Method and device for molding oral prosthesis model

Abstract

The present invention relates to the technical field of oral prosthesis, and in particular to a method and device for forming an oral prosthesis model, the method comprising the following steps: obtaining a multi-directional oral image; performing spline interpolation smoothing processing on the multi-directional oral image to construct a super-pixel oral image; marking each oral tissue feature point based on the super-pixel oral image; performing intra-oral spatial positioning calculation on each oral tissue feature point to obtain multiple oral tissue precise coordinates; constructing an oral tissue coordinate system based on multiple oral tissue precise coordinates; performing three-dimensional morphological structure fitting on multiple oral tissue precise coordinates to construct a three-dimensional curved surface oral structure model; performing texture contour quantitative analysis on the super-pixel oral image, and performing microscopic oral texture abstraction to generate an oral texture rendering. The present invention improves the personalized adaptability and matching degree of oral prostheses.

Description

Technical Field

[0001] The invention relates to the technical field of oral prosthesis, and in particular to a molding method and device for an oral prosthesis model. Background Art

[0002] In the context of the rapid development of dental technology, the traditional method of making oral prostheses can no longer meet the needs of modern dental diagnosis and treatment. The traditional method mainly relies on dentists to make them manually or select ready-made standard models, which is difficult to achieve complete personalization and precise customization. There are often problems such as low efficiency in making prosthesis models, low personalization adaptability and low matching with users. This will not only affect the wearing comfort and functionality of prostheses, but also fail to fully meet the requirements of increasingly picky patients for beauty and naturalness. With the rapid development of computer-aided design and manufacturing (CAD / CAM) technology and the widespread application of 3D scanning, modeling, printing and other technologies, the production of oral prostheses has ushered in new opportunities. By adopting advanced computer vision and digital modeling technology, high-precision digital modeling of the patient's oral structure can be achieved, providing reliable technical support for the subsequent production of personalized prostheses. At the same time, using rapid manufacturing technologies such as 3D printing, personalized prostheses that fit the patient's oral structure can be quickly manufactured based on digital models, greatly improving production efficiency and quality.

[0003] However, digital modeling and rapid manufacturing technology alone are far from enough. A complete and intelligent oral prosthesis model forming method must be established to truly realize the full process automation from oral digital acquisition to personalized prosthesis manufacturing. This not only requires cutting-edge technologies in multiple disciplines such as computer vision, 3D modeling, and material science, but also requires a deep understanding of the physiological structure and mechanical properties of the oral cavity to ensure that the final prosthesis can meet the needs of patients in terms of appearance, wearing feel, and functionality. Therefore, against the above background, the development of an intelligent, full-process oral prosthesis model forming method will become the key to the new generation of digital dental diagnosis and treatment technology. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a method and device for forming an oral prosthesis model to solve at least one of the above technical problems.

[0005] To achieve the above object, the present invention provides a method for forming an oral prosthesis model, comprising the following steps:

[0006] Step S1: acquiring a multi-directional oral image; performing spline interpolation smoothing processing on the multi-directional oral image to construct a super-pixel oral image;

[0007] Step S2: annotating each oral tissue feature point based on the superpixel oral image; performing intraoral spatial positioning calculation on each oral tissue feature point, thereby obtaining multiple oral tissue precise coordinates;

[0008] Step S3: constructing an oral tissue coordinate system based on multiple oral tissue precise coordinates; performing three-dimensional morphological structure fitting on the multiple oral tissue precise coordinates to construct a three-dimensional curved surface oral structure model;

[0009] Step S4: quantitatively analyzing the texture contour of the superpixel oral image, and abstracting the microscopic oral texture to generate an oral texture rendering;

[0010] Step S5: dynamically texture mapping the oral texture rendering image to the three-dimensional curved oral structure model based on the oral tissue coordinate system to obtain an optimized three-dimensional texture mapping model;

[0011] Step S6: Simulate the dynamic behavior of the oral cavity on the optimized three-dimensional texture mapping model, perform iterative simulation parameter tuning, and construct an oral cavity simulation tuning model to perform virtual molding operations of the oral cavity model.

[0012] The present invention provides a comprehensive perspective of the oral cavity by acquiring multi-directional oral images, including images at different angles and positions, which helps to fully understand the structure and morphology of the oral cavity. Spline interpolation smoothing is used to smooth the oral image to reduce noise and image discontinuity, and improve the accuracy and reliability of subsequent processing. Superpixel oral images are constructed to divide the oral image into smaller and more uniform areas, which is helpful for subsequent oral tissue feature point annotation and oral texture analysis. Oral tissue feature points are annotated to identify key points of different tissues in the oral cavity, such as anatomical feature points of teeth and gum line, which is helpful for subsequent construction and analysis of oral models. Intraoral spatial positioning calculation determines the position of oral tissue feature points in three-dimensional space, provides accurate oral tissue coordinate information, and provides a basis for the construction and analysis of oral models. An oral tissue coordinate system is constructed based on the precise coordinates of the oral tissue to establish the spatial relationship between various tissues in the oral cavity, and provide a consistent reference frame for the construction and analysis of the oral model. Three-dimensional morphological structure fitting is based on the distribution characteristics of the precise coordinates of the oral tissue to construct the oral structure. The three-dimensional curved oral structure model is generated by modeling and fitting, and a more realistic three-dimensional curved oral structure model is generated. The texture contour quantitative analysis extracts the texture features of the super-pixel oral image, such as texture edge, texture density, etc., to provide a basis for the subsequent oral texture rendering. The microscopic oral texture abstraction simplifies and abstracts the oral texture, highlights the key features of the oral texture, and makes the oral texture rendering more visual. Through the oral tissue coordinate system, the oral texture rendering is mapped to the three-dimensional curved oral structure model to achieve accurate fitting of the texture in the oral model. The dynamic texture mapping generates a more realistic and accurate oral model according to the structural changes of the oral model. By optimizing the three-dimensional texture mapping, the realism and visualization of the oral model are further improved. Through the oral dynamic behavior simulation, the movement and deformation of the oral tissue are simulated, and the physiological process in the oral cavity is simulated. Through iterative simulation parameter tuning, the simulation results are optimized and adjusted according to the actual situation to improve the authenticity and credibility of the oral model. The oral simulation tuning model is constructed to provide an accurate simulation and simulation environment for the virtual molding of the oral model.

[0013] Preferably, step S1 comprises the following steps:

[0014] Step S11: Acquire multi-directional oral cavity images;

[0015] Step S12: performing grayscale pixel distribution calculation on the multi-directional oral cavity image to obtain a pixel distribution value;

[0016] Step S13: performing regional brightness difference analysis based on pixel distribution values ​​to generate regional brightness difference data;

[0017] Step S14: performing grayscale uniform remapping on the multi-directional oral cavity image based on the regional brightness difference data to generate a brightness balanced oral cavity image;

[0018] Step S15: performing spline interpolation smoothing processing on the brightness-balanced oral cavity image to construct a super-pixel oral cavity image.

[0019] The present invention provides a comprehensive perspective of the oral cavity by acquiring multi-directional oral images, including images at different angles and positions, which helps to fully understand the structure and morphology of the oral cavity. The grayscale pixel distribution calculation counts the number of pixels at each grayscale level in the oral image, provides grayscale distribution information of the oral image, and provides a basis for subsequent brightness equalization and regional brightness difference analysis. The regional brightness difference analysis identifies the brightness difference between different regions in the oral image and provides quantitative data of regional brightness difference. The grayscale uniform remapping adjusts the grayscale value in the oral image according to the regional brightness difference data to achieve brightness equalization, so that the overall brightness distribution of the oral image is more uniform, and the image observation and analysis effect is improved. The spline interpolation smoothing process smoothes the brightness-balanced oral image, reduces noise and image discontinuity, and improves the accuracy and reliability of subsequent processing. The super-pixel oral image is constructed to divide the oral image into smaller and more uniform regions, which helps the subsequent oral tissue feature point annotation and oral texture analysis.

[0020] Preferably, the specific steps of S15 are:

[0021] Calculating pixel gradients on the brightness-balanced oral image to obtain a pixel gradient sequence;

[0022] Calculate the gradient amplitude of the pixel gradient sequence to generate the gradient amplitude;

[0023] According to the gradient amplitude, the sharp mutation of the pixel gradient sequence is identified to extract the edge pixels;

[0024] Based on the edge pixels, the non-edge pixel area of ​​the brightness-balanced oral image is annotated to obtain a non-edge pixel area image;

[0025] Perform spline interpolation smoothing processing on the non-edge pixel area image and perform edge contour enhancement processing to obtain an edge contour smoothed image;

[0026] The edge contour smoothed image is reconstructed using super-pixel depth representation to construct a super-pixel oral image.

[0027] The present invention evaluates the grayscale change degree of each pixel in the image through pixel gradient calculation, provides the edge information of the image, and is helpful for the subsequent edge extraction and edge contour smoothing processing. The gradient amplitude calculation obtains the gradient strength of each pixel in the pixel gradient sequence, which is used to measure the significance and strength of the edge and provide a basis for the subsequent edge recognition and edge contour processing. The sharp mutation recognition identifies the position of the edge in the image according to the change of the gradient amplitude, extracts the edge pixels, and is used for the subsequent edge area labeling and edge contour processing. The non-edge pixel area labeling labels the non-edge pixels in the brightness balanced oral image according to the extracted edge pixels, and obtains the regional image containing only the non-edge pixels, which is used for the subsequent image processing and analysis. The spline interpolation smoothing processing smoothes the non-edge pixel area image, reduces noise and image discontinuity, and improves the visual effect and quality of the image. The edge contour enhancement processing highlights and strengthens the edge contour in the image, making the oral structure and edge features clearer and more visible. The superpixel deep representation reconstruction divides the edge contour smoothed image into smaller and more uniform superpixels, extracts the local feature information of the image, and provides a more detailed and accurate data basis for the construction and analysis of the oral prosthesis model.

[0028] Preferably, the specific steps of step S2 are:

[0029] Step S21: Performing visual recognition of tissue features on the superpixel oral image and marking each oral tissue feature point;

[0030] Step S22: performing intraoral spatial positioning calculation on each oral tissue feature point to generate a plurality of oral tissue spatial coordinates;

[0031] Step S23: performing a three-dimensional orientation deviation analysis on the super-pixel oral image to obtain an image orientation deviation value;

[0032] Step S24: performing fine deviation correction on multiple oral tissue spatial coordinates based on the image orientation deviation value, thereby obtaining multiple oral tissue precise coordinates.

[0033] The present invention automatically detects and annotates feature points of different oral tissues, such as teeth, gums, tongue, etc., by analyzing super-pixel oral images through tissue feature visual recognition. These annotated feature points are helpful for subsequent intra-oral spatial positioning and coordinate calculation. The intra-oral spatial positioning calculation calculates the three-dimensional spatial position of the annotated oral tissue feature points in the oral cavity to generate the spatial coordinates of each oral tissue. These coordinate information are used for the construction and analysis of oral prosthesis models. The three-dimensional orientation deviation analysis identifies the orientation deviation in the image by analyzing the three-dimensional feature information in the super-pixel oral image. These deviation values ​​reflect the rotation or translation of the image relative to the real oral structure. The fine deviation correction corrects and amends the previously calculated oral tissue spatial coordinates according to the image orientation deviation value. By correcting the coordinates, more precise and accurate oral tissue position information is obtained, providing a more reliable data basis for the construction and analysis of oral prosthesis models.

[0034] Preferably, the specific steps of step S3 are:

[0035] Step S31: performing multi-directional posture alignment on multiple oral tissue precise coordinates to construct an oral tissue coordinate system;

[0036] Step S32: Performing spatial geometric layout analysis on multiple precise coordinates of oral tissues to generate spatial geometric layout data of feature points;

[0037] Step S33: performing three-dimensional morphological structure fitting on the superpixel oral cavity image based on the feature point spatial geometric layout data to generate a preliminary three-dimensional oral cavity structure model;

[0038] Step S34: Optimizing the overlapping tissue morphology of the preliminary three-dimensional oral structure model based on the oral tissue coordinate system to construct a three-dimensional curved surface oral structure model.

[0039] The present invention uses multi-directional posture alignment to align multiple oral tissues into a common oral tissue coordinate system according to their precise coordinates. The alignment process ensures the consistency and accuracy of the oral tissues in the coordinate system, providing a consistent reference frame for subsequent analysis and modeling. The spatial geometric layout analysis uses the precise coordinates of multiple oral tissues to analyze the spatial relationship and geometric layout between them. By analyzing the relative position, angle, distance and other characteristics of the oral tissues, the spatial geometric layout data of the feature points are generated. The three-dimensional morphological structure fitting uses the spatial geometric layout data of the feature points and applies it to super-pixel oral images. Through the fitting algorithm, the spatial layout information of the feature points is applied to the image data to generate a preliminary three-dimensional oral structure model. This model provides the overall morphological information of the oral structure. The overlapping tissue morphology optimization is based on the oral tissue coordinate system to optimize the morphology of the preliminary three-dimensional oral structure model. Through the optimization algorithm and technology, the morphology of the oral tissue is adjusted and improved to obtain a more accurate and realistic three-dimensional curved surface oral structure model. This model is used for the design and analysis of oral prostheses to provide more accurate oral structure information.

[0040] Preferably, the specific steps of step S34 are:

[0041] Based on the oral tissue coordinate system, the tissue structure overlap analysis is performed on each oral tissue feature point to generate a tissue overlap area;

[0042] Conduct tissue structure connection analysis on each oral tissue feature point to obtain the connection relationship of the feature points;

[0043] Based on the connection relationship of feature points, local compatibility constraint analysis is performed on the tissue overlap area to obtain local compatibility data of the overlap area;

[0044] Based on the local compatible data of the overlapping area, the overlapping morphology of the preliminary three-dimensional oral structure model is eliminated to generate an overlapping optimized three-dimensional model;

[0045] The overlapping optimized three-dimensional models are subjected to global surface smoothing to construct a three-dimensional surface oral structure model.

[0046] The present invention uses an oral tissue coordinate system to perform a tissue structure coincidence analysis on the feature points of each oral tissue, which helps determine which oral tissues have intersecting or overlapping areas. The generated tissue coincidence area provides a structural relationship between oral tissues. By performing a tissue structure connection analysis on the oral tissue feature points, the connection relationship between the feature points is determined, which helps to understand the anatomical structure and relative position between oral tissues. The feature point connection relationship provides topological structure information between tissues. Using the feature point connection relationship, a local compatibility constraint analysis is performed on the tissue coincidence area to help determine the compatibility relationship within the coincidence area, that is, the adaptability and consistency of each oral tissue in the coincidence area. The generated local compatibility data of the coincidence area provides a It provides morphological consistency information within the overlapping area of ​​oral tissue. Based on the local compatibility data of the overlapping area, the preliminary three-dimensional oral structure model is overlapped and the inconsistency of the overlapping area is eliminated, so that the oral tissue has a more continuous and smooth morphology within the overlapping area. The generated overlapping optimized three-dimensional model provides more accurate and realistic oral structure information. Global surface smoothing is performed on the overlapping optimized three-dimensional model to further improve the appearance quality and morphological continuity of the oral structure. Through smoothing, the irregularities and noise on the model surface are eliminated, making the oral structure model smoother and more realistic. The generated three-dimensional curved surface oral structure model can be used for the design and analysis of oral prostheses, providing more accurate and realistic oral structure information.

[0047] Preferably, the specific steps of step S4 are:

[0048] Step S41: performing inner wall detail texture recognition on the superpixel oral cavity image to obtain oral cavity inner wall detail texture data;

[0049] Step S42: performing texture contour quantitative analysis on the oral cavity inner wall detail texture data to extract texture contour feature parameters;

[0050] Step S43: abstracting the microscopic oral texture of the superpixel oral image based on the texture contour feature parameters, thereby generating an oral texture feature vector;

[0051] Step S44: Performing texture color subtle rendering on the oral texture feature vector to generate an oral texture rendering image.

[0052] The present invention recognizes and extracts detailed texture data of the inner wall by analyzing the texture features of the inner wall of the oral cavity in the super-pixel oral image through inner wall detail texture recognition. These texture data contain microscopic detail information of the inner wall of the oral cavity, such as wrinkles, textures, particles, etc. The texture contour quantitative analysis quantitatively analyzes the detailed texture data of the inner wall of the oral cavity, extracts the characteristic parameters of the texture contour, and quantitatively describes the texture information of the inner wall of the oral cavity by analyzing the shape, density, distribution and other characteristics of the texture. These characteristic parameters are used for subsequent texture feature abstraction and analysis. The microscopic oral texture abstraction uses the texture contour characteristic parameters to abstract the texture of the inner wall of the oral cavity in the super-pixel oral image, and better expresses the characteristics and changes of the oral texture by converting the texture information into a feature vector representation. These oral texture feature vectors provide an abstraction and description of the oral texture. The texture color subtle rendering performs rendering processing on the oral texture feature vector to generate an oral texture rendering image. The texture features and subtle color changes of the inner wall of the oral cavity are intuitively displayed through the rendered image. These oral texture rendering images are helpful for the visualization and analysis of the oral prosthesis model, and provide more realistic and vivid oral texture information.

[0053] Preferably, the specific steps of step S5 are:

[0054] Step S51: performing texture positioning on the oral texture rendering image based on the oral tissue coordinate system to obtain oral texture matching positioning data;

[0055] Step S52: dynamically texture mapping the oral texture rendering image to the three-dimensional curved surface oral structure model based on the oral texture matching positioning data to generate a three-dimensional oral texture mapping model;

[0056] Step S53: Optimizing the texture level of the three-dimensional oral cavity texture mapping model to obtain an optimized three-dimensional texture mapping model.

[0057] The present invention associates an oral texture rendering image with an oral tissue coordinate system through oral texture positioning to achieve oral texture positioning, and determines the position and direction of the oral texture in the oral model by positioning the oral texture rendering image on a three-dimensional oral structure model. Dynamic texture mapping uses oral texture matching positioning data to map the oral texture rendering image onto a three-dimensional curved surface oral structure model to achieve presentation of the oral texture in the three-dimensional model. By combining the oral texture with the oral structure model, a real oral texture effect is presented. These three-dimensional oral texture mapping models provide three-dimensional observation and analysis of oral texture, which is helpful for the realism and visualization of oral prosthesis models. Texture hierarchy optimization optimizes the three-dimensional oral texture mapping model to improve the quality and realism of the model. By adjusting parameters such as texture resolution, lighting effects and rendering details, the oral texture mapping model is made more realistic and natural. The optimized three-dimensional texture mapping model presents a more realistic oral texture effect, and improves the visualization and simulation effects of the oral prosthesis model.

[0058] Preferably, the specific steps of step S6 are:

[0059] Step S61: performing oral dynamic behavior simulation on the optimized three-dimensional texture mapping model to generate dynamic behavior simulation data;

[0060] Step S62: performing phase change trajectory analysis on the oral behavior simulation data to generate an oral phase change trajectory;

[0061] Step S63: performing nonlinear interaction analysis between tissues on the oral stage change trajectory to obtain oral tissue nonlinear interaction data;

[0062] Step S64: iteratively tuning the simulation parameters of the optimized three-dimensional texture mapping model according to the oral tissue nonlinear interaction data, and constructing an oral simulation tuning model to perform virtual molding operations of the oral model.

[0063] The present invention dynamically simulates the optimized three-dimensional texture mapping model through oral dynamic behavior simulation, simulates the movement and change process in the oral cavity, and generates simulation data by simulating the dynamic behavior of the oral cavity, including information such as deformation, movement trajectory and interactive behavior of oral tissue. These dynamic behavior simulation data provide the temporal evolution process of the oral prosthesis model, making the oral model more realistic and dynamic. The oral stage change trajectory analysis analyzes the oral behavior simulation data to determine the change trajectory and pattern of the oral cavity at different stages. By analyzing the oral behavior simulation data, different stages in the oral cavity, such as opening and closing, chewing, swallowing, etc., are identified. The generated oral stage change trajectory provides morphological change information of the oral model at different stages, providing a basis for subsequent interaction analysis and simulation parameter tuning. The nonlinear interaction analysis between tissues analyzes the trajectory of oral stage changes and studies the interaction and influence relationship between different tissues in the oral cavity. By analyzing the trajectory of oral stage changes, the nonlinear interaction of different tissues is identified, such as the contact between teeth and tongue, the friction between lips and teeth, etc. The obtained oral tissue nonlinear interaction data provides detailed information on the interaction between tissues in the oral model. The oral simulation tuning model performs parameter tuning and optimization on the optimized three-dimensional texture mapping model according to the nonlinear interaction data of oral tissues. Through iterative simulation parameter tuning, the parameters in the oral model are adjusted to make it closer to the behavior and characteristics of the real oral cavity. The constructed oral simulation tuning model is used to perform virtual molding operations of oral models and realize accurate molding and simulation of oral prosthesis models.

[0064] In the present invention, a molding device for an oral prosthesis model is provided, which is used to perform the molding method for an oral prosthesis model as described above, comprising:

[0065] An interpolation and smoothing module is used to obtain multi-directional oral images; perform spline interpolation and smoothing processing on the multi-directional oral images to construct super-pixel oral images;

[0066] The spatial positioning module is used to annotate each oral tissue feature point based on the superpixel oral image; perform intraoral spatial positioning calculations on each oral tissue feature point to obtain multiple precise coordinates of oral tissues;

[0067] A three-dimensional morphological structure module is used to construct an oral tissue coordinate system based on multiple precise coordinates of oral tissues; perform three-dimensional morphological structure fitting on multiple precise coordinates of oral tissues to construct a three-dimensional curved surface oral structure model;

[0068] Texture abstraction module, used to perform quantitative texture contour analysis on superpixel oral images, abstract microscopic oral textures, and generate oral texture renderings;

[0069] A dynamic texture mapping module is used to dynamically texture map the oral texture rendering image to the three-dimensional curved oral structure model based on the oral tissue coordinate system to obtain an optimized three-dimensional texture mapping model;

[0070] The parameter tuning module is used to simulate the dynamic behavior of the oral cavity for the optimized three-dimensional texture mapping model, perform iterative simulation parameter tuning, and construct an oral cavity simulation tuning model to perform virtual molding operations of the oral cavity model.

[0071] The present invention smoothes multi-directional oral images through spline interpolation smoothing, reduces noise and discontinuity in the images, and constructs super-pixel oral images, which helps to improve the consistency and continuity of the oral model and provide a more stable data basis for subsequent steps. The spatial positioning module is used to mark the characteristic points of each oral tissue and perform spatial positioning calculations in the oral cavity to obtain the precise coordinates of each oral tissue. The positioning of these oral tissue characteristic points helps in the subsequent steps of oral structure modeling and texture mapping. Based on the precise coordinates of the oral tissue, the three-dimensional morphological structure module is used to construct the oral tissue coordinate system and perform three-dimensional morphological structure fitting. The geometric shape and spatial structure of the oral tissue are established through the three-dimensional morphological structure module, which provides accurate geometric information for the construction of the oral model in the subsequent steps. The texture abstraction module is used to construct the super-pixel oral The image is quantitatively analyzed for texture contours, and the microscopic oral texture is abstracted to generate an oral texture rendering. This extracts the texture features of the inner wall of the oral cavity and abstracts it into a form that can be calculated and rendered, providing richer data for texture mapping and visualization of the oral model. The dynamic texture mapping module dynamically maps the oral texture rendering to the three-dimensional curved oral structure model based on the oral tissue coordinate system. This accurately corresponds the oral texture rendering to the oral structure model, making the texture mapping of the oral model more realistic and accurate. The parameter tuning module simulates the dynamic behavior of the oral cavity on the optimized three-dimensional texture mapping model, and performs iterative simulation parameter tuning. Through the oral simulation tuning model, the dynamic behavior and changes of the oral cavity are simulated, the morphology and texture mapping of the oral model are optimized, and the oral prosthesis model is made more in line with the actual situation. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 A schematic diagram of the steps of a method for forming an oral prosthesis model according to the present invention;

[0073] Figure 2 Detailed implementation flow chart of step S1;

[0074] Figure 3 Detailed implementation flow chart of step S2;

[0075] Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0076] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0077] The present invention provides a method and device for forming an oral prosthesis model. The execution subjects of the method and device for forming an oral prosthesis model include but are not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio image management system, an information management system, and a cloud data management system.

[0078] See also Figures 1 to 4 The present invention provides a method for forming an oral prosthesis model, and the method for forming an oral prosthesis model comprises the following steps:

[0079] Step S1: acquiring a multi-directional oral image; performing spline interpolation smoothing processing on the multi-directional oral image to construct a super-pixel oral image;

[0080] Step S2: annotating each oral tissue feature point based on the superpixel oral image; performing intraoral spatial positioning calculation on each oral tissue feature point, thereby obtaining multiple oral tissue precise coordinates;

[0081] Step S3: constructing an oral tissue coordinate system based on multiple oral tissue precise coordinates; performing three-dimensional morphological structure fitting on the multiple oral tissue precise coordinates to construct a three-dimensional curved surface oral structure model;

[0082] Step S4: quantitatively analyzing the texture contour of the superpixel oral image, and abstracting the microscopic oral texture to generate an oral texture rendering;

[0083] Step S5: dynamically texture mapping the oral texture rendering image to the three-dimensional curved oral structure model based on the oral tissue coordinate system to obtain an optimized three-dimensional texture mapping model;

[0084] Step S6: Simulate the dynamic behavior of the oral cavity on the optimized three-dimensional texture mapping model, perform iterative simulation parameter tuning, and construct an oral cavity simulation tuning model to perform virtual molding operations of the oral cavity model.

[0085] The present invention provides a comprehensive perspective of the oral cavity by acquiring multi-directional oral images, including images at different angles and positions, which helps to fully understand the structure and morphology of the oral cavity. Spline interpolation smoothing is used to smooth the oral image to reduce noise and image discontinuity, and improve the accuracy and reliability of subsequent processing. Superpixel oral images are constructed to divide the oral image into smaller and more uniform areas, which is helpful for subsequent oral tissue feature point annotation and oral texture analysis. Oral tissue feature points are annotated to identify key points of different tissues in the oral cavity, such as anatomical feature points of teeth and gum line, which is helpful for subsequent construction and analysis of oral models. Intraoral spatial positioning calculation determines the position of oral tissue feature points in three-dimensional space, provides accurate oral tissue coordinate information, and provides a basis for the construction and analysis of oral models. An oral tissue coordinate system is constructed based on the precise coordinates of the oral tissue to establish the spatial relationship between various tissues in the oral cavity, and provide a consistent reference frame for the construction and analysis of the oral model. Three-dimensional morphological structure fitting is based on the distribution characteristics of the precise coordinates of the oral tissue to construct the oral structure. The three-dimensional curved oral structure model is generated by modeling and fitting, and a more realistic three-dimensional curved oral structure model is generated. The texture contour quantitative analysis extracts the texture features of the super-pixel oral image, such as texture edge, texture density, etc., to provide a basis for the subsequent oral texture rendering. The microscopic oral texture abstraction simplifies and abstracts the oral texture, highlights the key features of the oral texture, and makes the oral texture rendering more visual. Through the oral tissue coordinate system, the oral texture rendering is mapped to the three-dimensional curved oral structure model to achieve accurate fitting of the texture in the oral model. The dynamic texture mapping generates a more realistic and accurate oral model according to the structural changes of the oral model. By optimizing the three-dimensional texture mapping, the realism and visualization of the oral model are further improved. Through the oral dynamic behavior simulation, the movement and deformation of the oral tissue are simulated, and the physiological process in the oral cavity is simulated. Through iterative simulation parameter tuning, the simulation results are optimized and adjusted according to the actual situation to improve the authenticity and credibility of the oral model. The oral simulation tuning model is constructed to provide an accurate simulation and simulation environment for the virtual molding of the oral model.

[0086] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a method for forming an oral prosthesis model of the present invention. In this example, the steps of the method for forming an oral prosthesis model include:

[0087] Step S1: acquiring a multi-directional oral image; performing spline interpolation smoothing processing on the multi-directional oral image to construct a super-pixel oral image;

[0088] In this embodiment, an oral imaging device (such as an oral endoscope, X-ray, CT scan, etc.) is used to acquire multiple oral images to obtain oral structure information from different angles and viewing angles. These images include tissues such as teeth, gums, and tongue inside the oral cavity. Each oral image is converted into a digital image for subsequent processing. Image processing software or a programming language (such as Python) is used to implement this step. Spline interpolation smoothing is performed on each oral image. Spline interpolation is a numerical analysis method used to perform smooth interpolation calculations between given data points. In oral images, spline interpolation reduces noise and discontinuities in the image, making the image smoother and continuous. The oral images that have been smoothed by spline interpolation are combined together to construct a superpixel oral image. Superpixels are a method of segmenting images. Adjacent pixels are combined into superpixel regions with similar features. Superpixel oral images provide more consistent and continuous oral structure information, providing a more stable data basis for subsequent steps.

[0089] Step S2: annotating each oral tissue feature point based on the superpixel oral image; performing intraoral spatial positioning calculation on each oral tissue feature point, thereby obtaining multiple oral tissue precise coordinates;

[0090] In this embodiment, image processing and computer vision algorithms, such as feature point detection algorithms or deep learning methods (such as convolutional neural networks), are used to mark the feature points of each oral tissue in the super-pixel oral image. The oral tissue feature points are key points in the oral cavity, such as the tips of the teeth, the gum line, the center of the oral cavity, etc. The marked oral tissue feature points are used to perform intra-oral spatial positioning calculations. The intra-oral spatial positioning calculation uses a three-dimensional reconstruction algorithm, such as a method based on structured light scanning or stereo vision technology, to calculate the coordinates of each feature point in three-dimensional space. The intra-oral spatial positioning calculation also combines a three-dimensional coordinate system and reference markers (such as dental arch or head markers) to determine the precise position and direction of the feature points. According to the results of the intra-oral spatial positioning calculation, the precise coordinates of each oral tissue feature point are obtained. The precise coordinates of the oral tissue represent the exact position of each tissue in the oral cavity in three-dimensional space. The marking of the oral tissue feature points and the intra-oral spatial positioning calculation are completed to obtain the precise coordinates of multiple oral tissues.

[0091] Step S3: constructing an oral tissue coordinate system based on multiple oral tissue precise coordinates; performing three-dimensional morphological structure fitting on the multiple oral tissue precise coordinates to construct a three-dimensional curved surface oral structure model;

[0092] In this embodiment, an oral tissue coordinate system is established based on the precise coordinates of the oral tissue. The oral tissue coordinate system is a three-dimensional coordinate system used to describe the relative positions and relationships of various tissues in the oral cavity. Appropriate reference feature points or reference markers (such as dental arch or head markers) are selected as the origin and direction of the oral tissue coordinate system. The three-dimensional morphological structure is fitted using the precise coordinates of the oral tissue to construct a three-dimensional curved surface structure model of the oral cavity. The three-dimensional morphological structure fitting uses methods such as surface fitting or voxel reconstruction to connect or fill the oral tissue feature points to generate a continuous three-dimensional curved surface structure. A surface fitting algorithm, such as the least squares method, spline curve or surface fitting, is used to fit the surface structure of the oral tissue feature points. A voxel reconstruction algorithm, such as the Marching Cubes algorithm, is also used to convert discrete feature points into a continuous three-dimensional curved surface structure. A three-dimensional curved surface oral structure model is constructed based on the result of the three-dimensional morphological structure fitting. Computer graphics technology and three-dimensional modeling software, such as OpenGL, Blender or CAD tools, are used to convert the fitted surface structure into a visual three-dimensional model. The three-dimensional curved surface oral structure model includes the shape and geometric information of oral tissues such as teeth, gums, tongue, and oral mucosa.

[0093] Step S4: quantitatively analyzing the texture contour of the superpixel oral image, and abstracting the microscopic oral texture to generate an oral texture rendering;

[0094] In this embodiment, a texture profile quantitative analysis is performed on a superpixel oral image to obtain texture features of different areas in the oral cavity. Texture features of each superpixel area in the oral image are calculated using a texture feature description algorithm, such as a gray level co-occurrence matrix (GLCM), a local binary pattern (LBP), or a Gaussian filter. Texture features include texture intensity, direction, contrast, uniformity, etc. The oral texture is microscopically abstracted to reduce details and highlight texture features. A filter, blurring, or an image processing algorithm, such as a Gaussian blur, a median filter, a wavelet transform, etc., is used to process the oral texture image to achieve texture abstraction. The goal of abstraction is to retain the overall features of the oral texture while reducing local details in order to better display the overall morphology of the oral texture. An oral texture rendering is generated based on the result of microscopic oral texture abstraction. The abstracted oral texture image is fused with an oral structure model using image rendering technology, a texture mapping method, or an image synthesis algorithm to generate an oral rendering with texture information. The oral rendering is a color image or a grayscale image used to display texture features and distribution of different areas in the oral cavity.

[0095] Step S5: dynamically texture mapping the oral texture rendering image to the three-dimensional curved oral structure model based on the oral tissue coordinate system to obtain an optimized three-dimensional texture mapping model;

[0096] In this embodiment, the oral tissue coordinate system is aligned with the three-dimensional curved surface oral structure model. The oral tissue coordinate system is matched with the three-dimensional curved surface oral structure model using methods such as rigid body transformation or non-rigid body deformation, so that they are aligned in the same coordinate space. Based on the oral tissue coordinate system, the oral texture rendering is dynamically mapped to the three-dimensional curved surface oral structure model. The oral texture rendering is projected onto the surface of the three-dimensional curved surface oral structure model. A projection algorithm, such as perspective projection or orthogonal projection, is used to map the texture image to the corresponding position on the surface of the three-dimensional model. An image registration algorithm (such as feature matching, transformation model, etc.) is used to achieve texture positioning, obtain oral texture matching positioning data, record the position of each area in the oral texture rendering and the corresponding oral tissue area, thereby obtaining oral texture coordinates, and transform and interpolate the texture coordinates of the oral texture rendering to achieve dynamic texture mapping. A texture coordinate interpolation algorithm, such as bilinear interpolation or trilinear interpolation, is used to map the texture coordinates to each vertex or pixel on the surface of the three-dimensional model. The texture obtained by dynamic mapping is applied to the three-dimensional curved surface oral structure model to present the details and features of the oral texture. The dynamic texture mapping model is optimized to improve the quality and effect of texture mapping. Post-processing steps such as texture coordinate correction and noise removal are performed to reduce distortion and artifacts during the mapping process. Texture mapping is further optimized and improved using techniques such as texture smoothing algorithms, texture enhancement algorithms, or texture repair algorithms.

[0097] Step S6: Simulate the dynamic behavior of the oral cavity on the optimized three-dimensional texture mapping model, perform iterative simulation parameter tuning, and construct an oral cavity simulation tuning model to perform virtual molding operations of the oral cavity model.

[0098] In this embodiment, the parameters required for the simulation of oral dynamic behavior are determined according to the characteristics of the oral model and the oral behavior to be simulated. These parameters include the physical properties of oral tissue (such as elasticity, viscosity, etc.), external forces (such as chewing force, tongue movement, etc.) and other parameters related to oral behavior. The oral simulation tuning model and the determined parameters are used to simulate the dynamic behavior of the oral cavity. The deformation, movement and interaction of the oral tissue are simulated using technologies such as computer graphics and physics engines. The external force is applied to the oral model, the response and dynamic behavior of the oral tissue are observed, the results of the oral dynamic behavior simulation are analyzed, and the simulation parameters are tuned as needed. According to the oral behavior characteristics and goals obtained, the simulation parameters are adjusted to better simulate the oral behavior. The parameters are tuned by gradually adjusting the parameter values, adopting optimization algorithms or using feedback control methods. According to the simulation results of the oral dynamic behavior after parameter tuning, an oral simulation tuning model is constructed. This model will contain optimized oral behavior simulation parameters and can more accurately reflect the dynamic behavior of the oral cavity. The oral simulation tuning model is used to perform virtual molding operations of the oral model, including simulation of oral surgery, oral treatment or the use of oral equipment. By simulating the process and results of the molding operation, the effect and performance of the oral model are evaluated, and necessary improvements and optimizations are made.

[0099] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0100] Step S11: Acquire multi-directional oral cavity images;

[0101] Step S12: performing grayscale pixel distribution calculation on the multi-directional oral cavity image to obtain a pixel distribution value;

[0102] Step S13: performing regional brightness difference analysis based on pixel distribution values ​​to generate regional brightness difference data;

[0103] Step S14: performing grayscale uniform remapping on the multi-directional oral cavity image based on the regional brightness difference data to generate a brightness balanced oral cavity image;

[0104] Step S15: performing spline interpolation smoothing processing on the brightness-balanced oral cavity image to construct a super-pixel oral cavity image.

[0105] In this embodiment, each oral image is converted into a grayscale image, and a color image is converted into a grayscale image. The conversion is implemented using a corresponding function in an image processing software or a programming language. The number of pixels at each grayscale level is counted and implemented using a histogram statistical method. The grayscale level is used as the horizontal axis and the number of pixels is used as the vertical axis to draw a histogram. The pixel distribution value of each grayscale level is calculated and obtained by normalizing the histogram or using other statistical methods. The multi-directional oral image is divided into different areas according to the characteristics and needs of the oral structure. For example, the teeth, gums, tongue and other areas are taken as different areas. The pixel distribution values ​​of the corresponding areas are extracted according to the position and range of the areas. The brightness differences between different areas are analyzed using statistical methods (such as mean, variance, etc.) or Other brightness contrast calculation methods adjust the grayscale level of each region according to the brightness difference value in the regional brightness difference data to make the brightness of different regions more uniform, and use the superpixel segmentation algorithm to segment the brightness-balanced oral image. Superpixel segmentation divides the image into regions with similar features, and uses linear or nonlinear grayscale mapping methods to make adjustments based on the specific regional brightness difference data. Spline interpolation smoothes each superpixel region. Spline interpolation uses an interpolation algorithm (such as bicubic interpolation) to smooth each superpixel region to reduce noise and discontinuity. The superpixel region that has been smoothed by spline interpolation is resynthesized into a superpixel oral image, and the superpixel segmentation information is retained as needed, or the superpixel region is remapped to the pixel space of the original image.

[0106] In this embodiment, the specific steps of step S15 are:

[0107] Calculating pixel gradients on the brightness-balanced oral image to obtain a pixel gradient sequence;

[0108] Calculate the gradient amplitude of the pixel gradient sequence to generate the gradient amplitude;

[0109] According to the gradient amplitude, the sharp mutation of the pixel gradient sequence is identified to extract the edge pixels;

[0110] Based on the edge pixels, the non-edge pixel area of ​​the brightness-balanced oral image is annotated to obtain a non-edge pixel area image;

[0111] Perform spline interpolation smoothing processing on the non-edge pixel area image and perform edge contour enhancement processing to obtain an edge contour smoothed image;

[0112] The edge contour smoothed image is reconstructed using super-pixel depth representation to construct a super-pixel oral image.

[0113] In this embodiment, a gradient operator (such as Sobel, Prewitt, etc.) is used to perform a convolution operation on the grayscale image to calculate the gradient value and direction of each pixel point. According to the result of the convolution operation, a pixel gradient sequence is obtained, including the gradient value and direction of each pixel point. According to the gradient value in the pixel gradient sequence, the gradient amplitude (i.e., the modulus of the gradient) of each pixel point is calculated to obtain a gradient amplitude sequence, including the gradient amplitude of each pixel point. According to the numerical characteristics and statistical information in the gradient amplitude sequence, an appropriate threshold is selected, and the pixels above the threshold in the gradient amplitude sequence are marked as edge pixels, the edge pixels are marked as edge areas, and the non-edge pixels are marked as non-edge areas to obtain a non-edge pixel area image, wherein the edge area and the non-edge area are distinguished. The non-edge pixel area image is smoothed using a spline interpolation method to reduce noise and discontinuity, so as to make the image smoother and more continuous. Next, according to the non-edge pixel area image and the position information of the edge pixels, the edge contour is enhanced to make the edge clearer and more obvious. The edge contour smoothed image is segmented using a superpixel segmentation algorithm to obtain a set of superpixel regions. For each superpixel region, its depth representation is calculated. The depth representation is the average depth value, median depth value or other statistic of the pixels in the superpixel region. The pixel depth in the superpixel region is statistically analyzed to calculate the depth representation. The depth representation of each superpixel region is applied to all pixels in the region. The depth representation is applied to each pixel in the superpixel region using an interpolation method (such as bilinear interpolation) or other reconstruction method. The color information of the original edge contour smoothed image and the reconstructed depth information are combined to generate a reconstructed superpixel oral image. A visualization tool (such as image processing software or a programming library) is used to display and save the reconstructed superpixel oral image.

[0114] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0115] Step S21: Performing visual recognition of tissue features on the superpixel oral image and marking each oral tissue feature point;

[0116] Step S22: performing intraoral spatial positioning calculation on each oral tissue feature point to generate a plurality of oral tissue spatial coordinates;

[0117] Step S23: performing a three-dimensional orientation deviation analysis on the super-pixel oral image to obtain an image orientation deviation value;

[0118] Step S24: performing fine deviation correction on multiple oral tissue spatial coordinates based on the image orientation deviation value, thereby obtaining multiple oral tissue precise coordinates.

[0119] In this embodiment, an image segmentation algorithm (such as a SLIC superpixel segmentation algorithm) is used to segment the superpixel oral image to obtain superpixel regions. For each superpixel region, feature points of each oral tissue are extracted. A feature point detection algorithm (such as a Harris corner point detection algorithm or a SIFT feature point detection algorithm) is used to detect the feature points of the oral tissue. The feature points are significant corner points, edge points or texture feature points. The extracted oral tissue feature points are labeled, and each feature point is associated with the corresponding oral tissue. Different colors or symbols are used to mark different oral tissue feature points for subsequent analysis and processing. Based on the labeled oral tissue feature points, intraoral spatial positioning calculation is performed. A three-dimensional reconstruction method in computer vision, such as stereoscopic vision or structured light scanning, is used to map the oral tissue feature points from the image space to the three-dimensional space. The calibration parameters of the intraoral camera and the position information of the oral tissue feature points in the image are used to perform three-dimensional coordinate calculation. A three-dimensional reconstruction algorithm (such as a triangulation method) is used to calculate the coordinates of the oral tissue feature points in the three-dimensional space. For each oral tissue feature point, its corresponding oral tissue spatial coordinates are generated. The oral tissue spatial coordinates are expressed as three-dimensional coordinates (x, y, z), where x, y, and z represent the positions of oral tissue points in three-dimensional space respectively. Stereoscopic vision analysis is performed. The depth information and camera parameters in the super-pixel oral image are used to calculate the stereoscopic orientation deviation of the image. The stereoscopic orientation deviation is expressed as the rotation angle or translation distance of the image. A stereo matching algorithm (such as SIFT matching and optical flow method) is used to match the corresponding points of the super-pixel oral image to obtain the disparity information between the two images. The stereoscopic orientation deviation value of the image is calculated based on the disparity information and camera parameters. The stereoscopic orientation deviation value is used to represent the rotation or translation of the super-pixel oral image relative to the reference image. The image orientation deviation value is used to perform fine deviation correction on the multiple oral tissue spatial coordinates calculated previously. The oral tissue spatial coordinates are corrected according to the image orientation deviation value and the positional relationship between the oral tissue feature points in three-dimensional space. By correcting the oral tissue spatial coordinates, the precise coordinates of multiple oral tissues are obtained, reflecting their accurate positions in three-dimensional space.

[0120] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0121] Step S31: performing multi-directional posture alignment on multiple oral tissue precise coordinates to construct an oral tissue coordinate system;

[0122] Step S32: Performing spatial geometric layout analysis on multiple precise coordinates of oral tissues to generate spatial geometric layout data of feature points;

[0123] Step S33: performing three-dimensional morphological structure fitting on the superpixel oral cavity image based on the feature point spatial geometric layout data to generate a preliminary three-dimensional oral cavity structure model;

[0124] Step S34: Optimizing the overlapping tissue morphology of the preliminary three-dimensional oral structure model based on the oral tissue coordinate system to construct a three-dimensional curved surface oral structure model.

[0125] In this embodiment, multiple precise coordinate data of oral tissues are collected and acquired through an oral scanner, medical imaging equipment or other measurement methods. The collected oral tissue coordinate data are subjected to multi-directional posture alignment, which is achieved through a point cloud registration algorithm (such as an iterative closest point (ICP) algorithm) or other posture alignment algorithm. One of the aligned oral tissue coordinate data is selected as a reference coordinate system to construct an oral tissue coordinate system. A representative tissue is selected as a reference, or a coordinate system is defined based on specific marking points. The coordinate data in the oral tissue coordinate system is used to perform spatial geometric layout analysis on the precise coordinates of multiple oral tissues, including calculating geometric properties such as distances, angles, and curvatures between tissues. Based on the analysis results, appropriate feature points are selected for the description and analysis of the oral structure. These feature points are key points with significant geometric properties or sampling points in a specific area. Feature point spatial geometric layout data is generated, and the coordinates, geometric properties, and associated information of the feature points are combined. The information is organized into a data set or data structure for subsequent three-dimensional morphological structure fitting and optimization. The feature points are located in the super-pixel oral image using the spatial geometric layout data of the feature points. The three-dimensional morphological structure fitting algorithm (such as a surface fitting-based method) is used to fit the three-dimensional morphological structure of the super-pixel oral image according to the located feature points. This is achieved by fitting surfaces or other geometric models. According to the fitting results, a preliminary three-dimensional oral structure model is generated, which includes information such as the shape, position and relative relationship of the oral tissue. The preliminary three-dimensional oral structure model is overlapped with the oral tissue coordinate system. This is achieved by aligning the model with specific points or areas in the coordinate system. According to the overlapping results, the tissue morphology is optimized and adjusted, including operations such as translation, rotation, and scaling of the model to more accurately match the morphology of the oral tissue. Finally, a three-dimensional curved surface oral structure model is obtained. The model provides a geometric representation of the oral structure based on the precise coordinates and morphological characteristics of the oral tissue.

[0126] In this embodiment, the specific steps of step S34 are:

[0127] Based on the oral tissue coordinate system, the tissue structure overlap analysis is performed on each oral tissue feature point to generate a tissue overlap area;

[0128] Conduct tissue structure connection analysis on each oral tissue feature point to obtain the connection relationship of the feature points;

[0129] Based on the connection relationship of feature points, local compatibility constraint analysis is performed on the tissue overlap area to obtain local compatibility data of the overlap area;

[0130] Eliminate overlapping morphology of the preliminary three-dimensional oral structure model based on local compatible data of the overlapping area to generate an overlapping optimized three-dimensional model;

[0131] The overlapping optimized three-dimensional models are subjected to global surface smoothing to construct a three-dimensional surface oral structure model.

[0132] In this embodiment, in the oral tissue coordinate system, a tissue structure coincidence analysis is performed on each oral tissue feature point, and based on the coordinate information of the oral tissue feature points and the geometric shape of the tissue structure, it is determined whether there is an overlapping area between each tissue structure. By analyzing the spatial position and morphological relationship of the tissue structure, a tissue coincidence area, that is, an overlapping area in the oral cavity, is generated. Based on the oral tissue coordinate system, a tissue structure connection analysis is performed on each oral tissue feature point, and based on the coordinates and geometric shape of the feature points, the connection relationship between each feature point is determined, that is, the connection relationship between different tissues is represented. By analyzing the connection relationship of the feature points, the tissue structure between the oral tissues is obtained, and the structural association between the various tissues in the oral cavity is revealed. Based on the position and relationship of the oral tissue feature points, the connection relationship between the feature points is established. According to the connection relationship of the feature points, an organizational structure diagram is constructed, and graph theory or other methods are used to represent and process the connection relationship between the feature points. Analyze the organizational structure chart to determine the hierarchy, connectivity and relative position between organizations. Perform local compatibility constraint analysis based on the connection relationship of feature points and the representation of overlapping areas. For each overlapping area, consider the compatibility between adjacent feature points. Use constraints, optimization algorithms or other methods to determine the local compatibility data of the overlapping area. Eliminate overlapping morphology of the preliminary three-dimensional oral structure model based on the local compatibility data of the overlapping area. Use an overlapping optimization algorithm to adjust the morphology of the overlapping area in the model based on the local compatibility data to make it more consistent with the actual structure of the oral tissue. Perform global surface smoothing on the overlapping optimized three-dimensional oral structure model. Use a smoothing algorithm (such as Laplacian smoothing) to adjust the surface shape of the model to reduce surface irregularities and ensure that the smoothed three-dimensional model maintains a reasonable morphology and continuity in terms of oral tissue structure. Use three-dimensional modeling software or programming library to generate the final three-dimensional curved surface oral structure model.

[0133] In this embodiment, step S4 includes the following steps:

[0134] Step S41: performing inner wall detail texture recognition on the superpixel oral cavity image to obtain oral cavity inner wall detail texture data;

[0135] Step S42: performing texture contour quantitative analysis on the oral cavity inner wall detail texture data to extract texture contour feature parameters;

[0136] Step S43: abstracting the microscopic oral texture of the superpixel oral image based on the texture contour feature parameters, thereby generating an oral texture feature vector;

[0137] Step S44: Performing texture color subtle rendering on the oral texture feature vector to generate an oral texture rendering image.

[0138] In this embodiment, the inner wall detail texture is recognized for the superpixel oral image, and a texture feature extraction method (such as local binary pattern, gray level co-occurrence matrix, etc.) is used to capture the texture information in the image. For each superpixel area, the inner wall detail texture feature is calculated, and the statistics of the texture feature (such as mean, variance, energy, etc.) are calculated or other texture descriptors (such as Gabor filter response) are used to associate the inner wall detail texture feature with the corresponding superpixel area to obtain the inner wall detail texture data of the oral image, and the texture contour is quantitatively analyzed for the inner wall detail texture data of the oral cavity. The texture contour is extracted by an edge detection algorithm (such as Canny edge detection), and the extracted texture contour is parameterized and analyzed. The characteristic parameters of the contour, such as the length, curvature, and number of straight line segments, are calculated, and the characteristic parameters of the texture contour are extracted for subsequent texture abstraction and rendering. Based on the texture contour characteristic parameters, Abstract the microscopic oral texture of the superpixel oral image, adjust the texture information in the superpixel area according to the characteristic parameters of the texture contour, use filters, interpolation methods or other texture operation techniques to achieve texture abstraction, retain information related to the oral texture features during the abstraction process, and reduce noise or irrelevant texture details to generate an oral texture feature vector, in which each element represents the texture feature of a superpixel area, perform subtle texture color rendering on the oral texture feature vector to generate an oral texture rendering image, adjust the texture color of the corresponding superpixel area according to each element of the oral texture feature vector, use color mapping methods (such as linear mapping, color table, etc.) to map the texture feature values ​​to a suitable color space to achieve visual rendering of the texture, and combine other information of the superpixel oral image (such as edge contour, color information, etc.) to generate an oral texture rendering image.

[0139] In this embodiment, step S5 includes the following steps:

[0140] Step S51: performing texture positioning on the oral texture rendering image based on the oral tissue coordinate system to obtain oral texture matching positioning data;

[0141] Step S52: dynamically texture mapping the oral texture rendering image to the three-dimensional curved surface oral structure model based on the oral texture matching positioning data to generate a three-dimensional oral texture mapping model;

[0142] Step S53: Optimizing the texture level of the three-dimensional oral cavity texture mapping model to obtain an optimized three-dimensional texture mapping model.

[0143] In this embodiment, texture positioning is performed on the oral texture rendering image based on the oral tissue coordinate system. The oral tissue coordinate system is a coordinate system defined according to a specific anatomical structure or reference point. According to the reference point or mark of the oral tissue coordinate system, the oral texture rendering image is mapped to the corresponding oral tissue area. An image registration algorithm (such as feature matching, transformation model, etc.) is used to achieve texture positioning, and oral texture matching positioning data is obtained. The position of each area in the oral texture rendering image and the corresponding oral tissue area are recorded. Based on the oral texture matching positioning data, the oral texture rendering image is mapped to the corresponding three-dimensional curved surface oral structure model. For each oral tissue area, the texture in the oral texture rendering image is mapped to the corresponding three-dimensional curved surface oral structure model according to the oral texture matching positioning data. On the three-dimensional surface, a texture mapping algorithm (such as map mapping, UV mapping, etc.) is used to combine the texture information in the oral texture rendering image with the geometric structure of the three-dimensional surface to achieve dynamic texture mapping and generate a three-dimensional oral texture mapping model, in which each three-dimensional surface oral structure has a texture that matches the oral texture rendering image. The generated three-dimensional oral texture mapping model is texture-optimized, and a texture compression algorithm or optimization method is used to reduce the storage space of texture data and improve rendering efficiency. According to needs, texture resolution adjustment, texture smoothing, texture edge optimization and other operations are performed to improve the quality and performance of texture mapping, and finally an optimized three-dimensional texture mapping model is obtained, in which texture information is processed and optimized to meet application requirements.

[0144] In this embodiment, step S6 includes the following steps:

[0145] Step S61: performing oral dynamic behavior simulation on the optimized three-dimensional texture mapping model to generate dynamic behavior simulation data;

[0146] Step S62: performing phase change trajectory analysis on the oral behavior simulation data to generate an oral phase change trajectory;

[0147] Step S63: performing nonlinear interaction analysis between tissues on the oral stage change trajectory to obtain oral tissue nonlinear interaction data;

[0148] Step S64: iteratively tuning the simulation parameters of the optimized three-dimensional texture mapping model according to the oral tissue nonlinear interaction data, and constructing an oral simulation tuning model to perform virtual molding operations of the oral model.

[0149] In this embodiment, an optimized three-dimensional texture mapping model is used as the initial state to simulate the dynamic behavior of the oral cavity. According to the physiological characteristics and movement laws of the oral cavity, corresponding mechanical or physical simulation methods are applied to simulate the dynamic behavior of the oral cavity. For example, finite element analysis, particle system, particle system and other methods are used. During the simulation process, the deformation, movement and interaction of the oral tissue are considered to make the simulation results more realistic and accurate. The dynamic behavior simulation data of the oral cavity is generated, the state and behavior of the oral model at different time steps are recorded, the oral behavior simulation data is divided into stages, the dynamic behavior of the oral cavity is divided into different stages, the changes and characteristics of the oral tissue in each stage of the oral behavior simulation data are analyzed, and the key features or indicators in the oral behavior simulation data, such as oral morphology, deformation degree, movement trajectory, etc., are extracted to generate the oral stage change trajectory, record the changes and evolution of the oral tissue in the oral behavior simulation data at different stages, and organize the oral stage change trajectory. Nonlinear interaction analysis between tissues, considering the mutual influence and action between oral tissues, analyzing the correlation and nonlinear interaction between different tissues in the oral stage change trajectory, using statistical analysis methods, machine learning algorithms, etc. to explore the relationship and action mode of oral tissues, obtain oral tissue nonlinear interaction data, record the nonlinear interaction relationship between different tissues in the oral stage change trajectory, and iteratively tune the simulation parameters of the optimized three-dimensional texture mapping model according to the nonlinear interaction data of oral tissues. According to the requirements of the oral simulation tuning model, adjust the oral simulation parameters, such as tissue stiffness, friction coefficient, simulation time step, etc., to improve the accuracy and authenticity of the simulation results. Perform multiple iterative simulation parameter tuning until the performance and effect requirements of the oral simulation tuning model are met, and construct an oral simulation tuning model, which includes an iteratively tuned three-dimensional texture mapping model and optimized simulation parameters, which is used to perform virtual molding operations of the oral model.

[0150] In this embodiment, a molding device for an oral prosthesis model is provided, which is used to perform the molding method for an oral prosthesis model as described above, comprising:

[0151] An interpolation and smoothing module is used to obtain multi-directional oral images; perform spline interpolation and smoothing processing on the multi-directional oral images to construct super-pixel oral images;

[0152] The spatial positioning module is used to annotate each oral tissue feature point based on the superpixel oral image; perform intraoral spatial positioning calculations on each oral tissue feature point to obtain multiple precise coordinates of oral tissues;

[0153] A three-dimensional morphological structure module is used to construct an oral tissue coordinate system based on multiple precise coordinates of oral tissues; perform three-dimensional morphological structure fitting on multiple precise coordinates of oral tissues to construct a three-dimensional curved surface oral structure model;

[0154] Texture abstraction module, used to perform quantitative texture contour analysis on superpixel oral images, abstract microscopic oral textures, and generate oral texture renderings;

[0155] A dynamic texture mapping module is used to dynamically texture map the oral texture rendering image to the three-dimensional curved oral structure model based on the oral tissue coordinate system to obtain an optimized three-dimensional texture mapping model;

[0156] The parameter tuning module is used to simulate the dynamic behavior of the oral cavity for the optimized three-dimensional texture mapping model, perform iterative simulation parameter tuning, and construct an oral cavity simulation tuning model to perform virtual molding operations of the oral cavity model.

[0157] The present invention smoothes multi-directional oral images through spline interpolation smoothing, reduces noise and discontinuity in the images, and constructs super-pixel oral images, which helps to improve the consistency and continuity of the oral model and provide a more stable data basis for subsequent steps. The spatial positioning module is used to mark the characteristic points of each oral tissue and perform spatial positioning calculations in the oral cavity to obtain the precise coordinates of each oral tissue. The positioning of these oral tissue characteristic points helps in the subsequent steps of oral structure modeling and texture mapping. Based on the precise coordinates of the oral tissue, the three-dimensional morphological structure module is used to construct the oral tissue coordinate system and perform three-dimensional morphological structure fitting. The geometric shape and spatial structure of the oral tissue are established through the three-dimensional morphological structure module, which provides accurate geometric information for the construction of the oral model in the subsequent steps. The texture abstraction module is used to construct the super-pixel oral The image is quantitatively analyzed for texture contours, and the microscopic oral texture is abstracted to generate an oral texture rendering. This extracts the texture features of the inner wall of the oral cavity and abstracts it into a form that can be calculated and rendered, providing richer data for texture mapping and visualization of the oral model. The dynamic texture mapping module dynamically maps the oral texture rendering to the three-dimensional curved oral structure model based on the oral tissue coordinate system. This accurately corresponds the oral texture rendering to the oral structure model, making the texture mapping of the oral model more realistic and accurate. The parameter tuning module simulates the dynamic behavior of the oral cavity on the optimized three-dimensional texture mapping model, and performs iterative simulation parameter tuning. Through the oral simulation tuning model, the dynamic behavior and changes of the oral cavity are simulated, the morphology and texture mapping of the oral model are optimized, and the oral prosthesis model is made more in line with the actual situation.

[0158] Therefore, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the above description. Therefore, all changes that fall within the meaning and range of equivalent elements of the application documents are intended to be included in the present invention.

[0159] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for forming an oral prosthesis model, characterized in that: The following steps are involved: Step S1: acquiring a multi-directional oral image; performing spline interpolation smoothing processing on the multi-directional oral image to construct a super-pixel oral image; Step S2: annotating each oral tissue feature point based on the superpixel oral image; Perform spatial positioning calculations on each oral tissue feature point in the oral cavity to obtain multiple precise coordinates of oral tissues; Step S3: constructing an oral tissue coordinate system based on multiple oral tissue precise coordinates; Perform three-dimensional morphological structure fitting on the precise coordinates of multiple oral tissues to construct a three-dimensional curved oral structure model; Step S4: quantitatively analyzing the texture contour of the superpixel oral image, and abstracting the microscopic oral texture to generate an oral texture rendering; Step S5: dynamically texture mapping the oral texture rendering image to the three-dimensional curved oral structure model based on the oral tissue coordinate system to obtain an optimized three-dimensional texture mapping model; Step S6: simulating the dynamic behavior of the oral cavity on the optimized three-dimensional texture mapping model, and performing iterative simulation parameter tuning to construct an oral cavity simulation tuning model to perform a virtual molding operation of the oral cavity model; The specific steps of step S6 are: Step S61: performing oral dynamic behavior simulation on the optimized three-dimensional texture mapping model to generate dynamic behavior simulation data; Step S62: performing phase change trajectory analysis on the oral behavior simulation data to generate an oral phase change trajectory; Step S63: performing nonlinear interaction analysis between tissues on the oral stage change trajectory to obtain oral component nonlinear interaction data; Step S64: Iteratively tune the simulation parameters of the optimized three-dimensional texture mapping model according to the nonlinear interaction data of the oral components, and construct an oral simulation tuning model to perform virtual molding operations of the oral model. The iterative simulation parameter tuning specifically includes: adjusting the oral simulation parameters, including tissue stiffness, friction coefficient and simulation time step.

2. The method for forming an oral prosthesis model according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: Acquire multi-directional oral cavity images; Step S12: performing grayscale pixel distribution calculation on the multi-directional oral cavity image to obtain a pixel distribution value; Step S13: performing regional brightness difference analysis based on pixel distribution values ​​to generate regional brightness difference data; Step S14: performing grayscale uniform remapping on the multi-directional oral cavity image based on the regional brightness difference data to generate a brightness balanced oral cavity image; Step S15: performing spline interpolation smoothing processing on the brightness-balanced oral cavity image to construct a super-pixel oral cavity image.

3. The method for forming an oral prosthesis model according to claim 2, characterized in that: The specific steps of step S15 are: Calculating pixel gradients on the brightness-balanced oral image to obtain a pixel gradient sequence; Calculate the gradient amplitude of the pixel gradient sequence to generate the gradient amplitude; According to the gradient amplitude, the sharp mutation of the pixel gradient sequence is identified to extract the edge pixels; Based on the edge pixels, the non-edge pixel area of ​​the brightness-balanced oral image is annotated to obtain a non-edge pixel area image; Perform spline interpolation smoothing processing on the non-edge pixel area image and perform edge contour enhancement processing to obtain an edge contour smoothed image; The edge contour smoothed image is reconstructed using super-pixel depth representation to construct a super-pixel oral image.

4. The method for forming an oral prosthesis model according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: Performing visual recognition of tissue features on the superpixel oral image and marking each oral tissue feature point; Step S22: performing intraoral spatial positioning calculation on each oral tissue feature point to generate a plurality of oral tissue spatial coordinates; Step S23: performing a three-dimensional orientation deviation analysis on the super-pixel oral image to obtain an image orientation deviation value; Step S24: performing fine deviation correction on multiple oral tissue spatial coordinates based on the image orientation deviation value, thereby obtaining multiple oral tissue precise coordinates.

5. The method for forming an oral prosthesis model according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: performing multi-directional posture alignment on multiple oral tissue precise coordinates to construct an oral tissue coordinate system; Step S32: Performing spatial geometric layout analysis on multiple precise coordinates of oral tissues to generate spatial geometric layout data of feature points; Step S33: performing three-dimensional morphological structure fitting on the superpixel oral cavity image based on the feature point spatial geometric layout data to generate a preliminary three-dimensional oral cavity structure model; Step S34: Optimizing the overlapping tissue morphology of the preliminary three-dimensional oral structure model based on the oral tissue coordinate system to construct a three-dimensional curved surface oral structure model.

6. The method for forming an oral prosthesis model according to claim 5, characterized in that: The specific steps of step S34 are: Based on the oral tissue coordinate system, the tissue structure component coincidence analysis is performed on each oral tissue feature point to generate a tissue coincidence area; Conduct tissue structure connection analysis on each oral tissue feature point to obtain the connection relationship of the feature points; Based on the connection relationship of feature points, local compatibility constraint analysis is performed on the tissue overlap area to obtain local compatibility data of the overlap area; Eliminate overlapping morphology of the preliminary three-dimensional oral structure model based on local compatible data of the overlapping area to generate an overlapping optimized three-dimensional model; The overlapping optimized three-dimensional models are subjected to global surface smoothing to construct a three-dimensional surface oral structure model.

7. The method for forming an oral prosthesis model according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: performing inner wall detail texture recognition on the superpixel oral cavity image to obtain oral cavity inner wall detail texture data; Step S42: performing texture contour quantitative analysis on the oral cavity inner wall detail texture data to extract texture contour feature parameters; Step S43: abstracting the microscopic oral texture of the superpixel oral image based on the texture contour feature parameters, thereby generating an oral texture feature vector; Step S44: Performing texture color subtle rendering on the oral texture feature vector to generate an oral texture rendering image.

8. The method for forming an oral prosthesis model according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: performing texture positioning on the oral texture rendering image based on the oral tissue coordinate system to obtain oral texture matching positioning data; Step S52: dynamically texture mapping the oral texture rendering image to the three-dimensional curved surface oral structure model based on the oral texture matching positioning data to generate a three-dimensional oral texture mapping model; Step S53: Optimizing the texture level of the three-dimensional oral cavity texture mapping model to obtain an optimized three-dimensional texture mapping model.

9. A molding device for an oral prosthesis model, characterized in that: The method for forming the oral prosthesis model according to claim 1 comprises: An interpolation and smoothing module is used to obtain multi-directional oral images; perform spline interpolation and smoothing processing on the multi-directional oral images to construct super-pixel oral images; The spatial positioning module is used to annotate each oral tissue feature point based on the superpixel oral image; perform intraoral spatial positioning calculations on each oral tissue feature point to obtain multiple precise coordinates of oral tissues; A three-dimensional morphological structure module is used to construct an oral tissue coordinate system based on multiple precise coordinates of oral tissues; perform three-dimensional morphological structure fitting on multiple precise coordinates of oral tissues to construct a three-dimensional curved surface oral structure model; Texture abstraction module, used to perform quantitative texture contour analysis on superpixel oral images, abstract microscopic oral textures, and generate oral texture renderings; A dynamic texture mapping module is used to dynamically texture map the oral texture rendering image to the three-dimensional curved oral structure model based on the oral tissue coordinate system to obtain an optimized three-dimensional texture mapping model; The parameter tuning module is used to simulate the dynamic behavior of the oral cavity for the optimized three-dimensional texture mapping model, perform iterative simulation parameter tuning, and construct an oral cavity simulation tuning model to perform virtual molding operations of the oral cavity model.

Images