Image data processing method for determining binding surface, electronic equipment and storage medium

Abstract

The invention belongs to the field of image processing, and particularly relates to an image data processing method for determining a binding surface, electronic equipment and a storage medium. The method provided by the invention comprises the following steps: acquiring a first path of an operation record selection operation of a user on a first image at a first angle; obtaining a second path of the operation record selection operation of the user on the second image at the second angle; selecting a first tooth plane sequence based on the first path; selecting a second tooth plane sequence based on the second path; updating a first tooth plane list according to the first tooth plane sequence and the second tooth plane sequence; determining the total area of the user operation area based on the connectivity of the tooth planes in the first tooth plane list; and generating or updating a first target contour on the user operation image based on the first tooth plane list. The method provided by the invention can assist a physician in accurately selecting an expected structure so as to obtain a better fitting surface.

Description

Technical Field

[0001] This invention belongs to the field of image processing, and specifically relates to an image data processing method, electronic device, and storage medium for determining the bonding surface based on a user-drawn interface. Background Technology

[0002] Digital dental treatment solutions (such as implants, orthodontics, and prosthodontics) rely on the precise definition of specific tooth surfaces. The design of a crown, veneer, or orthodontic appliance must fit snugly on the selected tooth plane. The precision of this selection directly determines whether the subsequently designed restoration or appliance can fit the target area and directly affects the final outcome.

[0003] Currently, digital structures of teeth can be obtained via CT scans, and teeth can be segmented and their boundaries extracted using 3Shape, 3D Slicer, and software plugins, ultimately forming a partial mesh model of the tooth. While open-source communities offer software plugins and platforms for data processing, these models only provide basic geometric structures and cannot intuitively reflect the details and functional areas of the tooth surface. Doctors still need to repeatedly adjust their perspective and selection areas. Therefore, the processed tooth data requires further intelligent processing to help doctors more accurately identify and select target veneer surfaces.

[0004] However, currently, there is still a lack of effective tools for quickly and accurately selecting the tooth plane to obtain the mating surface when it comes to selecting and displaying the mating surface. Tools that can provide such selection functionality are a much-needed technical solution in this field. Summary of the Invention

[0005] The technical solution and beneficial effects of the present invention will be further described in the following description, and can be obtained through the implementation of the present invention. According to one embodiment of the present invention, an image data processing method for determining the bonding surface includes:

[0006] Obtain the first path of the user's operation record on the first image from the first angle;

[0007] Obtain the second path of the user's operation record on the second image from the second angle;

[0008] The first tooth plane sequence is selected based on the first path;

[0009] The second tooth plane sequence is selected based on the second path;

[0010] Update the first tooth plane list based on the first tooth plane sequence and the second tooth plane sequence;

[0011] The total area of ​​the user operation area is determined based on the connectivity of the tooth planes within the first tooth plane list.

[0012] Generate or update the first target contour on the user-operated image based on the first tooth plane list;

[0013] The first or second image is obtained by projection of a tooth spatial model, and the first and second images at least contain image regions formed by partially consistent projections of the tooth plane.

[0014] According to one embodiment of the present invention, the image of user operation is generated based on the following method:

[0015] The model obtained from the toothed plate transformation is converted into the world coordinate system to obtain the first model information;

[0016] Get the user's current first-person perspective;

[0017] Apply the translation, rotation, and scaling matrices corresponding to the first viewpoint to the first model information to obtain the second model information;

[0018] The second model information is subjected to backface culling based on the viewpoint to obtain the third model information;

[0019] Apply projection transformation and viewport transformation to the third model information to obtain the image and planar mapping information of the user operation;

[0020] The planar mapping information includes the tooth plane and its corresponding shape, the shape including path points, and the coordinate system of the path points being the coordinate system of the image operated by the user.

[0021] According to an embodiment of the present invention, the process of obtaining the first tooth plane sequence and the second tooth plane sequence includes:

[0022] The shape of the overlap of the first path or the second path is determined based on the planar mapping information and the pixels contained in the first path or the second path.

[0023] The corresponding tooth plane is determined based on the shape of the overlap between the first path and the second path.

[0024] The corresponding tooth planes are determined by the overlapping shapes of the first or second path to remove duplicates, resulting in the first tooth plane sequence or the second tooth plane sequence.

[0025] According to one embodiment of the present invention, when a pixel overlaps with two tooth planes simultaneously, it is determined that the pixel does not overlap with either tooth plane.

[0026] According to one embodiment of the present invention, generating or updating the first target contour includes:

[0027] The eighth tooth plane list is obtained based on the first tooth plane list and plane mapping information;

[0028] The shape is rendered according to the rendering parameters corresponding to the first target contour, based on the eighth tooth plane list and plane mapping information.

[0029] According to one embodiment of the present invention, updating the first tooth plane list includes:

[0030] The first intersection is obtained based on the first tooth plane sequence and the second tooth plane sequence;

[0031] The third tooth plane sequence is obtained based on the first intersection;

[0032] Merge the third tooth plane sequence into the first tooth plane list.

[0033] According to one embodiment of the present invention, updating the first tooth plane list includes:

[0034] The second intersection is obtained based on the first tooth plane sequence and the second tooth plane sequence;

[0035] The fourth tooth plane sequence is obtained based on the second intersection;

[0036] Obtain the fifth tooth plane sequence and the sixth tooth plane sequence, wherein the fifth tooth plane sequence is the difference between the first tooth plane sequence and the intersection of the second tooth plane sequence, and the sixth tooth plane sequence is the difference between the second tooth plane sequence and the intersection of the second tooth plane sequence;

[0037] Traverse the fifth tooth plane sequence, obtain the seventh tooth plane sequence within the sixth tooth plane sequence where the distance between the tooth plane and its inner tooth plane is less than the first threshold, and in response to the seventh tooth plane sequence not being empty, add the tooth plane and the corresponding seventh tooth plane sequence to the fourth tooth plane sequence;

[0038] Update the fourth tooth plane sequence to the first tooth plane list.

[0039] According to one embodiment of the present invention, the total area of ​​the tooth planes in the first tooth plane list is obtained in the following manner:

[0040] A first graph network is constructed based on the relationships between planes in the tooth model. Points in the graph network are tooth planes. Points with relationships in the graph network are spatially adjacent. Points in the graph network have a first attribute and a second attribute. The first attribute is the coordinates of the center of the tooth plane, and the second attribute is the area of ​​the tooth plane. The edge between two points in the graph network has a length attribute, and the value of the length attribute is the spatial distance between the coordinates corresponding to the first attribute of the two points.

[0041] Calculate the total area of ​​the first tooth plane list based on the first graph network.

[0042] According to one embodiment of the present invention, an electronic device includes a memory and a processor, wherein the memory is coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement an image data processing method.

[0043] According to one embodiment of the present invention, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements an image data processing method.

[0044] The above method can achieve accurate and fast selection of regions, and the pixel and tooth plane can be compared by adjusting the viewing angle and shape matching.

[0045] The beneficial effects of the image data processing method and device provided by this invention are as follows:

[0046] By introducing a cross-validation and intelligent fusion mechanism for multi-view operation paths, the system effectively overcomes the problems of misselection and omission caused by model occlusion, visual errors, or operational jitter in a single viewpoint. The system can automatically identify the user's true selection intent from different angles and intelligently expand and correct based on the adjacency relationship in the tooth plane space, ensuring the accuracy and anatomical rationality of the final determined mating surface in three-dimensional space.

[0047] Transforming the complex task of selecting 3D tooth planes into intuitive 2D path drawing significantly reduces the operational threshold and learning cost for physicians. Unique interactive logic makes correction operations simple and quick. The system automatically calculates the total area of ​​connected regions and generates a visual contour in real time, providing physicians with immediate positive feedback and achieving a "what you see is what you get" interactive experience, greatly shortening the preparation time before prosthetic design.

[0048] By constructing a dental plane network and utilizing its connectivity for computation, the method itself exhibits good tolerance to noise and individual variability in the model data. Furthermore, the solution supports continuous multiple operations and dynamic updates, flexibly adapting to complex clinical scenarios and different physicians' operating habits, demonstrating strong universality and promising prospects for industrial application. Attached Figure Description

[0049] Figure 1 This is a flowchart of an image data processing method for determining the bonding surface provided in an embodiment of the present invention. Detailed Implementation

[0050] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0051] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0052] refer to Figure 1 The operational framework shown, in one embodiment of the present invention, provides an image data processing method for determining the bonding surface, specifically including the following execution steps:

[0053] Obtain the first path of the user's operation record on the first image from the first angle;

[0054] Obtain the second path of the user's operation record on the second image from the second angle;

[0055] The first tooth plane sequence is selected based on the first path;

[0056] The second tooth plane sequence is selected based on the second path;

[0057] Update the first tooth plane list based on the first tooth plane sequence and the second tooth plane sequence;

[0058] The total area of ​​the user operation area is determined based on the connectivity of the tooth planes within the first tooth plane list.

[0059] Generate or update the first target contour on the user-operated image based on the first tooth plane list;

[0060] The first or second image is obtained by projection of a tooth spatial model, and the first and second images at least contain image regions formed by partially consistent projections of the tooth plane.

[0061] The first and second images described in this invention originate from 3D images such as three-dimensional mesh models of teeth and dental surface models. These images are typically generated from point cloud data directly acquired by an intraoral scanner or from 3D scanning of plaster models followed by reconstruction. During their digital generation and processing, they deeply integrate various clinical diagnostic and design intent information from the dental placement chart, including information on the location of missing teeth, abutment design, clasp and rest positioning, and connector morphology. Specifically, the generation of the three-dimensional tooth space model relies heavily on the reference data contained in the dental placement chart (or dental lab worksheet) filled out by the dentist after clinical procedures. The fusion process includes, but is not limited to: obtaining initial three-dimensional geometric data of the patient's dentition, gingiva, and related tissues through a high-precision 3D scan using an intraoral scanner or a traditional impression; clearly identifying the edentulous area in the initial 3D model based on the "X" marked or blackened missing tooth location on the dental placement chart, which is crucial for subsequent design of the prosthesis structure in the correct position; and converting the abutment tooth location, clasp morphology, rest position, and connector design hand-drawn by the dentist on the dental placement chart into constraints in three-dimensional space. For example, the corresponding tooth position of the circled abutment tooth on the model will be marked as a key support point, and its surface morphology (such as observation lines) will be analyzed in detail to determine the optimal retention path. The hand-drawn clasps and supports provide design guidance for the attachment points, orientation and coverage of the system. This information is used to generate a precise three-dimensional retention structure on the corresponding surface of the abutment tooth. The drawn connector outline directly guides the morphological generation and boundary determination of the large metal connector or base in three-dimensional space.

[0062] Finally, the system integrates the original geometric scan data with the structured design data parsed from the tooth position chart to generate an enhanced three-dimensional tooth space model that not only includes anatomical morphology but also pre-defined restoration design intentions. This model already incorporates information on missing teeth, abutment tooth classification, and preset areas for retention and connection structures.

[0063] The user's operation of selecting the tooth plane via a path from two different angles essentially involves precise area confirmation and refinement on a digital model that has already been defined and enhanced by the clinician's design intent. This technical solution ensures that the final determined "fitting surface" is highly consistent with the physician's initial clinical design, achieving a seamless connection and data loop from clinical diagnosis to digital design, effectively improving the accuracy and efficiency of removable partial dentures and other prostheses.

[0064] The solution of this invention can be provided in a browser / server (BS) mode or a client / server (CS) model. To avoid the inconvenience caused by 3D rotation operations, the image area of ​​this invention is a normal two-dimensional viewpoint. The viewpoint adjustment is controlled through a separate user interaction area. The achievable controls include zooming in, zooming out, panning up, panning down, panning left, panning right, and rotating, each with its corresponding transformation matrix, thereby enabling image scaling, translation, and rotation operations on a two-dimensional image. To better support physician operations, shortcut keys can be set to quickly execute the above operations.

[0065] The image rendering of the present invention is implemented within a container, which can be an element in HTML or a renderable component in the client, which re-renders the image in response to changes in data.

[0066] The interaction between the physician and the image involves two valid operations. If one operation is invalid, the system can consider it as no operation by the user, thus enabling the quick cancellation of incorrect selections. The tooth model involved in this invention is a processed model containing multiple tooth planes and the spatial coordinates of points contained within those tooth planes. These points can be vertices of rectangular or triangular regions. After multiple matrix transformations, each point in the tooth model is finally projected onto its corresponding position in a two-dimensional image.

[0067] The position of a specific point from the observer's perspective (with the camera as the reference coordinate system) can be obtained through the following transformation process:

[0068] First, obtain the coordinates of points within a tooth model. The tooth model stores an array containing three dimensions (x, y, z). After mapping these coordinate arrays, the resulting arrays are recombined to obtain their coordinates in a new coordinate system. This transformation typically involves converting model coordinates to world coordinates, then to view coordinates, followed by projection and viewport transformations to obtain the final screen coordinates. Specifically, this includes:

[0069] The model's position and orientation in the 3D world are determined by translating, rotating, and scaling using the model matrix.

[0070] Transformation is performed using a view matrix, which is determined by the camera's position, viewing direction, and up vector direction. In this coordinate system, the camera is located at the origin and points in the negative Z-axis direction.

[0071] Then, using a projection matrix, the simulated camera lens projects the object within the 3D view frustum onto a standard cube; subsequently, a viewport transformation is performed to map the points in the aforementioned coordinate system onto the final screen for display. For details on implementing this transformation within the browser, refer to https: / / developer.mozilla.org / en-US / docs / Web / API / WebGL_API. This page details how to utilize the WebGL RenderingContext and its methods to complete the entire process from data to rendering, ultimately drawing onto the browser canvas. The specific operation can be summarized as: preparation and context acquisition, creating in HTML... <canvas>The process involves: element creation and obtaining the WebGL rendering context via JavaScript; data management (corresponding to model coordinates), creating buffers using interfaces such as WebGLBuffer to upload the vertex coordinates of the model (e.g., the (x,y,z) array of teeth) to the GPU; shader programming (the core of matrix transformation), creating and linking shader programs using WebGLShader and WebGLProgram; vertex shader, the crucial stage for performing the model matrix (translation, rotation, scaling), view matrix (camera transformation), and projection matrix transformations you described, passing the calculated matrices to the shader through uniform variables (such as WebGLUniformLocation) to perform coordinate transformations on each vertex; and finally, issuing drawing commands using methods such as drawArrays or drawElements to drive the GPU to execute the shader program, process the vertices, and generate the final pixels.

[0072] The WebGL API itself is low-level and does not provide matrix operation functions. Therefore, in actual development, third-party mathematical libraries (such as glMatrix) mentioned in the documentation are usually used to conveniently calculate the model, view, and projection matrices, and then the results are passed to WebGL. After the above transformation, the 3D model is converted into 2D graphics. The 2D graphics are used to determine whether the pixels operated by the user fall within a specific shape (such as the shape formed by connecting the pixels obtained from the transformation of the tooth plane), and thus to determine whether the pixels of the user's operation path are associated with a certain shape. For example, a tooth plane contains 3 pixels A, B, and C. After transformation, the points obtained in the image are a, b, and c. Then, a, b, and c form a shape constrained in the 2D plane. The overlap detection (some software uses contains detection) is used to detect whether a pixel is within this shape.

[0073] The user's operation path is captured through an integrated handwriting input device. For example, in a Canvas-based rendering environment, the system listens for pointer events emitted by the handwriting tablet, including pointerDown, pointerMove, and pointerUp. When the stylus is pressed (pointerDown), the system begins recording the position coordinates of its tip; during the movement (pointerMove), new coordinate points are continuously added to the recording sequence; recording stops when the stylus is released (pointerUp). In this way, an array of [x:number, y:number] coordinate objects is obtained, which accurately represents the operation path drawn by the user on the image using the stylus. Simultaneously, this path is visually presented on the image as continuously drawn lines in real time, providing the user with clear and smooth operation feedback, allowing the user to intuitively feel their actions.

[0074] A user can perform an operation at one angle to obtain a selection area; then switch directions and perform the operation again to obtain another selection area. If the two are similar or consistent, the user's selection can be considered reliable; if the two are unrelated, the user is considered to have undone the selection.

[0075] The confirmed selection area can be used to update the cached tooth plane list, which can be set to empty during initialization.

[0076] However, since a tooth plane is typically composed of multiple partitions, relying solely on a single selection requires multiple correct operations to obtain a complete sequence of tooth planes. To address this, the applicant introduced adjacency relationships based on the concept of graph networks and expanded and determined the selection area by detecting connectivity and operational area. Connectivity is achieved by detecting connected tooth planes within the selected area, thus calculating the area of ​​the selected region.

[0077] Specifically, a graph network can be constructed based on whether the tooth planes are adjacent. This graph network does not consider the cost problem and is set as an undirected graph network. It includes points representing the tooth planes. The length between points can represent the relationship between the two planes, and a boolean attribute is set to determine whether they are adjacent. When constructing the graph, the addition of corresponding edges in the graph network can be determined by checking whether they are adjacent. In this case, if there is an edge between two points, they are necessarily adjacent.

[0078] After constructing the graph, graph calculations can be performed to obtain the total area of ​​the selected regions contained in the first toothed plane list. Then, based on connectivity, it can be determined which toothed planes can be added to the area calculation within the selected regions. Specifically, for example, a toothed plane may not be included in the first toothed plane list, but if it has at least three neighbors in the first toothed plane list, it can be added to the area calculation list. It should be noted that adding to the area calculation is not the same as adding to the first toothed plane list.

[0079] In addition, the corresponding outline can be updated on the user's graphical interface to achieve a visual display effect. Specifically, the shape of the first tooth plane list within the graphic is obtained by converting its coordinates, and the shape is filled to achieve outline recognition, that is, to achieve the rendering of the first target outline.

[0080] In addition, a menu item can be set up to export the corresponding selection model.

[0081] The above method can be used to quickly select a target area. When the selection is correct, it can be done by selecting from two different perspectives. If the selection is incorrect in one step, the selection can be cleared simply by selecting an irrelevant area.

[0082] In some embodiments of the present invention, the first angle and the second angle are not the same. The user selects tooth planes distributed at different angles and viewing angles by selecting tooth planes at different angles and merging them.

[0083] In some embodiments of the present invention, the first angle and the second angle are the same. By continuously selecting and merging the tooth planes at a uniform angle, the user overcomes the drawback of word selection requiring high operator skill.

[0084] It should be noted that the above operation relies on two operations, which means that after the two operations are completed, the previous operation can be ignored or regarded as the first step of a new operation. For example, if paths P1, P2, P3, and P4 are obtained, P1 and P2, P3 and P4 can be processed according to the method of the present invention, and P1 and P2, P2 and P3, P3 and P4 can also be processed according to the method of the present invention. Under this operation mode, if the P1 operation is incorrect, P2 can be selected outside the tooth plane area, which can achieve the aforementioned effect of eliminating incorrect selection.

[0085] It should be noted that the above operations can be applied to a single tooth or multiple teeth. When dealing with multiple teeth, the corresponding graphic mappings should be calculated and generated separately for each tooth.

[0086] To avoid interference, you can choose to display part or all of the tooth model.

[0087] According to one embodiment of the present invention, the image of user operation is generated based on the following method:

[0088] The model obtained from the toothed plate transformation is converted into the world coordinate system to obtain the first model information;

[0089] Get the user's current first-person perspective;

[0090] Apply the translation, rotation, and scaling matrices corresponding to the first viewpoint to the first model information to obtain the second model information;

[0091] The second model information is subjected to backface culling based on the viewpoint to obtain the third model information;

[0092] Apply projection transformation and viewport transformation to the third model information to obtain the image and planar mapping information of the user operation;

[0093] The planar mapping information includes the tooth plane and its corresponding shape, the shape including path points, and the coordinate system of the path points being the coordinate system of the image operated by the user.

[0094] According to an embodiment of the present invention, the process of obtaining the first tooth plane sequence and the second tooth plane sequence includes:

[0095] The shape of the overlap of the first path or the second path is determined based on the planar mapping information and the pixels contained in the first path or the second path.

[0096] The corresponding tooth plane is determined based on the shape of the overlap between the first path and the second path.

[0097] The corresponding tooth planes are determined by the overlapping shapes of the first or second path to remove duplicates, resulting in the first tooth plane sequence or the second tooth plane sequence.

[0098] According to one embodiment of the present invention, when a pixel overlaps with two tooth planes simultaneously, it is determined that the pixel does not overlap with either tooth plane.

[0099] In this embodiment, if a point corresponds to two selection areas simultaneously, the pixel is considered an invalid selection. This method avoids selecting too many tooth planes and prevents accidental selection. It should be noted that a path contains multiple pixels, and in very low probability, the user strictly follows the shape boundaries when selecting. That is, a path will always contain pixels that are only included in one selection area, thus avoiding invalid selections.

[0100] According to one embodiment of the present invention, generating or updating the first target contour includes:

[0101] The eighth tooth plane list is obtained based on the first tooth plane list and plane mapping information;

[0102] The shape is rendered according to the rendering parameters corresponding to the first target contour, based on the eighth tooth plane list and plane mapping information.

[0103] According to one embodiment of the present invention, updating the first tooth plane list includes:

[0104] The first intersection is obtained based on the first tooth plane sequence and the second tooth plane sequence;

[0105] The third tooth plane sequence is obtained based on the first intersection;

[0106] Merge the third tooth plane sequence into the first tooth plane list.

[0107] According to one embodiment of the present invention, updating the first tooth plane list includes:

[0108] The second intersection is obtained based on the first tooth plane sequence and the second tooth plane sequence;

[0109] The fourth tooth plane sequence is obtained based on the second intersection;

[0110] Obtain the fifth tooth plane sequence and the sixth tooth plane sequence, wherein the fifth tooth plane sequence is the difference between the first tooth plane sequence and the intersection of the second tooth plane sequence, and the sixth tooth plane sequence is the difference between the second tooth plane sequence and the intersection of the second tooth plane sequence;

[0111] Traverse the fifth tooth plane sequence, obtain the seventh tooth plane sequence within the sixth tooth plane sequence where the distance between the tooth plane and its inner tooth plane is less than the first threshold, and in response to the seventh tooth plane sequence not being empty, add the tooth plane and the corresponding seventh tooth plane sequence to the fourth tooth plane sequence;

[0112] Update the fourth tooth plane sequence to the first tooth plane list.

[0113] The specific implementation process of updating the first tooth plane list in the above embodiments is as follows:

[0114] Based on the first tooth plane sequence obtained from the first angle and the second tooth plane sequence obtained from the second angle, a second intersection is calculated. This intersection represents the tooth planes explicitly selected by the user from both different perspectives, representing the core area where the user's selection intent is most certain and consistent. Based on this second intersection, a fourth tooth plane sequence is created. Initially, the fourth tooth plane sequence contains all tooth planes within this core consensus area. Next, the system calculates the difference between the first tooth plane sequence and the second intersection to obtain the fifth tooth plane sequence, and the difference between the second tooth plane sequence and the second intersection to obtain the sixth tooth plane sequence. The fifth and sixth tooth plane sequences represent the tooth planes selected by the user from only a single perspective, which have not yet reached a consensus. Subsequently, the system further traverses each tooth plane P in the fifth tooth plane sequence. For each plane P, the system searches for all tooth planes in the sixth tooth plane sequence whose distance in three-dimensional space is less than a first threshold; these tooth planes are collected into a seventh tooth plane sequence. If the seventh tooth plane sequence is not empty, it indicates that there exists a selected area spatially adjacent to the current plane P from another perspective. This strongly suggests that the user intended to select a continuous surface, even if it didn't perfectly overlap due to viewpoint occlusion or operational errors. At this point, the system adds plane P and its corresponding neighboring tooth plane sequences to the fourth tooth plane sequence. Finally, the fourth tooth plane sequence, containing the core consensus region and the intelligent matching region, is updated to the first tooth plane list as the final selection area after this user operation.

[0115] The above processing method, by introducing the key parameter of spatial distance threshold, upgrades simple set operations to intelligent selection and fusion based on three-dimensional spatial understanding. It effectively overcomes the inherent uncertainty and incompleteness in multi-view operation, ensuring that the final generated first target contour is more complete and continuous, and can truly reflect the entire fitting surface selected by the user's intention. This enables accurate, efficient, and robust selection of the fitting surface, thereby greatly improving the efficiency and clarity of doctor-patient communication.

[0116] According to one embodiment of the present invention, the total area of ​​the tooth planes in the first tooth plane list is obtained in the following manner:

[0117] A first graph network is constructed based on the relationships between planes in the tooth model. Points in the graph network are tooth planes. Points with relationships in the graph network are spatially adjacent. Points in the graph network have a first attribute and a second attribute. The first attribute is the coordinates of the center of the tooth plane, and the second attribute is the area of ​​the tooth plane. The edge between two points in the graph network has a length attribute, and the value of the length attribute is the spatial distance between the coordinates corresponding to the first attribute of the two points.

[0118] Calculate the total area of ​​the first tooth plane list based on the first graph network.

[0119] According to one embodiment of the present invention, an electronic device includes a memory and a processor, wherein the memory is coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the above-described image data processing method.

[0120] According to one embodiment of the present invention, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the aforementioned image data processing method.

[0121] Those skilled in the art will recognize that the modules and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0122] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described apparatus and equipment can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0123] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0124] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0125] In addition, the functional modules in the embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0126] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the energy-saving signal transmission / reception methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0127] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

[0128] It should be understood that the sequence numbers of the steps in the invention's content and embodiments do not absolutely imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention. The foregoing description of embodiments of this disclosure has been provided for illustrative and descriptive purposes. The foregoing description is not exhaustive and is not intended to limit this disclosure to the exact form disclosed. Various modifications and variations may exist based on the foregoing teachings, or various modifications and variations may be derived from the practice of this disclosure. These embodiments were chosen and described to illustrate the principles of this disclosure and its practical application, so that those skilled in the art can utilize this disclosure in various implementations and modifications suitable for the specific purpose of the concept.< / canvas>

Claims

1. An image data processing method for determining the bonding surface, characterized in that, include: Obtain the first path of the user's operation record on the first image from the first angle; Obtain the second path of the user's operation record on the second image from the second angle; The first tooth plane sequence is selected based on the first path; The second tooth plane sequence is selected based on the second path; Update the first tooth plane list based on the first tooth plane sequence and the second tooth plane sequence; The total area of ​​the user operation area is determined based on the connectivity of the tooth planes within the first tooth plane list. Generate or update the first target contour on the user-operated image based on the first tooth plane list; The first or second image is obtained by projection of a tooth spatial model, and the first and second images at least contain image regions formed by partially consistent projections of the tooth plane.

2. The image data processing method for determining the bonding surface as described in claim 1, characterized in that, The images that the user interacts with are generated based on the following method: The model obtained from the toothed plate transformation is converted into the world coordinate system to obtain the first model information; Get the user's current first-person perspective; Apply the translation, rotation, and scaling matrices corresponding to the first viewpoint to the first model information to obtain the second model information; The second model information is subjected to backface culling based on the viewpoint to obtain the third model information; Apply projection transformation and viewport transformation to the third model information to obtain the image and planar mapping information of the user operation; The planar mapping information includes the tooth plane and its corresponding shape, the shape including path points, and the coordinate system of the path points being the coordinate system of the image operated by the user.

3. The image data processing method for determining the bonding surface as described in claim 2, characterized in that, The process of obtaining the first tooth plane sequence and the second tooth plane sequence includes: The shape of the overlap of the first path or the second path is determined based on the planar mapping information and the pixels contained in the first path or the second path. The corresponding tooth plane is determined based on the shape of the overlap between the first path and the second path. The corresponding tooth planes are determined by the overlapping shapes of the first or second path to remove duplicates, resulting in the first tooth plane sequence or the second tooth plane sequence.

4. The image data processing method for determining the bonding surface as described in claim 3, characterized in that, When a pixel overlaps with two tooth planes simultaneously, it is determined that the pixel does not overlap with either tooth plane.

5. The image data processing method for determining the bonding surface as described in claim 2, characterized in that, The generation or updating of the first target contour includes: The eighth tooth plane list is obtained based on the first tooth plane list and plane mapping information; The shape is rendered according to the rendering parameters corresponding to the first target contour, based on the eighth tooth plane list and plane mapping information.

6. The image data processing method for determining the bonding surface as described in claim 1, characterized in that, The updated first tooth plane list includes: The first intersection is obtained based on the first tooth plane sequence and the second tooth plane sequence; The third tooth plane sequence is obtained based on the first intersection; Merge the third tooth plane sequence into the first tooth plane list.

7. The image data processing method for determining the bonding surface as described in claim 1, characterized in that, The updated first tooth plane list includes: The second intersection is obtained based on the first tooth plane sequence and the second tooth plane sequence; The fourth tooth plane sequence is obtained based on the second intersection; Obtain the fifth tooth plane sequence and the sixth tooth plane sequence, wherein the fifth tooth plane sequence is the difference between the first tooth plane sequence and the intersection of the second tooth plane sequence, and the sixth tooth plane sequence is the difference between the second tooth plane sequence and the intersection of the second tooth plane sequence; Traverse the fifth tooth plane sequence, obtain the seventh tooth plane sequence within the sixth tooth plane sequence where the distance between the tooth plane and its inner tooth plane is less than the first threshold, and in response to the seventh tooth plane sequence not being empty, add the tooth plane and the corresponding seventh tooth plane sequence to the fourth tooth plane sequence; Update the fourth tooth plane sequence to the first tooth plane list.

8. The image data processing method for determining the bonding surface as described in claim 1, characterized in that, The total area of ​​the tooth planes in the first tooth plane list is obtained in the following way: A first graph network is constructed based on the relationships between planes in the tooth model. Points in the graph network are tooth planes. Points with relationships in the graph network are spatially adjacent. Points in the graph network have a first attribute and a second attribute. The first attribute is the coordinates of the center of the tooth plane, and the second attribute is the area of ​​the tooth plane. The edge between two points in the graph network has a length attribute, and the value of the length attribute is the spatial distance between the coordinates corresponding to the first attribute of the two points. Calculate the total area of ​​the first tooth plane list based on the first graph network.

9. An electronic device, characterized in that, The method includes a memory and a processor, wherein the memory is coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the image data processing method according to any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the image data processing method as described in any one of claims 1-8.

Images