WO2022001001A1 - 一种3d牙模牙龈线的识别方法、系统、装置和存储介质 - Google Patents

一种3d牙模牙龈线的识别方法、系统、装置和存储介质 Download PDF

Info

Publication number
WO2022001001A1
WO2022001001A1 PCT/CN2020/134573 CN2020134573W WO2022001001A1 WO 2022001001 A1 WO2022001001 A1 WO 2022001001A1 CN 2020134573 W CN2020134573 W CN 2020134573W WO 2022001001 A1 WO2022001001 A1 WO 2022001001A1
Authority
WO
WIPO (PCT)
Prior art keywords
dental mold
feature
dental
reference line
fitting
Prior art date
Application number
PCT/CN2020/134573
Other languages
English (en)
French (fr)
Inventor
王勇
冯伟
Original Assignee
广州黑格智造信息科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 广州黑格智造信息科技有限公司 filed Critical 广州黑格智造信息科技有限公司
Priority to EP20942870.5A priority Critical patent/EP4167125A1/en
Publication of WO2022001001A1 publication Critical patent/WO2022001001A1/zh
Priority to US18/072,732 priority patent/US20230089649A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61C—DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE
    • A61C7/00—Orthodontics, i.e. obtaining or maintaining the desired position of teeth, e.g. by straightening, evening, regulating, separating, or by correcting malocclusions
    • A61C7/002—Orthodontic computer assisted systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/10—Pre-processing; Data cleansing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/149—Segmentation; Edge detection involving deformable models, e.g. active contour models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/469—Contour-based spatial representations, e.g. vector-coding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/64—Three-dimensional objects
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61C—DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE
    • A61C7/00—Orthodontics, i.e. obtaining or maintaining the desired position of teeth, e.g. by straightening, evening, regulating, separating, or by correcting malocclusions
    • A61C7/002—Orthodontic computer assisted systems
    • A61C2007/004—Automatic construction of a set of axes for a tooth or a plurality of teeth
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30036—Dental; Teeth

Definitions

  • the present invention relates to the technical field of orthodontics, and in particular, to a method, system, device and storage medium for identifying a 3D dental mold gum line.
  • Dental care is an unavoidable problem for most people. With the improvement of computer software and hardware technology and the emergence of more and more sophisticated dental data, people also turn their attention from traditional pure artificial dental care to digital dental care such as invisible Orthodontic dental diagnosis and treatment, with the help of prior knowledge provided by high-tech digital technology, improve the safety and success rate of dental treatment.
  • the technical solution of the present application aims at the technical problems of low automation, low efficiency and poor user experience in tooth model data processing in the process of orthodontic automation in China. Based on the improvement of efficiency, it innovatively explores the combination of the dental field and 3D printing technology.
  • the digital 3D printing technology is integrated into the dental restoration process.
  • the gum line data is automatically identified, reducing manpower, deepening digital production, and filling in the dental model data processing in the process of orthodontic.
  • Low automation and low efficiency The vacancy technology with poor user experience lays a solid foundation for the subsequent application scenarios of the combination of dentistry and 3D technology.
  • the purpose of the present invention is to provide a method, system, device and storage medium for identifying the gum line of a 3D dental mold.
  • the first technical scheme adopted in the present invention is:
  • a method for identifying a 3D dental mold gum line comprising the following steps:
  • the initial fitting curve is smoothed by a dimensionality reduction algorithm, and the gum line is output.
  • the preprocessing includes filtering or denoising, and extracting a plurality of feature points from the 3D dental mold based on a curvature geometry algorithm, and preprocessing each of the feature points to output a set of feature contour points specifically includes: The following steps:
  • the feature points are distributed in the concave and convex regions of the 3D dental mold;
  • a feature contour point group is generated.
  • the morphological parameters include the shape of the 3D dental mold, and the step of matching the first fitting reference line from the pre-stored fitting reference line pool according to the morphological parameters specifically includes the following steps:
  • the shape of the 3D dental mold determine the direction of the 3D dental mold
  • the feature contour points with the same direction of the current dental mold feature contour are matched from the pre-stored fitting reference line pool;
  • the first fitting reference line is screened from the feature contour points in the same direction in combination with the pre-built coordinate system and the first threshold.
  • the step of performing an iterative operation on the first fitting reference line based on the feature contour point group to generate an initial fitting curve specifically includes the following steps:
  • An approximate iterative algorithm is used to iteratively fit the first fitting reference line and each feature point of the feature contour point group to generate an initial fitting curve.
  • the dimensionality reduction algorithm includes a principal component analysis method, and the dimensionality reduction algorithm is used to smooth the initial fitting curve, and the step of outputting the gum line specifically includes the following steps:
  • the initial fitting curve is smoothed by using the principal component analysis method, and the main direction point of the initial fitting curve is determined;
  • the step of aligning the 3D dental mold to the target position specifically includes the following steps:
  • the 3D dental mold is rotated to the target position.
  • the second technical scheme adopted by the present invention is:
  • a 3D dental model gum line identification system comprising:
  • the extraction module is used to extract a plurality of feature points based on the curvature geometry algorithm for the 3D dental mold, and preprocess each of the feature points to output a feature contour point group;
  • the matching module is used to match the first fitting reference line from the pre-stored fitting reference line pool according to the morphological parameters
  • an iterative module configured to perform an iterative operation on the first fitting reference line based on the feature contour point group to generate an initial fitting curve
  • the output module is used for smoothing the initial fitting curve using a dimensionality reduction algorithm, and outputting the gum line.
  • the extraction module includes:
  • the identification unit is used to correct the 3D dental mold to the target position after identifying the morphological parameters and the maximum bottom surface of the 3D dental mold;
  • an extraction unit used for extracting a plurality of feature points from the 3D dental mold at the target position by using a curvature geometry algorithm, and the feature points are distributed in the concave-convex area of the 3D dental mold;
  • the generating unit is configured to generate a feature contour line point group after filtering or denoising each of the extracted feature points.
  • the identifying unit includes:
  • the acquisition subunit is used to acquire a 3D dental mold, identify the maximum bottom surface and morphological parameters of the 3D dental mold, and output the normal vector of the largest bottom surface;
  • a first rotation subunit for rotating the 3D dental mold to a target plane in combination with the normal vector of the maximum bottom surface and a preset first normal vector
  • the output subunit is used to obtain the contour of the 3D dental mold on the target plane, determine the tooth skeleton curve equation according to the contour, and output the direction vector of the 3D dental mold;
  • the second rotation subunit is used for rotating the 3D dental mold to a target position by combining the direction vector of the 3D dental mold and a preset second normal vector.
  • the matching module includes:
  • a determining unit for determining the direction of the 3D dental mold according to the shape of the 3D dental mold
  • a matching unit for matching the feature contour points with the same direction of the current dental mold feature contour from the pre-stored fitting reference line pool based on the direction of the 3D dental mold;
  • the screening unit is used for screening out the first fitting reference line from the feature contour points in the same direction in combination with the pre-built coordinate system and the first threshold.
  • the iteration module includes:
  • a superimposing unit for geometrically superimposing the barycenter of the first fitting reference line and the barycenter of the feature contour point group based on a pre-built coordinate system
  • An iterative unit configured to iteratively fit the first fitting reference line with each feature point of the feature contour point group by using an approximate iterative algorithm to generate an initial fitting curve.
  • the output module includes:
  • a smoothing unit used for smoothing the initial fitting curve by using the principal component analysis method, and determining the main direction point of the initial fitting curve
  • the smoothing unit is used for smoothly connecting the smoothed initial fitting curve to the main direction points of the initial fitting curve according to the interpolation spline, and outputting the gum line.
  • the third technical scheme adopted by the present invention is:
  • An apparatus includes a memory for storing at least one program, and a processor for loading the at least one program to perform the above-described method.
  • the fourth technical scheme adopted by the present invention is:
  • Fig. 1 is a kind of step flow chart of the identification method of 3D dental mold gum line of the present invention
  • FIG. 2 is a structural block diagram of a recognition system for a 3D dental mold gum line of the present invention
  • FIG. 3 is a schematic flowchart of the overall method of the 3D dental mold gum line provided by the present invention.
  • the present embodiment provides a method for identifying the gum line of a 3D dental mold, including the following steps:
  • the 3D dental model that is, the 3D dental model
  • the 3D dental model is a tooth model with a corresponding plane which is processed and restored based on 3D printing technology and computer programs.
  • the curvature geometry algorithm is the rotation rate of the tangential direction angle of a certain surface on the 3D dental mold to the arc length, indicating the degree of concavity and convexity of the surface.
  • the first fitting reference line is the same as the direction of the feature point (the direction of the 3D dental mold), ensuring that the range of the optimal contour line can cover the feature point area.
  • the 3D dental mold is adjusted to the target position; then, multiple feature points are extracted from the 3D dental mold at the target position according to the curvature geometry algorithm; according to the identified 3D dental mold
  • the morphological parameters of the dental mold are matched with the characteristic contour line with the smallest deviation from the pre-stored fitting reference line pool as the first fitting reference line; the first fitting reference line is iteratively calculated according to multiple feature points to generate the initial fitting
  • the dimensionality reduction algorithm is used to smooth the initial fitting curve, output the final gum line, and complete the preprocessing of the 3D dental model data.
  • the technical solution of the present application proposes a method that can greatly simplify the automatic generation and processing of dental orthodontics.
  • Process reduce work costs, shorten the data processing time of dental model data, improve work efficiency, and enhance the user experience of 3D dental model gum line identification method, and at the same time establish the application scene of the combination of dental treatment and 3D technology, filling the domestic orthodontic correction. of automated machining processes.
  • the method for identifying the gum line of the 3D dental model provided in this embodiment is also applicable to tooth models with arbitrary planes and directions, and any other types of tooth models with planes do not affect the implementation of the present invention.
  • the preprocessing includes filtering or denoising
  • the step S1 specifically includes the following steps:
  • a feature contour is generated and stored in a feature contour pool.
  • the obtained initial 3D dental model feature points are denoised or filtered to eliminate the influence of the feature points in the non-gingival line area on the fitting of subsequent contour lines;
  • the curvature geometry algorithm refers to a certain surface on the dental mold
  • the rotation rate of the tangential direction angle to the arc length indicates the degree of concavity and convexity of the surface, which is called a feature in the solution of this application, and feature points can be extracted from the concave and convex area of the 3D dental mold by the curvature method.
  • step of S11 includes the following steps:
  • the preset first normal vector is the normal vector corresponding to the rotation of the 3D dental mold to the target plane
  • the preset second normal vector is the normal vector corresponding to the rotation of the 3D dental mold to the target position.
  • the morphological parameters include the shape of the 3D dental mold, and the step of S2 specifically includes the following steps:
  • the coordinate system is a rectangular coordinate system with X, Y, and Z axes, and other coordinate systems may also be selected according to application scenarios, which will not be described here.
  • the first threshold refers to a value that minimizes the deviation between the matched feature contour in the same direction and the 3D dental mold in the established coordinate system.
  • the characteristic contour line refers to a tooth's gum line file, which consists of point coordinates; the fitting reference pool is actually the smoothed historical gum line, and these gum lines are generated based on other dental models.
  • step of S3 specifically includes the following steps:
  • the approximate iterative algorithm means that after the first fitting reference line is projected, the cyclic iteration means that the projection error is smaller than the set threshold.
  • the first fitting reference line is The center of gravity of a fitting reference line is combined with the center of gravity of the line connecting each feature point.
  • the initial fitting line is formed by connecting the projected points to ensure that the optimal feature contour line can cover the feature points. area.
  • the dimensionality reduction algorithm includes principal component analysis, and the step of S4 specifically includes the following steps:
  • the generated initial fitting line is not a smooth curve, and there will be local folding and deviation phenomena.
  • principal component analysis is used to obtain its main contour shape, Determine the points of the main direction of the contour, and use interpolation splines such as Kochanek-Bartels style to reconnect them smoothly to avoid the unsmooth area of the line segment, and obtain the final desired smooth gum line.
  • this embodiment provides a 3D dental model gum line recognition system, including:
  • the extraction module is used to extract a plurality of feature points based on the curvature geometry algorithm for the 3D dental mold, and preprocess each of the feature points to output a feature contour point group;
  • the matching module is used to match the first fitting reference line from the pre-stored fitting reference line pool according to the morphological parameters
  • an iterative module configured to perform an iterative operation on the first fitting reference line based on the feature contour point group to generate an initial fitting curve
  • the output module is used for smoothing the initial fitting curve using a dimensionality reduction algorithm, and outputting the gum line.
  • the extraction module includes:
  • the identification unit is used to correct the 3D dental mold to the target position after identifying the morphological parameters and the maximum bottom surface of the 3D dental mold;
  • an extraction unit used for extracting a plurality of feature points from the 3D dental mold at the target position by using a curvature geometry algorithm, and the feature points are distributed in the concave-convex area of the 3D dental mold;
  • the generating unit is configured to generate a feature contour line point group after filtering or denoising each of the extracted feature points.
  • the identifying unit includes:
  • the acquisition subunit is used to acquire a 3D dental mold, identify the maximum bottom surface and morphological parameters of the 3D dental mold, and output the normal vector of the largest bottom surface;
  • a first rotation subunit for rotating the 3D dental mold to a target plane in combination with the normal vector of the maximum bottom surface and a preset first normal vector
  • the output subunit is used to obtain the contour of the 3D dental mold on the target plane, determine the tooth skeleton curve equation according to the contour, and output the direction vector of the 3D dental mold;
  • the second rotation subunit is used for rotating the 3D dental mold to a target position by combining the direction vector of the 3D dental mold and a preset second normal vector.
  • the matching module includes:
  • a determining unit for determining the direction of the 3D dental mold according to the shape of the 3D dental mold
  • a matching unit for matching the feature contour points with the same direction of the current dental mold feature contour from the pre-stored fitting reference line pool based on the direction of the 3D dental mold;
  • the screening unit is used for screening out the first fitting reference line from the feature contour points in the same direction in combination with the pre-built coordinate system and the first threshold.
  • the iteration module includes:
  • a superimposing unit for geometrically superimposing the barycenter of the first fitting reference line and the barycenter of the feature contour point group based on a pre-built coordinate system
  • An iterative unit configured to iteratively fit the first fitting reference line with each feature point of the feature contour point group by using an approximate iterative algorithm to generate an initial fitting curve.
  • the output module includes:
  • a smoothing unit used for smoothing the initial fitting curve by using the principal component analysis method, and determining the main direction point of the initial fitting curve
  • the smoothing unit is used for smoothly connecting the smoothed initial fitting curve to the main direction points of the initial fitting curve according to the interpolation spline, and outputting the gum line.
  • An apparatus with a memory for storing at least one program and a processor for loading the at least one program to perform a method embodiment method.
  • a device in this embodiment can execute a method for identifying a 3D dental mold gum line provided by the method embodiment of the present invention, and can execute any combination of implementation steps of the method embodiment, and has corresponding functions and beneficial effects of the method.
  • the storage medium of this embodiment can execute a method for identifying a 3D dental model gum line provided by the method embodiment of the present invention, can execute any combination of the implementation steps of the method embodiment, and has corresponding functions and beneficial effects of the method. .
  • 3 is a schematic flowchart of the overall method of the 3D dental mold gum line provided by the present invention, including the following:
  • the tooth model is a digital three-dimensional body composed of a series of triangular facets.
  • the method of detecting the maximum plane of the tooth is: set a certain triangular face, superimpose the set triangular face and the 3D tooth model composed of the triangular face, and set the error threshold e, when e is greater than a certain value, it is considered that the set triangular face and the face on the 3D tooth model are not flat; otherwise, it is considered to be in the same plane.
  • the set triangular face and a certain face of the tooth model are on the same plane, superimpose the two together, and continue to search for the next triangular face and judge the error threshold. The above steps are repeated until the largest plane of the tooth model is obtained. In the process of detecting the maximum plane of the tooth model, the equation of its plane can be obtained.
  • the rotation angle and the rotation axis are solved according to the vector values before and after the rotation.
  • the cross product operation method is a binary operation of a vector in a vector space, and the operation result is a vector rather than a scalar; From the above rotation angle and its rotation axis, any model can be rotated to the desired spatial position.
  • the feature points of the 3D dental model are extracted based on the curvature geometry algorithm.
  • the rotation rate of the tangent direction angle of each surface to the arc length indicates the degree of concavity and convexity of the surface, which is also called feature in this scheme.
  • the feature points of the concave and convex area of the dental mold can be obtained by the curvature method (the real gum line on the dental mold is also determined by concave and convex).
  • the feature contour point group contains a plurality of remaining feature points after optimization, and the distribution shape of the feature points in the feature contour point group ( Referred to as feature contour point group shape) will approximate the gum line contour of the dental mold.
  • the center of gravity of the feature contour point group can be understood as the center of gravity of the shape of the feature contour point group.
  • the optimal fitting reference line is automatically selected.
  • the optimal fitting reference line is automatically selected through the placed dental mold.
  • the fitting reference line refers to the gum line file of a tooth.
  • the main method of searching for the best fitting reference line is: first, match the same batch of tooth fitting reference line data in the same direction according to the direction of the dental mold; secondly, from the filtered data in the same direction, according to X , Y, Z three directions to determine the matching degree between the fitting reference line and the dental mold, and select the fitting reference line with the smallest deviation, that is, the optimal fitting reference line.
  • the feature points and the optimal fitting reference line are obtained at the same time, and the fitting reference line needs to be superimposed or drawn closer to the feature points as much as possible, that is, the center of gravity of the fitting reference line is in the three directions of X, Y, and Z.
  • Translate to coincide with the center of gravity of the dental mold preferably, make the center of gravity of the fitting reference line coincide with the center of gravity of the shape of the feature contour point group, and at the same time ensure that the fitting reference line can cover the feature point area;
  • (2) Use the approximate iterative algorithm to Fitting the reference line and the feature points of the feature contour point group to form an initial fitting line, wherein the fitting is to project the points of the fitting reference line (essentially a series of coordinate points) to the closest feature point.
  • Approximate iteration means that after the contour line is projected, continue to iterate until the projection error is less than the set threshold; (3) After the iteration is completed, connect the projected points to form the initial fitting line.
  • the initial fitting line is obtained. Since the initial fitting line is not a smooth curve, there will be local folding and deviation. In view of this situation, this scheme uses the principal component analysis method to obtain its main contour shape, and determines the main contour shape. Direction points, and reconnect them smoothly using the Kochanek-Bartels style, avoiding the unsmooth areas of the line segments, and getting the final desired smooth gum line.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Dentistry (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Epidemiology (AREA)
  • Multimedia (AREA)
  • Software Systems (AREA)
  • Dental Tools And Instruments Or Auxiliary Dental Instruments (AREA)
  • Image Processing (AREA)

Abstract

一种3D牙模牙龈线的识别方法、系统、装置和存储介质，其中方法包括对3D牙模基于曲率几何算法提取多个特征点，并对各所述特征点预处理，输出特征轮廓点组（S1）；根据形态参数从预存的拟合参考线池中匹配出第一拟合参考线（S2）；基于特征轮廓点组对所述第一拟合参考线进行迭代运算，生成初始拟合曲线（S3）；采用降维算法对所述初始拟合曲线进行平滑处理，输出牙龈线（S4）。

Description

一种3D牙模牙龈线的识别方法、系统、装置和存储介质
相关申请的交叉引用
本申请基于申请号为202010634000.2、申请日为2020年07月02日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本发明涉及牙齿矫正技术领域，尤其涉及一种3D牙模牙龈线的识别方法、系统、装置和存储介质。
背景技术
术语解释：
隐形正畸(Invisible Orthodontic)：指隐形无托槽矫正，是牙齿矫正的一种。
随着科技信息的发展，计算机技术、制造技术、数字建模技术、材料科学、数控技术等技术迅速发展壮大以及这些学科相互之间的融合，尤其计算机技术已经越来越多地渗透于医学各领域的教学、科研和临床应用等各个方面而且能够实现更具进步的互相合作。而随着测量技术的发展及普及，人们能够很方便地获取数字化牙齿模型，而这在口腔临床诊断和医治过程中起着重要作用。3D打印技术的出现与发展已成为现在的热门之一，3D打印技术应用于医疗领域也屡见不鲜。3D打印在医学领域的应用已有二十余年，广泛应用于口腔种植、骨科、神经外科等手术。
牙齿医疗是绝大多数人无法避免的问题，随着计算机软硬件技术的提高，以及越来越精密的牙齿数据的出现，人们也将目光从传统的纯人工牙齿医疗转向了数字化牙齿医疗如隐形正畸牙齿诊疗，借助高新数字化技术提供的先验知识，提高牙齿治疗的安全性和成功率。
目前的隐形正畸牙齿诊疗的应用场景中，所有的应用场景均需要对牙齿模型进行数据处理，而牙齿模型的数据预处理占据大部分3D牙齿打印工作的时间。尤其在正畸矫正的应用场景中，除了需要将牙模进行包括摆放、镂空、布尔运行在内的数据前处理，而且打印完成之后还需要进行压膜，压膜之后需要进行人工切割，或者是通过手动绘制牙龈线，供给CNC机器切割。在这一过程需要耗费巨大的人力成本，以及巨大工作量。为了提高整个诊疗流程的效率，增强用户体验，需要缩短牙齿模型数据的数据处理时间。
此外，正畸矫正的自动化加工流程目前在国内尚处于空白阶段，因此迫切需要结合人工智能算法、3D打印、数控加工等技术实现牙齿矫正的自动化生成加工流程，以提升整个行业的工作效率及竞争力。
本申请技术方案针对目前国内在牙齿矫正自动化过程中牙齿模型数据处理自动化程度低、效率差、用户体验差的技术问题，以提升效率为基准，创新性地探索牙科领域与3D打印技术的结合，将数字化3D打印技术融入牙齿修复工艺中，通过引入人工智能技术，及一系列算法自动识别出牙龈线数据，减少人力，深化数字化生产，填补牙齿矫正过程中牙齿模型数据处理自动化程度低、效率差、用户体验差的空缺技术，为后续牙科与3D技术结合的应用场景奠定坚实基础。
发明内容
为了解决上述技术问题，本发明的目的是提供一种3D牙模牙龈线的识别方法、系统、装置和存储介质。
本发明所采用的第一技术方案是：
一种3D牙模牙龈线的识别方法，包括以下步骤：
对3D牙模基于曲率几何算法提取多个特征点，并对各所述特征点预处理，输出特征轮廓点组；
根据形态参数从预存的拟合参考线池中匹配出第一拟合参考线；
基于特征轮廓点组对所述第一拟合参考线进行迭代运算，生成初始拟合曲线；
采用降维算法对所述初始拟合曲线进行平滑处理，输出牙龈线。
可选地，所述预处理包括过滤或去噪，所述对3D牙模基于曲率几何算法提取多个特征点，并对各所述特征点预处理，输出特征轮廓点组这一步骤具体包括以下步骤：
采用曲率几何算法从处于目标位置的所述3D牙模中提取多个特征点，所述特征点分布于所述3D牙模的凹凸区域；
对提取的各所述特征点进行过滤处理或去噪处理后，生成特征轮廓线点组。
可选地，所述形态参数包括所述3D牙模的形状，所述根据形态参数从预存的拟合参考线池中匹配出第一拟合参考线这一步骤具体包括以下步骤：
根据所述3D牙模的形状，确定所述3D牙模的方向；
基于所述3D牙模的方向从预存的拟合参考线池中匹配出当前牙模特征轮廓同向的特征轮廓点；
结合预建的坐标系和第一阈值从各所述同向的特征轮廓点筛选出第一拟合参考线。
可选地，所述基于特征轮廓点组对所述第一拟合参考线进行迭代运算，生成初始拟合曲线这一步骤具体包括以下步骤：
基于预建的坐标系将所述第一拟合参考线的重心与所述特征轮廓点组的重心进行几何叠合；
采用近似迭代算法将所述第一拟合参考线与所述特征轮廓点组的各特征点进行迭代拟合，生成初始拟合曲线。
可选地，所述降维算法包括主成分分析法，所述采用降维算法对所述初始拟合曲线进行平滑处理，输出牙龈线这一步骤具体包括以下步骤：
采用主成分分析法对所述初始拟合曲线进行平滑处理，确定所述初始拟合曲线的主方向点；
对所述初始拟合曲线的主方向点按照插值样条将平滑处理后的所述初始拟合曲线进行顺滑连接，输出牙龈线。
可选地，所述识别3D牙模的形态参数与最大底面后，将所述3D牙模摆正至目标位置这一步骤具体包括以下步骤：
获取3D牙模，识别出所述3D牙模的最大底面与形态参数，并输出最大底面的法向量；
结合所述最大底面的法向量和预设第一法向量，将所述3D牙模旋转至目标平面；
获取目标平面上3D牙模的轮廓，根据轮廓确定牙齿骨架曲线方程，并输出所述3D牙模的方向向量；
结合所述3D牙模的方向向量和预设第二法向量，将所述3D牙模旋转至目标位置。
本发明所采用的第二技术方案是：
一种3D牙模牙龈线的识别系统，包括：
提取模块，用于对3D牙模基于曲率几何算法提取多个特征点，并对各所述特征点预处理，输出特征轮廓点组；
匹配模块，用于根据形态参数从预存的拟合参考线池中匹配出第一拟合参考线；
迭代模块，用于基于特征轮廓点组对所述第一拟合参考线进行迭代运算，生成初始拟合曲线；
输出模块，用于采用降维算法对所述初始拟合曲线进行平滑处理，输出牙龈线。
可选地，所述提取模块包括：
识别单元，用于识别3D牙模的形态参数与最大底面后，将所述3D牙模摆正至目标位置；
提取单元，用于采用曲率几何算法从处于目标位置的所述3D牙模中提取多个特征点，所述特征点分布于所述3D牙模的凹凸区域；
生成单元，用于对提取的各所述特征点进行过滤处理或去噪处理后，生成特征轮廓线点组。
可选地，所述识别单元包括：
获取子单元，用于获取3D牙模，识别出所述3D牙模的最大底面与形态参数，并输出最大底面的法向量；
第一旋转子单元，用于结合所述最大底面的法向量和预设第一法向量，将所述3D牙模旋转至目标平面；
输出子单元，用于获取目标平面上3D牙模的轮廓，根据轮廓确定牙齿骨架曲线方程，并输出所述3D牙模的方向向量；
第二旋转子单元，用于结合所述3D牙模的方向向量和预设第二法向量，将所述3D牙模旋转至目标位置。
可选地，所述匹配模块包括：
确定单元，用于根据所述3D牙模的形状，确定所述3D牙模的方向；
匹配单元，用于基于所述3D牙模的方向从预存的拟合参考线池中匹配出当前牙模特征轮廓同向的特征轮廓点；
筛选单元，用于结合预建的坐标系和第一阈值从各所述同向的特征轮廓点筛选出第一拟合参考线。
可选地，所述迭代模块包括：
叠合单元，用于基于预建的坐标系将所述第一拟合参考线的重心与所述特征轮廓点组的重心进行几何叠合；
迭代单元，用于采用近似迭代算法将所述第一拟合参考线与所述特征轮廓点组的各特征点进行迭代拟合，生成初始拟合曲线。
可选地，所述输出模块包括：
平滑单元，用于采用主成分分析法对所述初始拟合曲线进行平滑处理，确定所述初始拟合曲线的主方向点；
顺滑单元，用于对所述初始拟合曲线的主方向点按照插值样条将平滑处理后的所述初始拟合曲线进行顺滑连接，输出牙龈线。
本发明所采用的第三技术方案是：
一种装置，包括存储器和处理器，所述存储器用于存储至少一个程序，所述处理器用于加载所述至少一个程序以执行上所述方法。
本发明所采用的第四技术方案是：
一种存储介质，其中存储有处理器可执行的程序，所述处理器可执行的程序在由处理器执行时用于执行如上所述方法。
附图说明
图1是本发明一种3D牙模牙龈线的识别方法步骤流程图；
图2是本发明一种3D牙模牙龈线的识别系统结构框图；
图3是本发明提供的3D牙模牙龈线的整体方法流程示意图。
具体实施方式
如图1所示，本实施例提供一种3D牙模牙龈线的识别方法，包括以下步骤：
S1、对目标位置的3D牙模基于曲率几何算法提取多个特征点，并对各特征点预处理生成特征轮廓线；
S2、根据形态参数从预存的拟合参考线池中匹配出第一拟合参考线；
S3、基于各特征点对第一拟合参考线进行迭代运算，生成初始拟合曲线；
S4、采用降维算法对初始拟合曲线进行平滑处理，输出牙龈线。
本实施例中，3D牙模即3D牙齿模型，是基于3D打印技术和计算机程序加工修复制成的并带有相应平面的牙齿模型。曲率几何算法为针对3D牙模上某个面的切线方向角对弧长的转动率，表明该面的凹凸程度。第一拟合参考线为与特征点的方向(3D牙模的方向)相同，确保最优轮廓线的范围可以覆盖至特征点区域。具体地，识别导入的3D牙模的形态参数与最大底面后，将3D牙模摆正至目标位置；之后对目标位置的3D牙模根据曲率几何算法提取多个特征点；根据识别出的3D牙模的形态参数从预存的拟合参考线池中匹配出偏差最小的特征轮廓线作为第一拟合参考线；根据多个特征点对第一拟合参考线进行迭代运算，生成初始拟合曲线；最后采用降维算法对初始拟合曲线进行平滑处理，输出最终的牙龈线，完成3D牙模数据的预处理。本申请技术方案针对目前隐形正畸的应用场景等对牙齿模型数据处理过程中工作量大、人工成本高、工作效率低以及用户体验差的问题，提出了一种能够大大简化牙齿矫正自动化生成加工流程，降低工作成本，缩短牙齿模型数据的数据处理时间，提高工作效率，增强用户体验的3D牙模牙龈线的识别方法，同时奠定牙科诊疗与3D技术结合的应用场景，填补了国内正畸矫正的自动化加工流程的空白。此外，本实施例中提供的3D牙模牙龈线的识别方法，也适用于带有任意平面和方向的牙齿模型，其他任意带有平面的牙齿模型类型并不影响本发明的实现。
可选地，预处理包括过滤或去噪，S1这一步骤具体包括以下步骤：
S11、获取3D牙模，识别出3D牙模的最大底面与形态参数，并输出最大底面的法向量；
S12、采用曲率几何算法从处于目标位置的3D牙模中提取多个特征点，各所述特征点分布于所述3D牙模的凹凸区域；
S13、对提取的各特征点进行过滤处理或去噪处理后，生成特征轮廓线并存储至特征轮廓线池。
本实施例中，对得到的初始3D牙模特征点进行去噪或过滤，以消除非牙龈线区域的特征点对后续轮廓线的拟合影响；曲率几何算法指针对牙模上某个面的切线方向角对弧长的转动率，表明面的凹凸程度，本申请方案中称为特征，可以通过曲率方法从3D牙模凹凸区域中提取特征点。
可选地，所述S11这一步骤，包括以下步骤：
S111、获取3D牙模，识别出3D牙模的最大底面与形态参数，并输出最大底面的法向量；
S112、结合最大底面的法向量和预设第一法向量，将3D牙模旋转至目标平面；
S113、获取目标平面上3D牙模的轮廓，根据轮廓确定牙齿骨架曲线方程，并输出3D牙模的方向向量；
S114、结合3D牙模的方向向量和预设第二法向量，将3D牙模旋转至目标位置。
本实施例中，预设第一法向量为将3D牙模旋转至目标平面时对应的法向量；预设第二法向量为将3D牙模旋转至目标位置时对应的法向量。具体地，首先，获取导入的3D牙齿模型，通过获取带有底面的任意方向的牙齿模型，获取底面的法向量，基于叉乘法和第一法向量将3D牙模旋转至目标平面；其次，当3D模型处在目标平面时，对3D牙模进行投影，得到牙齿轮廓曲线；对牙齿的轮廓曲线形状进行骨架提取，并对所提取的骨架形状进行噪音处理，获取平滑连续的骨架曲线；求解骨架曲线方程，得到目标位置的第二法向量；根据得到的目标位置的第二法向量，根据叉乘方法求解旋转角度及旋转轴，进而将牙齿模型旋转至目标位置；从而完成了任意方向的3D牙模的自动摆放至目标位置。
可选地，形态参数包括3D牙模的形状，S2这一步骤具体包括以下步骤：
S21、根据3D牙模的形状，确定3D牙模的方向；
S22、基于3D牙模的方向从预存的拟合参考线池中匹配出当前牙模特征轮廓同向的特征轮廓点；
S23、结合预建的坐标系和第一阈值从各同向的特征轮廓点筛选出第一拟合参考线。
本实施例中，坐标系为设有X，Y，Z轴的直角坐标系，也可以根据应用场景选用其他坐标系，在此不做赘述。第一阈值是指使匹配出的同向特征轮廓线与3D牙模在建立的坐标系上偏差最小的值。其中特征轮廓线指一个牙齿的牙龈线文件，该文件由点坐标组成；所述拟合参考池实际是为经过平滑处理的历史牙龈线，这些牙龈线基于其他牙模生成。
可选地，S3这一步骤具体包括以下步骤：
S31、基于预建的坐标系将第一拟合参考线的重心与特征轮廓点组的重心进行几何叠合；
S32、采用近似迭代算法将第一拟合参考线与特征轮廓点组的各特征点进行迭代拟合， 生成初始拟合曲线。
本实施例中，近似迭代算法指第一拟合参考线投影后，循环迭代指投影误差小于设定的阈值，通过同时获取特征点和第一拟合参考线，在建立的坐标系上将第一拟合参考线的重心与各特征点连线的重心进行结合叠合，循环投影迭代后，将投影的点相连形成的初始拟合线，以保证最优的特征轮廓线可以覆盖至特征点区域。
可选地，降维算法包括主成分分析法，S4这一步骤具体包括以下步骤：
S41、采用主成分分析法对初始拟合曲线进行平滑处理，确定初始拟合曲线的主方向点；
S42、对初始拟合曲线的主方向点按照插值样条将平滑处理后的初始拟合曲线进行顺滑连接，输出牙龈线。
本实施例中，生成的初始拟合线，并非平滑的曲线，会有局部的折叠、偏离的现象，针对这种现象，采用主成分分析法(Principal Component Analysis，PCA)获取其主要轮廓形状，确定轮廓主方向的点，按点采用插值样条如Kochanek-Bartels样式将其重新顺滑连接，规避线段不平滑区域，得到最终所需平滑的牙龈线。
如图2所示，本实施例提供一种3D牙模牙龈线的识别系统，包括：
提取模块，用于对3D牙模基于曲率几何算法提取多个特征点，并对各所述特征点预处理，输出特征轮廓点组；
匹配模块，用于根据形态参数从预存的拟合参考线池中匹配出第一拟合参考线；
迭代模块，用于基于特征轮廓点组对所述第一拟合参考线进行迭代运算，生成初始拟合曲线；
输出模块，用于采用降维算法对所述初始拟合曲线进行平滑处理，输出牙龈线。
可选地，所述提取模块包括：
识别单元，用于识别3D牙模的形态参数与最大底面后，将所述3D牙模摆正至目标位置；
提取单元，用于采用曲率几何算法从处于目标位置的所述3D牙模中提取多个特征点，所述特征点分布于所述3D牙模的凹凸区域；
生成单元，用于对提取的各所述特征点进行过滤处理或去噪处理后，生成特征轮廓线点组。
可选地，所述识别单元包括：
获取子单元，用于获取3D牙模，识别出所述3D牙模的最大底面与形态参数，并输出最大底面的法向量；
第一旋转子单元，用于结合所述最大底面的法向量和预设第一法向量，将所述3D牙模旋转至目标平面；
输出子单元，用于获取目标平面上3D牙模的轮廓，根据轮廓确定牙齿骨架曲线方程，并输出所述3D牙模的方向向量；
第二旋转子单元，用于结合所述3D牙模的方向向量和预设第二法向量，将所述3D牙模旋转至目标位置。
可选地，所述匹配模块包括：
确定单元，用于根据所述3D牙模的形状，确定所述3D牙模的方向；
匹配单元，用于基于所述3D牙模的方向从预存的拟合参考线池中匹配出当前牙模特征轮廓同向的特征轮廓点；
筛选单元，用于结合预建的坐标系和第一阈值从各所述同向的特征轮廓点筛选出第一拟合参考线。
可选地，所述迭代模块包括：
叠合单元，用于基于预建的坐标系将所述第一拟合参考线的重心与所述特征轮廓点组的重心进行几何叠合；
迭代单元，用于采用近似迭代算法将所述第一拟合参考线与所述特征轮廓点组的各特征点进行迭代拟合，生成初始拟合曲线。
可选地，所述输出模块包括：
平滑单元，用于采用主成分分析法对所述初始拟合曲线进行平滑处理，确定所述初始拟合曲线的主方向点；
顺滑单元，用于对所述初始拟合曲线的主方向点按照插值样条将平滑处理后的所述初始拟合曲线进行顺滑连接，输出牙龈线。
一种装置，存储器用于存储至少一个程序，处理器用于加载至少一个程序以执行方法实施例方法。
本实施例的一种装置，可执行本发明方法实施例所提供的一种3D牙模牙龈线的识别方法，可执行方法实施例的任意组合实施步骤，具备该方法相应的功能和有益效果。
一种存储介质，其中存储有处理器可执行的程序，该处理器可执行的程序在由处理器执行时用于执行方法实施例方法。
本实施例的一种存储介质，可执行本发明方法实施例所提供的一种3D牙模牙龈线的识别方法，可执行方法实施例的任意组合实施步骤，具备该方法相应的功能和有益效果。
具体实施例
参照图3是本发明提供的3D牙模牙龈线的整体方法流程示意图，包括如下：
开始导入3D牙模，并建立直角坐标系。
获取3D牙模，将3D牙模自动摆正至目标位置。
具体为：(1)对于获取导入的3D牙齿模型，通过获取带有底面的任意方向的牙齿模型，牙齿模型为由一系列三角面片组成的数字化三维体。
(2)检测牙齿模型的最大平面，检测牙齿最大平面的方法为：设定某个三角面片，将设定的三角面片和由三角面片组成的3D牙齿模型进行叠加，设定误差阈值e，当e大于某个值时，认为设定的三角面片与3D牙齿模型上的面片不平；反之则认为处于同一平面。当设定的三角面片与牙齿模型的某个面片在同一平面时，将其两者叠加一起，并继续寻找下一个三角面片并判断误差阈值。循环上述步骤直至得到牙齿模型最大的平面。在检测牙齿模型的最大平面过程中，可得到其平面的方程。
(3)根据叉乘运算方法，根据旋转前后的向量值求解旋转角度及旋转轴，叉乘运算方法是一种在向量空间中向量的二元运算，其运算结果是一个向量而不是一个标量；由上述旋转角度及其旋转轴，可以将任意模型旋转至想要的空间位置上。
(4)基于(3)实现的旋转后，获取牙齿模型，并将其投影成牙齿轮廓曲线，牙齿轮廓曲线即是把3D空间的物体投射到2D平面上得到的物体平面轮廓。得到了牙齿模型的轮廓骨架曲线，可用二次曲线方程表示，并求解该曲线方程，可求得牙模模型的方向向量，根据叉乘运算方法，如同(3)，根据旋转前后的向量值求解旋转角度及旋转轴，上述旋转角度及其旋转轴，基于特定平面旋转至想要的方向位置上。
基于曲率几何算法提取3D牙模的特征点。
具体为：将模型摆放至指定位置之后，按照曲率的几何计算方法，对牙齿模型提取的特征点进行过滤、去噪，可得到3D牙模特征轮廓；曲率几何计算方法为针对牙模上某个面的切线方向角对弧长的转动率，表明面的凹凸程度，在本方案中亦称为特征，则通过曲率方法可获取牙模凹凸区域的特征点(牙模上真实牙龈线也是由凹凸体现的)。
优化特征点，得到3D牙模的特征轮廓点组。
具体为：对(2)得到初始的牙模特征点，需要将其去除噪音，去噪除了牙龈线区域之外，牙齿的其他地方也有凹凸，也被认为是特征，这部分会影响后续与轮廓线的拟合，因此需要将其过滤或者去除，最终得到最优的特征点；其中特征轮廓点组包含多个经过优化后剩下的特征点，特征轮廓点组中的特征点的分布形状(简称为特征轮廓点组形状)会与牙模的牙龈线轮廓近似。需要说明的是特征轮廓点组的重心可理解为特征轮廓点组形状的重心。
根据3D牙模的形状和轮廓，自动选取最优的拟合参考线。
具体为：(1)根据导入后牙模的形状和轮廓，通过摆放后的牙模自动选取最优的拟合参考线，拟合参考线是指一个牙齿的牙龈线文件，该文件由点坐标组成；(2)搜寻最优拟合参考线的主要方法为：首先，根据牙模的方向匹配同一批方向相同的牙齿拟合参考线数据；其次，从筛选的同方向数据中，根据X、Y、Z三个方向确定拟合参考线与牙模的匹配程度，从中选出偏差最小的拟合参考线，即最优的拟合参考线。
将特征点与拟合参考线进行拟合，得到初始拟合线。
具体为：同时取得了特征点和最优拟合参考线，需要将拟合参考线尽可能地和特征点叠合或者拉近，即将拟合参考线的重心按X、Y、Z三个方向平移至和牙模重心重合，优选地，使拟合参考线的重心与特征轮廓点组形状的重心重合，同时确保拟合参考线可覆盖特征点区域；(2)运用近似迭代算法，将拟合参考线和特征轮廓点组的特征点进行拟合，形成初始的拟合线，其中拟合为将拟合参考线(实质为一系列的坐标点)的点投影至离其最近的特征点；近似迭代是指轮廓线投影之后，继续迭代，直至投影误差小于设定的阈值；(3)迭代完成之后，将投影的点相连形成初始的拟合线。
平滑初始拟合线，获得最终的牙龈线。
具体为：获得初始的拟合线，由于初始拟合线不是平滑的曲线，会有局部的折叠、偏离的情况，针对此情况，本方案运用主成分分析方法获取其主要轮廓形状，确定轮廓主方向的点，并按点用Kochanek-Bartels样式将其重新顺滑连接，规避线段不平滑区域，得到最终所需的平滑牙龈线。
结束，输出最终的3D牙模的牙龈线。
以上是对本发明的较佳实施进行了具体说明，但本发明创造并不限于所述实施例，熟悉本领域的技术人员在不违背本发明精神的前提下还可做出等同的各种变形或替换，这些等同的变形或替换均包含在本申请权利要求所限定的范围内。

Claims (10)

  1. 一种3D牙模牙龈线的识别方法，其中，包括以下步骤：
    对3D牙模基于曲率几何算法提取多个特征点，并对各所述特征点预处理，输出特征轮廓点组；
    根据形态参数从预存的拟合参考线池中匹配出第一拟合参考线；
    基于特征轮廓点组对所述第一拟合参考线进行迭代运算，生成初始拟合曲线；
    采用降维算法对所述初始拟合曲线进行平滑处理，输出牙龈线。
  2. 根据权利要求1所述的一种3D牙模牙龈线的识别方法，其中，所述预处理包括过滤或去噪，所述对3D牙模基于曲率几何算法提取多个特征点，并对各所述特征点预处理，输出特征轮廓点组这一步骤具体包括以下步骤：
    识别3D牙模的形态参数与最大底面后，将所述3D牙模摆正至目标位置；
    采用曲率几何算法从处于目标位置的所述3D牙模中提取多个特征点，所述特征点分布于所述3D牙模的凹凸区域；
    对提取的各所述特征点进行过滤处理或去噪处理后，生成特征轮廓线点组。
  3. 根据权利要求1所述的一种3D牙模牙龈线的识别方法，其中，所述形态参数包括所述3D牙模的形状，所述根据形态参数从预存的拟合参考线池中匹配出第一拟合参考线这一步骤具体包括以下步骤：
    根据所述3D牙模的形状，确定所述3D牙模的方向；
    基于所述3D牙模的方向从预存的拟合参考线池中匹配出当前牙模特征轮廓同向的特征轮廓点；
    结合预建的坐标系和第一阈值从各所述同向的特征轮廓点筛选出第一拟合参考线。
  4. 根据权利要求1所述的一种3D牙模牙龈线的识别方法，其中，所述基于特征轮廓点组对所述第一拟合参考线进行迭代运算，生成初始拟合曲线这一步骤具体包括以下步骤：
    基于预建的坐标系将所述第一拟合参考线的重心与所述特征轮廓点组的重心进行几何叠合；
    采用近似迭代算法将所述第一拟合参考线与所述特征轮廓点组的各特征点进行迭代拟合，生成初始拟合曲线。
  5. 根据权利要求1所述的一种3D牙模牙龈线的识别方法，其中，所述降维算法包括主成分分析法，所述采用降维算法对所述初始拟合曲线进行平滑处理，输出牙龈线这一步骤具体包括以下步骤：
    采用主成分分析法对所述初始拟合曲线进行平滑处理，确定所述初始拟合曲线的主方向点；
    对所述初始拟合曲线的主方向点按照插值样条将平滑处理后的所述初始拟合曲线进行顺滑连接，输出牙龈线。
  6. 根据权利要求2所述的一种3D牙模牙龈线的识别方法，其中，所述识别3D牙模的形态参数与最大底面后，将所述3D牙模摆正至目标位置这一步骤具体包括以下步骤：
    获取3D牙模，识别出所述3D牙模的最大底面与形态参数，并输出最大底面的法向量；
    结合所述最大底面的法向量和预设第一法向量，将所述3D牙模旋转至目标平面；
    获取目标平面上3D牙模的轮廓，根据轮廓确定牙齿骨架曲线方程，并输出所述3D牙模的方向向量；
    结合所述3D牙模的方向向量和预设第二法向量，将所述3D牙模旋转至目标位置。
  7. 一种3D牙模牙龈线的识别系统，其中，包括：
    提取模块，用于对3D牙模基于曲率几何算法提取多个特征点，并对各所述特征点预处理，输出特征轮廓点组；
    匹配模块，用于根据形态参数从预存的拟合参考线池中匹配出第一拟合参考线；
    迭代模块，用于基于特征轮廓点组对所述第一拟合参考线进行迭代运算，生成初始拟合曲线；
    输出模块，用于采用降维算法对所述初始拟合曲线进行平滑处理，输出牙龈线。
  8. 根据权利要求7所述的一种3D牙模牙龈线的识别系统，其中，所述提取模块，包括：
    识别单元，用于识别3D牙模的形态参数与最大底面后，将所述3D牙模摆正至目标位置；
    提取单元，用于采用曲率几何算法从处于目标位置的所述3D牙模中提取多个特征点，所述特征点分布于所述3D牙模的凹凸区域；
    生成单元，用于对提取的各所述特征点进行过滤处理或去噪处理后，生成特征轮廓线点组。
  9. 一种装置，其中，包括存储器和处理器，所述存储器用于存储至少一个程序，所述处理器用于加载所述至少一个程序以执行权利要求1-6中任一项所述的方法。
  10. 一种存储介质，其中存储有处理器可执行的程序，其中，所述处理器可执行的程序在由处理器执行时用于执行如权利要求1-6中任一项所述的方法。
PCT/CN2020/134573 2020-07-02 2020-12-08 一种3d牙模牙龈线的识别方法、系统、装置和存储介质 WO2022001001A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP20942870.5A EP4167125A1 (en) 2020-07-02 2020-12-08 3d teeth model gum line identifying method, system and apparatus, and storage medium
US18/072,732 US20230089649A1 (en) 2020-07-02 2022-12-01 Method for Identifying Gum Line of Tooth Model, Device, and Storage Medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010634000.2A CN113963345A (zh) 2020-07-02 2020-07-02 一种3d牙模牙龈线的识别方法、系统、装置和存储介质
CN202010634000.2 2020-07-02

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/072,732 Continuation-In-Part US20230089649A1 (en) 2020-07-02 2022-12-01 Method for Identifying Gum Line of Tooth Model, Device, and Storage Medium

Publications (1)

Publication Number Publication Date
WO2022001001A1 true WO2022001001A1 (zh) 2022-01-06

Family

ID=79317364

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/134573 WO2022001001A1 (zh) 2020-07-02 2020-12-08 一种3d牙模牙龈线的识别方法、系统、装置和存储介质

Country Status (4)

Country Link
US (1) US20230089649A1 (zh)
EP (1) EP4167125A1 (zh)
CN (1) CN113963345A (zh)
WO (1) WO2022001001A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115375903A (zh) * 2022-10-27 2022-11-22 天津大学 一种获取用于重建牙齿的重建数据的方法及系统

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116168808A (zh) * 2022-12-02 2023-05-26 广州黑格智造信息科技有限公司 牙龈线提取方法、牙科器械的制作方法、设备及介质
CN115880286B (zh) * 2023-02-16 2023-06-27 极限人工智能有限公司 智能规划推荐口腔种植体的方法、系统、介质及电子设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8029277B2 (en) * 2005-05-20 2011-10-04 Orametrix, Inc. Method and system for measuring tooth displacements on a virtual three-dimensional model
US8442283B2 (en) * 2006-08-30 2013-05-14 Anatomage Inc. Patient-specific three-dimensional dentition model
KR101476715B1 (ko) * 2014-08-22 2014-12-26 홍경재 투명 교정 장치
CN106037979A (zh) * 2016-05-16 2016-10-26 杭州美齐科技有限公司 一种数字化牙龈线提取方法
CN108986123A (zh) * 2017-06-01 2018-12-11 无锡时代天使医疗器械科技有限公司 牙颌三维数字模型的分割方法
US20200125069A1 (en) * 2018-10-23 2020-04-23 Ormco Corporation Systems and methods for designing and manufacturing an orthodontic appliance

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8029277B2 (en) * 2005-05-20 2011-10-04 Orametrix, Inc. Method and system for measuring tooth displacements on a virtual three-dimensional model
US8442283B2 (en) * 2006-08-30 2013-05-14 Anatomage Inc. Patient-specific three-dimensional dentition model
KR101476715B1 (ko) * 2014-08-22 2014-12-26 홍경재 투명 교정 장치
CN106037979A (zh) * 2016-05-16 2016-10-26 杭州美齐科技有限公司 一种数字化牙龈线提取方法
CN108986123A (zh) * 2017-06-01 2018-12-11 无锡时代天使医疗器械科技有限公司 牙颌三维数字模型的分割方法
US20200125069A1 (en) * 2018-10-23 2020-04-23 Ormco Corporation Systems and methods for designing and manufacturing an orthodontic appliance

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115375903A (zh) * 2022-10-27 2022-11-22 天津大学 一种获取用于重建牙齿的重建数据的方法及系统
CN115375903B (zh) * 2022-10-27 2023-01-17 天津大学 一种获取用于重建牙齿的重建数据的方法及系统

Also Published As

Publication number Publication date
US20230089649A1 (en) 2023-03-23
CN113963345A (zh) 2022-01-21
EP4167125A1 (en) 2023-04-19

Similar Documents

Publication Publication Date Title
WO2022001001A1 (zh) 一种3d牙模牙龈线的识别方法、系统、装置和存储介质
US11694418B2 (en) Systems and methods for constructing a three-dimensional model from two-dimensional images
CA2505892C (en) A method of producing dental prosthetic items or making tooth restorations using electronic dental representations
WO2021238673A1 (zh) 牙齿扫描方法、装置、计算机设备和计算机可读存储介质
CN107301673B (zh) 一种利用标准模型库构造牙齿的局部坐标系的算法
CN111991106B (zh) 一种牙套切割线自动生成方法及应用
CN107595419B (zh) 义齿计算机辅助设计方法、终端及计算机可读存储介质
TWI669484B (zh) 加工程式與對應之切削刀具之匹配辨識方法與系統
US20220079714A1 (en) Automatic segmentation quality assessment for secondary treatment plans
WO2017048668A1 (en) Method for creating flexible arch model of teeth for use in restorative dentistry
WO2016083519A1 (en) Method of digitally designing a modified dental setup
US20240033060A1 (en) Artificial intelligence-based method and application for manufacturing 3d prosthesis for tooth restoration
Zhang et al. Computer-aided design of dental inlay restoration based on dual-factor constrained deformation
CN111265317A (zh) 一种牙齿正畸过程预测方法
CN116246046A (zh) 三维牙齿模型分割方法和装置
Ahmed et al. 3D reconstruction of the human jaw from a sequence of images
CN107638224A (zh) 一种数字化义齿的形位参数测量方法
CN116168808A (zh) 牙龈线提取方法、牙科器械的制作方法、设备及介质
CN116549148A (zh) 三维牙齿模型的牙齿排列方法、装置以及电子设备
CN115375720A (zh) 牙龈边缘线生成方法、装置、计算机设备和存储介质
Wang et al. Tooth alignment network based on landmark constraints and hierarchical graph structure
Jung et al. Control of the manipulator position with the kinect sensor
CN114453981A (zh) 工件找正方法及装置
WO2024114343A1 (zh) 牙龈线提取方法、牙科器械的制作方法及电子设备
WO2018035837A1 (zh) 一种估算三维牙轴的方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20942870

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020942870

Country of ref document: EP

Effective date: 20230112

NENP Non-entry into the national phase

Ref country code: DE