executes the dental model processing method according to any one of claims 1 to 14.

Images