WO2021238673A1 - 牙齿扫描方法、装置、计算机设备和计算机可读存储介质 - Google Patents

牙齿扫描方法、装置、计算机设备和计算机可读存储介质 Download PDF

Info

Publication number
WO2021238673A1
WO2021238673A1 PCT/CN2021/093685 CN2021093685W WO2021238673A1 WO 2021238673 A1 WO2021238673 A1 WO 2021238673A1 CN 2021093685 W CN2021093685 W CN 2021093685W WO 2021238673 A1 WO2021238673 A1 WO 2021238673A1
Authority
WO
WIPO (PCT)
Prior art keywords
tooth
model
mesh
coarse
coarse mesh
Prior art date
Application number
PCT/CN2021/093685
Other languages
English (en)
French (fr)
Inventor
陈晓军
胡俊
章惠全
赵广林
Original Assignee
先临三维科技股份有限公司
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 先临三维科技股份有限公司 filed Critical 先临三维科技股份有限公司
Publication of WO2021238673A1 publication Critical patent/WO2021238673A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
    • G06T17/205—Re-meshing
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
    • A61B5/0082—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence adapted for particular medical purposes
    • A61B5/0088—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence adapted for particular medical purposes for oral or dental tissue
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61C—DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE
    • A61C19/00—Dental auxiliary appliances
    • A61C19/04—Measuring instruments specially adapted for dentistry
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Definitions

  • the present invention relates to the field of three-dimensional scanning, in particular to a tooth scanning method, device, computer equipment and computer-readable storage medium.
  • the embodiments of the present application provide a tooth scanning method, device, system, computer equipment, and computer-readable storage medium, so as to at least solve the problem of low tooth scanning efficiency in related technologies.
  • an embodiment of the present application provides a tooth scanning method, including:
  • the dental identification data separate and extract the first coarse grid data corresponding to the scan bar area in the coarse grid three-dimensional model of the tooth;
  • a first fine mesh and a second fine mesh are generated, and then combined to generate an overall multi-resolution mesh model.
  • the generating a first fine mesh and a second fine mesh according to the first coarse mesh data and the second coarse mesh data, and then combining to generate an overall multi-resolution mesh model includes :
  • an overall multi-resolution mesh model is combined to generate an overall multi-resolution mesh model.
  • the inputting the three-dimensional model of the coarse mesh of the tooth into a preset recognition model, and before obtaining the dental recognition data includes:
  • the method further includes:
  • the dental identification data includes: at least one of tooth area, tooth position information, restoration type information, gum area, and base area;
  • the cutting height of the three-dimensional model of the coarse mesh of the tooth is obtained.
  • the obtaining the cutting height of the three-dimensional model of the coarse mesh of the tooth according to the tooth bounding box includes:
  • the cutting height of the three-dimensional model of the coarse mesh of the tooth is obtained.
  • the method further includes:
  • the dental identification data includes: at least one of tooth area, tooth position information, restoration type information, gum area, and base area;
  • the obtaining a rotating coordinate system according to the tooth region and the tooth position information includes: the tooth position information includes dentition information of a tooth, and the tooth region includes an anterior tooth region and a posterior tooth. area;
  • the method further includes:
  • order information is generated.
  • an embodiment of the present application provides a tooth scanning device, including:
  • the scanning module is set to obtain a three-dimensional model of the coarse mesh of the tooth
  • a recognition module configured to input the three-dimensional model of the coarse mesh of the tooth into the recognition model to obtain dental recognition data
  • the first extraction module is configured to separate and extract the first coarse grid data corresponding to the scan bar region in the three-dimensional tooth coarse grid model according to the dental identification data;
  • the second extraction module is configured to obtain second coarse mesh data corresponding to other areas outside the scan bar area in the coarse mesh three-dimensional model of the tooth;
  • the modeling module is configured to generate a first fine mesh and a second fine mesh according to the first coarse mesh data and the second coarse mesh data, and then combine to generate an overall multi-resolution mesh model.
  • an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored on the memory and running on the processor.
  • the processor executes the computer program, The tooth scanning method as described in the above-mentioned first aspect is realized.
  • an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the tooth scanning method as described in the first aspect is implemented.
  • the tooth scan provided by the embodiments of the present application is performed by separately comparing the coarse mesh data outside the scanning rod area in the coarse mesh three-dimensional model of the tooth and the coarse mesh data of the scanning rod area in the coarse mesh three-dimensional model of the tooth.
  • the fusion process is carried out to realize the automation of extracting the scanning rod and improve the efficiency of tooth scanning.
  • Fig. 1 is a flowchart of a tooth scanning method according to an embodiment of the present application
  • Fig. 2 is a flowchart of another tooth scanning method according to an embodiment of the present application.
  • Fig. 3 is a structural block diagram of a tooth scanning device according to an embodiment of the present application.
  • Fig. 4 is a block diagram of a preferred structure of a tooth scanning device according to an embodiment of the present application.
  • Fig. 5 is a schematic diagram of the hardware structure of a tooth scanning device according to an embodiment of the present application.
  • connection refers to physical or mechanical connections, but may include electrical connections, whether direct or indirect.
  • the "plurality” referred to in this application refers to two or more.
  • “And/or” describes the association relationship of the associated objects, which means that there can be three kinds of relationships. For example, “A and/or B” can mean that: A alone exists, A and B exist at the same time, and B exists alone.
  • the character “/” generally indicates that the associated objects before and after are in an “or” relationship.
  • first”, “second”, “third”, etc. involved in this application merely distinguish similar objects, and do not represent a specific order for the objects.
  • 3D scanners are also called 3D scanners.
  • 3D scanners are high-tech products that integrate optical, mechanical, electrical and computer technologies. It is used to obtain the three-dimensional coordinates of the outer surface of the object and the three-dimensional digital model of the object.
  • the 3D scanner is a desktop 3D scanner or a mouth scan scanner.
  • FIG. 2 is a flowchart of a tooth scanning method according to an embodiment of the present application. As shown in Fig. 2, the process includes the following steps:
  • step S102 a three-dimensional model of the coarse mesh of the tooth is obtained.
  • the tooth image is acquired through a three-dimensional scanner.
  • Three-dimensional reconstruction of the tooth image is performed to obtain multiple point clouds, which are spliced and optimized in the world coordinate system according to the multiple point clouds, and a coarse mesh three-dimensional model of the tooth is quickly fused.
  • the world coordinate system is an absolute coordinate system, and the coordinates of all points on the screen are determined by the origin of the world coordinate system.
  • Step S104 Input the three-dimensional model of the coarse mesh of the tooth to the recognition model to obtain dental recognition data.
  • the dental identification data includes at least one of tooth area, tooth position information, restoration type information, gum area, and base area.
  • the tooth area is the area where the teeth are located and the information of the teeth, and the distribution of the teeth in the area is recorded.
  • the tooth position information records the number of each tooth.
  • the restoration type information is related information such as tooth position information to be restored, restoration type, tooth color, tooth design and the like.
  • the gum area is the area where the gum is located.
  • the base area is the area where the base of the tooth is located and the information of the base.
  • Said inputting the coarse mesh three-dimensional model of the teeth into a preset recognition model for recognition, before obtaining dental recognition data includes: establishing an initial recognition model, and training the initial recognition model by using the three-dimensional mesh model of the teeth as a training set; A recognition model is obtained, the input of the recognition model is the three-dimensional tooth coarse-grid model, and the output is the dental recognition data in the three-dimensional tooth coarse-grid model.
  • the mesh 3D model of the tooth may be a coarse mesh 3D model or a fine mesh 3D model.
  • the mesh 3D model of the tooth is used as the training set to train the initial recognition model.
  • the initial recognition model recognizes the coarse mesh 3D model of the tooth by learning the internal laws and representation levels of the sample data. After deep learning training, a recognition model is generated. Further, the recognition model can also perform deep learning in the subsequent process of recognizing the three-dimensional tooth coarse mesh model.
  • Step S106 according to the dental identification data, separate and extract the first coarse grid data corresponding to the scan bar region in the coarse grid three-dimensional model of the tooth.
  • the scan bar area is the area where the scan bar is located.
  • the scanning rod is a standard body accessory used by the three-dimensional scanner to scan the dental model.
  • the scanning rod can be inserted into the dental jaw. By scanning the standard scanning rod on the jaw, the position of the implant can be better positioned.
  • the dental identification data is analyzed to obtain tooth area, restoration type information, gum area, and base area; according to the tooth area, the gum area, and the base area, the scan bar area is obtained; according to the scan The rod region, separating and extracting the first coarse grid data corresponding to the scanning rod region in the three-dimensional tooth coarse mesh model.
  • the three-dimensional scanner pre-determines that there is a scan bar area in the three-dimensional tooth coarse mesh model, and extracts the first coarse mesh corresponding to the scan bar area in the tooth coarse mesh three-dimensional model according to the scan bar area separation. data.
  • the three-dimensional scanner scans the tooth model from multiple angles to obtain coarse mesh data of the tooth model.
  • the separately separated scanning rod data can be used for subsequent digital tooth design when scanning the implant model.
  • Step S108 Obtain the second coarse grid data corresponding to other areas outside the scan bar area in the three-dimensional tooth coarse grid model.
  • the dental identification data is analyzed to obtain tooth area, restoration type information, gum area, and base area; according to the tooth area, the gum area, and the base area, the scan bar area is obtained; according to the scan The rod area, separating and extracting the second coarse grid data corresponding to other areas outside the scan rod area in the three-dimensional model of the tooth coarse grid.
  • the three-dimensional scanner scans the tooth model from multiple angles to obtain coarse mesh data of the tooth model. Analyze the dental identification data according to the user's instruction to obtain the scan bar area, and separate one or more second coarse grid data of different angles from other areas outside the scan bar area by cutting, and perform fusion processing separately , Merge one or more second coarse grid data into a second fine grid.
  • step S110 a first fine mesh and a second fine mesh are generated according to the first coarse mesh data and the second coarse mesh data, and then combined to generate an overall multi-resolution mesh model.
  • the first coarse grid data in the scan bar area is separately subjected to fusion processing to obtain the first fine grid.
  • the second coarse grid data outside the scan bar area is separately fused to obtain the second fine grid.
  • the first fine mesh should ensure that the details of the generated data are retained as much as possible, so that the quality of the important areas of the overall multi-resolution mesh model is better.
  • the second fine mesh should ensure that the fusion process is completed as quickly as possible under the condition of available details, so that the overall multi-resolution mesh model established is more efficient. If you need to separate the scan bar area, then this method does not need to separate the scan bar area separately and then process it.
  • This method does not need to separate the scan bar area separately and then process it.
  • the scanning software allows the deletion of the data after the scanning is completed to achieve this goal ;
  • some software will also set a cutting plane for real-time removal of redundant data during the data scanning process, but because the set cutting height is adjusted based on experience or needs to be manually adjusted by the customer, there will be cutting In the case of inaccuracy, automatic adjustment cannot be achieved.
  • the method further includes: analyzing the dental identification data to obtain a tooth area and a base area; obtaining a tooth bounding box according to the tooth area; obtaining the tooth rough net according to the tooth bounding box and a preset deviation value The cutting height of the grid 3D model.
  • the tooth bounding box is a rectangular parallelepiped formed along the edge of the tooth.
  • the deviation value is an estimate of the tailoring, an estimate obtained by calculating the tailoring height of one or more tooth models.
  • the dental identification data is analyzed to obtain the tooth area and the base area, and the tooth bounding box is obtained according to the tooth area.
  • the tooth bounding box is identified, and the height of the bounding box is obtained.
  • the deviation between the height of the bounding box and the Z axis of the world coordinate system is less than 90 degrees.
  • the three-dimensional tooth model of the coarse mesh is cut, and the cutting plane is displayed.
  • the height of the bounding box is obtained by identifying the bounding box of the tooth, and the deviation value is subtracted from the height of the bounding box to obtain the cutting height of the three-dimensional model of the coarse mesh of the tooth.
  • the scan data obtained by the 3D scanner is based on the data coordinate system established by the 3D scanner manufacturer (for example, the tooth design software of Exocad in Germany or the tooth design software of 3shape in Denmark. ), but according to these data coordinate system input into the digital tooth design software all need to comply with certain coordinate system rules. Therefore, the scanning software needs to transform the coordinate system of the tooth model through coordinate adjustment. Since the coordinate system established by the scanner is uncertain when acquiring the scanned model, this transformation process will fail probabilistically, causing the manual coordinate system correction to be performed after the data is imported.
  • the method further includes: analyzing the dental identification data to obtain tooth region and tooth position information; obtaining a rotating coordinate system according to the tooth region and the tooth position information; and arranging the tooth coarse mesh according to the rotating coordinate system
  • the three-dimensional model or the overall multi-resolution grid model is rotated to the target position.
  • the tooth position information includes dentition information, anterior teeth information, and posterior teeth information.
  • the dental identification data is analyzed to obtain tooth region and tooth position information.
  • Calculate the dentition information obtain the dental arch curve through the dental arch calculation method; obtain the Z-axis direction of the three-dimensional tooth coarse mesh model according to the dental arch curve and the tooth region; according to the anterior tooth information and the tooth
  • the posterior tooth information and the tooth area are used to obtain the X-axis direction and the Y-axis direction of the three-dimensional tooth model of the coarse mesh; according to the Z-axis direction, the X-axis direction and the Y-axis direction, a rotating coordinate system is generated. Rotating the three-dimensional tooth coarse mesh model or the overall multi-resolution mesh model to a target position according to the rotating coordinate system.
  • the dental arch curve is calculated from the dentition information to obtain the Z-axis direction of the three-dimensional model of the coarse mesh of the tooth, and the Z-axis direction is set to be perpendicular to the plane where the dental arch curve is located.
  • the X-axis direction in the arch curve plane is obtained through the arch calculation method, and the X-axis direction is toward the middle of the incisor teeth.
  • the Y-axis direction is determined according to the law of the right-hand coordinate system. According to the Z-axis direction, the X-axis direction, and the Y-axis direction, a rotating coordinate system is generated.
  • a change is made to convert the tooth coarse mesh 3D model to the target position in the rotating coordinate system.
  • a rotating coordinate system based on the tooth arrangement direction is established. Rotating the coarse mesh 3D model of the tooth according to the rotating coordinate system can effectively improve the success rate of coordinate conversion.
  • This information contains the necessary information for this restoration.
  • This information can be divided into two categories.
  • the first category refers to the basic information of the patient, mainly number, Name, etc.;
  • the second category means that the restoration type information contains information about the tooth position that needs restoration, restoration type, tooth color, and tooth design related information.
  • the repair type information is the information that must be confirmed in advance to start the scan, so it must be filled in before the scan can be used by the scanning software to create the necessary scanning process based on this information to complete the data collection work.
  • the method further includes: generating order information according to the dental identification data.
  • a scanning operation is performed first, and the dental identification data is analyzed to obtain tooth position information and restoration type information; according to the tooth position information and the restoration type, order information is generated.
  • the user can perform proofreading based on the scanned order information and the first type of information reported at the beginning.
  • the order information includes patient information and restoration type information.
  • the patient information is based on the basic conditions of the patient input by the personnel.
  • the restoration type information includes information about the tooth position to be restored, the restoration type, tooth color, and tooth design related information.
  • the coarse mesh three-dimensional model of the tooth is analyzed and recognized through the recognition model, and the tooth position information and restoration type information can be accurately extracted, and order information is generated according to the tooth position information and the restoration type. There is no need to enter order information in advance, and the three-dimensional model of the coarse mesh of the tooth is automatically scanned to obtain the order information.
  • the coarse mesh data outside the scanning rod area in the coarse mesh three-dimensional model of the tooth and the coarse mesh data outside the scanning rod area in the coarse mesh three-dimensional model of the tooth are respectively fused to solve the problem of model detail preservation and overall The balance between fusion efficiency.
  • FIG. 2 is a flowchart of another tooth scanning method according to an embodiment of the present application. As shown in Fig. 2, the process includes the following steps:
  • Step S301 Obtain a picture collected by the three-dimensional scanner.
  • Step S302 Perform three-dimensional reconstruction from the picture to obtain a point cloud.
  • step S303 the multiple point clouds are spliced and optimized.
  • multiple point clouds are spliced and optimized in the world coordinate system.
  • step S304 a three-dimensional model of the coarse mesh of the tooth is established by rapid fusion.
  • multiple point clouds are fused to build a three-dimensional model of the coarse mesh of the tooth.
  • step S305 the coarse mesh three-dimensional model of the tooth is recognized through the recognition model to obtain dental recognition data.
  • Step S306 Generate order information based on the tooth position information and the repair type.
  • Step S307 order proofreading.
  • the dental identification data is analyzed to obtain tooth position information and restoration type information; and order information is generated according to the tooth position information and the restoration type.
  • the user can perform proofreading based on the order information obtained by scanning and the information filled out by the patient at the beginning.
  • the second type is the first type:
  • Step S308 based on the restoration type information, the tooth area, the gum area, and the base area.
  • the scan bar area is obtained.
  • Step S309 Perform fusion processing on the first coarse grid data of the scan bar area to generate a first fine grid.
  • Step S310 Perform fusion processing on the second coarse grid data of other regions to generate a second fine grid.
  • step S309 and step S310 can be processed at the same time.
  • step S311 the first fine mesh and the second fine mesh are merged into an overall multi-resolution mesh model.
  • the third type is the third type.
  • Step S312 Determine the tooth bounding box of the tooth region based on the tooth region.
  • Step S313 Determine the cropping height according to the cropped deviation value and the height of the bounding box.
  • step S314 according to the cutting height CutZ, the cutting plane is displayed in the model scene.
  • the three-dimensional model of the coarse mesh of the tooth is cut according to the cutting height, and the cutting plane is displayed.
  • the fourth type is the fourth type.
  • step S315 based on the tooth position information and the tooth region, a rotating coordinate system of the three-dimensional tooth coarse mesh model is determined.
  • Step S316 Determine the target position of the conversion according to the rotating coordinate system.
  • step S317 a rotation transformation is performed on the three-dimensional tooth coarse mesh model to transform the target position.
  • This embodiment also provides a tooth scanning device, which is used to implement the above-mentioned embodiments and preferred implementations, and what has been described will not be repeated.
  • the terms “module”, “unit”, “sub-unit”, etc. can realize a combination of software and/or hardware that can implement predetermined functions.
  • the devices described in the following embodiments are preferably implemented by software, implementation by hardware or a combination of software and hardware is also possible and conceived.
  • FIG. 3 is a structural block diagram of a tooth scanning device according to an embodiment of the present application. As shown in FIG. 3, the device includes: a scanning module 310, an identification module 320, a first extraction module 330, a second extraction module 340, and a modeling module 350 .
  • the scanning module 310 is configured to obtain a three-dimensional model of the coarse mesh of the tooth.
  • the recognition module 320 is configured to input the three-dimensional model of the coarse mesh of the tooth into the recognition model to obtain dental recognition data.
  • the first extraction module 330 is configured to separate and extract the first coarse grid data corresponding to the scan bar region in the three-dimensional tooth coarse grid model according to the dental identification data.
  • the second extraction module 340 is configured to obtain second coarse grid data corresponding to other regions outside the scan bar region in the three-dimensional tooth coarse grid model.
  • the modeling module 350 is configured to generate a first fine mesh and a second fine mesh according to the first coarse mesh data and the second coarse mesh data, and then combine them to generate an overall multi-resolution mesh model.
  • the modeling module 350 is further configured to perform fusion processing on one or more of the first coarse grid data to obtain a first fine grid; and perform fusion processing on one or more of the second coarse grid data to obtain The second fine mesh; according to the first fine mesh and the second fine mesh, combined to generate an overall multi-resolution mesh model.
  • the recognition module 320 is also set to establish an initial recognition model, train the recognition model using the mesh 3D model of the tooth as a training set, and obtain a recognition model.
  • the input of the recognition model is the coarse mesh 3D model of the tooth, and the output is Dental identification data in the three-dimensional model of the coarse mesh of the tooth.
  • FIG. 4 is a preferred structural block diagram of a tooth scanning device according to an embodiment of the present application. As shown in FIG. 4, the device includes all the modules shown in FIG. 3, and further includes: an order module 410, a cutting module 420, and a rotation module 430 .
  • the cutting module 420 is configured to obtain a tooth bounding box according to the tooth region; according to the tooth bounding box, obtain the cutting height of the three-dimensional model of the coarse mesh of the tooth.
  • the cutting module 420 is further configured to identify the tooth bounding box and obtain the height of the bounding box; according to the height of the bounding box and a preset deviation value, obtain the cutting height of the coarse mesh three-dimensional model of the tooth.
  • the rotation module 430 is configured to obtain a rotating coordinate system according to the tooth area and the tooth position information; and rotate the tooth coarse mesh three-dimensional model or the overall multi-resolution mesh model to a target position according to the rotating coordinate system .
  • the rotation module 430 is also configured to calculate the dentition information of the teeth in the anterior tooth region and the posterior tooth region, and obtain the dental arch curve through the dental arch calculation method; according to the dental arch curve, obtain the Z of the coarse mesh three-dimensional model of the tooth Axis direction; according to the anterior tooth region and the dental arch curve, obtain the X-axis direction and the Y-axis direction of the three-dimensional tooth model of the coarse mesh; according to the Z-axis direction, the X-axis direction and the Y-axis direction To generate a rotating coordinate system.
  • the order module 410 is configured to generate order information according to the dental identification data.
  • each of the above-mentioned modules may be a functional module or a program module, which may be implemented by software or hardware.
  • each of the foregoing modules may be located in the same processor; or each of the foregoing modules may also be located in different processors in any combination.
  • each of the above-mentioned modules may be a functional module or a program module, which may be implemented by software or hardware.
  • each of the foregoing modules may be located in the same processor; or each of the foregoing modules may also be located in different processors in any combination.
  • Fig. 5 is a schematic diagram of the hardware structure of a tooth scanning device according to an embodiment of the present application.
  • the tooth scanning device may include a processor 81 and a memory 82 storing computer program instructions.
  • the foregoing processor 81 may include a central processing unit (CPU), or a specific integrated circuit (Application Specific Integrated Circuit, ASIC for short), or may be configured to implement one or more integrated circuits in the embodiments of the present application.
  • CPU central processing unit
  • ASIC Application Specific Integrated Circuit
  • the memory 82 may include a large-capacity memory for data or instructions.
  • the storage 82 may include a hard disk drive (Hard Disk Drive, referred to as HDD), a floppy disk drive, a solid state drive (Solid State Drive, referred to as SSD), flash memory, optical disk, magneto-optical disk, magnetic tape, or universal serial Universal Serial Bus (USB for short) driver or a combination of two or more of these.
  • the storage 82 may include removable or non-removable (or fixed) media.
  • the memory 82 may be internal or external to the data processing device.
  • the memory 82 is a non-volatile (Non-Volatile) memory.
  • the memory 82 includes a read-only memory (Read-Only Memory, ROM for short) and a random access memory (Random Access Memory, RAM for short).
  • the ROM can be mask-programmed ROM, programmable ROM (Programmable Read-Only Memory, referred to as PROM), erasable PROM (Erasable Programmable Read-Only Memory, referred to as EPROM), and electrically accessible Erase PROM (Electrically Programmable Read-Only Memory, EEPROM for short), Electrically Alterable Read-Only Memory (EAROM for short), Flash memory (FLASH), or a combination of two or more of these.
  • the RAM can be a static random access memory (Static Random-Access Memory, referred to as SRAM) or a dynamic random access memory (Dynamic Random Access Memory, referred to as DRAM), where the DRAM can be a fast page Mode Dynamic Random Access Memory (Fast Page Mode Dynamic Random Access Memory, referred to as FPMDRAM), Extended Data Output Dynamic Random Access Memory (Extended Date Out Dynamic Random Access Memory, referred to as EDODRAM), Synchronous Dynamic Random Access Memory (Synchronous) Dynamic Random-Access Memory, SDRAM for short), etc.
  • SRAM Static Random-Access Memory
  • DRAM Dynamic Random Access Memory
  • FPMDRAM fast page Mode Dynamic Random Access Memory
  • EDODRAM Extended Data Output Dynamic Random Access Memory
  • Synchronous Dynamic Random Access Memory Synchronous Dynamic Random-Access Memory
  • the memory 82 may be used to store or cache various data files that need to be processed and/or used for communication, as well as possible computer program instructions executed by the processor 81.
  • the processor 81 reads and executes the computer program instructions stored in the memory 82 to implement any one of the tooth scanning methods in the foregoing embodiments.
  • the tooth scanning device may further include a communication interface 83 and a bus 80.
  • the processor 81, the memory 82, and the communication interface 83 are connected through the bus 80 and complete the communication with each other.
  • the communication interface 83 is used to implement communication between various modules, devices, units, and/or devices in the embodiments of the present application.
  • the communication port 83 can also implement data communication with other components such as: external devices, image/data acquisition devices, databases, external storage, and image/data processing workstations.
  • the bus 80 includes hardware, software, or both, and couples the components of the dental scanning device to each other.
  • the bus 80 includes but is not limited to at least one of the following: a data bus (Data Bus), an address bus (Address Bus), a control bus (Control Bus), an expansion bus (Expansion Bus), and a local bus (Local Bus).
  • the bus 80 may include Accelerated Graphics Port (AGP) or other graphics buses, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (Front Side Bus).
  • FSB HyperTransport
  • ISA Industry Standard Architecture
  • IGBASE Interconnect
  • LPC Low Pin Count
  • MCA Micro Channel Architecture
  • PCI Peripheral Component Interconnect
  • PCI-X Peripheral Component Interconnect
  • SATA Serial Advanced Technology Attachment
  • VLB Video Electronics Standards Association Local Bus
  • the bus 80 may include one or more buses.
  • the tooth scanning device can execute the tooth scanning method in the embodiment of the present application based on the acquired tooth scanning data, so as to realize the tooth scanning method described in conjunction with FIG. 1.
  • the embodiment of the present application may provide a computer-readable storage medium for implementation.
  • Computer program instructions are stored on the computer-readable storage medium; when the computer program instructions are executed by the processor, any one of the tooth scanning methods in the foregoing embodiments is implemented.
  • the solution provided by the embodiment of the present invention can be applied to the process of tooth scanning.
  • the embodiment of the present invention solves the technical problem that the prior art cannot coordinate the balance between model detail preservation and overall fusion efficiency, realizes automatic extraction of scanning rods, and improves tooth scanning efficiency.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Animal Behavior & Ethology (AREA)
  • Dentistry (AREA)
  • Computing Systems (AREA)
  • Pathology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Surgery (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Geometry (AREA)
  • Computer Graphics (AREA)
  • Epidemiology (AREA)
  • Dental Tools And Instruments Or Auxiliary Dental Instruments (AREA)

Abstract

一种牙齿扫描方法、装置、计算机设备和计算机可读存储介质。其中，该牙齿扫描方法包括：获取牙齿粗网格三维模型（S102）；将所述牙齿粗网格三维模型输入至识别模型，获得齿科识别数据（S104）；根据所述齿科识别数据，分离提取出所述牙齿粗网格三维模型中扫描杆区域对应的第一粗网格数据（S106）；获取牙齿粗网格三维模型中扫描杆区域外其他区域对应的第二粗网格数据（S108）；根据所述第一粗网格数据以及第二粗网格数据，生成第一精网格和第二精网格，然后合并生成整体多分辨率网格模型（S110）。通过分别对牙齿粗网格三维模型中扫描杆区域外的粗网格数据和牙齿粗网格三维模型中扫描杆区域的粗网格数据进行融合处理，解决了模型细节保留和整体融合效率之间的平衡问题。

Description

牙齿扫描方法、装置、计算机设备和计算机可读存储介质
本申请要求于2020年07月17日提交中国专利局、申请号为202010691617.8、发明名称“牙齿扫描方法、装置、系统、计算机设备和计算机可读存储介质”的中国专利申请的优先权，以及要求于2020年05月29日提交中国专利局、申请号为202010476785.5、发明名称“牙齿扫描方法、装置、系统和计算机可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及三维扫描领域，具体而言，涉及一种牙齿扫描方法、装置、计算机设备和计算机可读存储介质。
背景技术
技师或者诊所医生在技工所内利用三维模型扫描仪或者口扫扫描仪进行模型数据获取时，针对扫描完成的种植类型扫描数据，为了方便后续的cad修复体设计，需要分离出单独的扫描杆数据，用于后续的数字化牙齿设计。
但是目前扫描杆数据的分离方式需要通过人工选定区域，进行多次提取，分离效果差、自动化程度低，降低了生成效率。
发明内容
本申请实施例提供了一种牙齿扫描方法、装置、系统、计算机设备和计算机可读存储介质，以至少解决相关技术中牙齿扫描效率低的问题。
第一方面，本申请实施例提供了一种牙齿扫描方法，包括：
获取牙齿粗网格三维模型；
将所述牙齿粗网格三维模型输入至识别模型，获得齿科识别数据；
根据所述齿科识别数据，分离提取出所述牙齿粗网格三维模型中扫描杆区域对应的第一粗网格数据；
获取牙齿粗网格三维模型中扫描杆区域外其他区域对应的第二粗网格数据；
根据所述第一粗网格数据以及第二粗网格数据，生成第一精网格和第二精网格，然后合并生成整体多分辨率网格模型。
在其中一些实施例中，所述根据所述第一粗网格数据以及第二粗网格数据，生成第一精网格和第二精网格，然后合并生成整体多分辨率网格模型包括：
将一个或多个所述第一粗网格数据进行融合处理，获得第一精网格；
将一个或多个所述第二粗网格数据进行融合处理，获得第二精网格；
根据所述第一精网格和所述第二精网格，合并生成整体多分辨率网格模型。
在其中一些实施例中，所述将所述牙齿粗网格三维模型输入至预设的识别模型中，获得齿科识别数据之前包括：
建立初始识别模型，将牙齿的网格三维模型作为训练集对识别模型进行训练，获得识别模型，所述识别模型的输入为所述牙齿粗网格三维模型，输出为所述牙齿粗网格三维模型中的齿科识别数据。
在其中一些实施例中，所述方法还包括：
所述齿科识别数据包括：牙齿区域、牙位信息、修复类型信息、牙龈区域以及底座区域中至少一项；
根据所述牙齿区域，获得牙齿包围盒；
根据所述牙齿包围盒，获得所述牙齿粗网格三维模型的裁切高度。
在其中一些实施例中，所述根据所述牙齿包围盒，获得所述牙齿粗网格三维模型的裁切高度包括：
识别所述牙齿包围盒，获得所述包围盒高度；
根据所述包围盒高度以及预设偏差值，获得所述牙齿粗网格三维模型的裁切高度。
在其中一些实施例中，所述方法还包括：
所述齿科识别数据包括：牙齿区域、牙位信息、修复类型信息、牙龈区域以及底座区域中至少一项；
根据所述牙齿区域和所述牙位信息，获得旋转坐标系；
根据旋转坐标系将所述牙齿粗网格三维模型或所述整体多分辨率网格模型旋转至目标位置。
在其中一些实施例中，所述根据所述牙齿区域和所述牙位信息，获得旋转坐标系包括：所述牙位信息包括牙齿的牙列信息，所述牙齿区域包括前牙区域以及后牙区域；
计算所述前牙区域和后牙区域上牙齿的牙列信息，通过牙弓计算方法获得牙弓曲线；
根据所述牙弓曲线，获得牙齿粗网格三维模型的Z轴方向；
根据所述前牙区域和所述牙弓曲线，获得牙齿粗网格三维模型的X轴方向和Y轴方向；
根据所述Z轴方向、所述X轴方向和所述Y轴方向，生成旋转坐标系。
在其中一些实施例中，所述方法还包括：
根据所述齿科识别数据，生成订单信息。
第二方面，本申请实施例提供了一种牙齿扫描装置，包括：
扫描模块，设置为获取牙齿粗网格三维模型；
识别模块，设置为将所述牙齿粗网格三维模型输入至识别模型，获得齿科识别数据；
第一提取模块，设置为根据所述齿科识别数据，分离提取出所述牙齿粗网格三维模型中扫描杆区域对应的第一粗网格数据；
第二提取模块，设置为获取牙齿粗网格三维模型中扫描杆区域外其他区域对应的第二粗网格数据；
建模模块，设置为根据所述第一粗网格数据以及第二粗网格数据，生成第一精网格和第二精网格，然后合并生成整体多分辨率网格模型。
第三方面，本申请实施例提供了一种计算机设备，包括存储器、处理器以及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现如上述第一方面所述的牙齿扫描方法。
第四方面，本申请实施例提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如上述第一方面所述的牙齿扫描方法。
相比于相关技术，本申请实施例提供的牙齿扫描，通过分别对牙齿粗网格三维模型中扫描杆区域外的粗网格数据和牙齿粗网格三维模型中扫描杆区域的粗网格数据进行融合处理，实现提取扫描杆的自动化，提高了牙齿扫描效率。
本申请的一个或多个实施例的细节在以下附图和描述中提出，以使本申请的其他特征、目的和优点更加简明易懂。
附图说明
此处所说明的附图用来提供对本申请的进一步理解，构成本申请的一部分，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的不当限定。在附图中：
图1是根据本申请实施例的牙齿扫描方法的流程图；
图2是根据本申请实施例的另一种牙齿扫描方法的流程图；
图3是根据本申请实施例的牙齿扫描装置的结构框图；
图4是根据本申请实施例的牙齿扫描装置的优选结构框图；
图5为根据本申请实施例的牙齿扫描设备的硬件结构示意图。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行描述和说明。应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。基于本申请提供的实施例，本领域普通技术人员在没有作出创造性劳动的前提下所获得的所有其他实施例，都属于本申请保护的范围。
显而易见地，下面描述中的附图仅仅是本申请的一些示例或实施例，对于本领域的普通技术人员而言，在不付出创造性劳动的前提下，还可以根据这些附图将本申请应用于其他类似情景。此外，还可以理解的是，虽然这种开发过程中所作出的努力可能是复杂并且冗长的，然而对于与本申请公开的内容相关的本领域的普通技术人员而言，在本申请揭露的技术内容的基础上进行的一些设计，制造或者生产等变更只是常规的技术手段，不应当理解为本申请公开的内容不充分。
在本申请中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域普通技术人员显式地和隐式地理解的是，本申请所描述的实施例在不冲突的情况下，可以与其它实施例相结合。
除非另作定义，本申请所涉及的技术术语或者科学术语应当为本申请所属技术领域内具有一般技能的人士所理解的通常意义。本申请所涉及的“一”、“一个”、“一种”、“该”等类似词语并不表示数量限制，可表示单数或复数。本申请所涉及的术语“包括”、“包含”、“具有”以及它们任何变形，意图在于覆盖不排他的包含；例如包含了 一系列步骤或模块(单元)的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可以还包括没有列出的步骤或单元，或可以还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。本申请所涉及的“连接”、“相连”、“耦接”等类似的词语并非限定于物理的或者机械的连接，而是可以包括电气的连接，不管是直接的还是间接的。本申请所涉及的“多个”是指两个或两个以上。“和/或”描述关联对象的关联关系，表示可以存在三种关系，例如，“A和/或B”可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。本申请所涉及的术语“第一”、“第二”、“第三”等仅仅是区别类似的对象，不代表针对对象的特定排序。
本申请中描述的各种技术可用于各种三维扫描仪中，三维扫描仪也称为三维立体扫描仪，3D扫描仪，是融合光、机、电和计算机技术于一体的高新科技产品，主要用于获取物体外表面的三维坐标及物体的三维数字化模型。在本实施例中，所述三维扫描仪为桌面式三维扫描仪或者口扫扫描仪。
本实施例还提供了一种牙齿扫描方法。图2是根据本申请实施例的牙齿扫描方法的流程图，如图2所示，该流程包括如下步骤：
步骤S102，获取牙齿粗网格三维模型。
具体地，通过三维扫描仪，获取牙齿图像。将牙齿图像进行三维重建，获得多个点云，根据多个点云在世界坐标系中进行拼接优化，快速融合建立牙齿粗网格三维模型。其中，所述世界坐标系为绝对坐标系，画面上所有点的坐标都是以该世界坐标系的原点来确定各自的位置的。
步骤S104，将所述牙齿粗网格三维模型输入至识别模型，获得齿科识别数据。
具体地，将所述牙齿粗网格三维模型输入预设的识别模型采用人工智能算法自动识别所述牙齿粗网格三维模型，通过对所述牙齿粗网格三维模型各区域的比对分析，识别出齿科识别数据。其中，所述齿科识别数据包括牙齿区域、牙位信息、修复类型信息、牙龈区域以及底座区域中至少一项。所述牙齿区域为牙齿所在区域以及牙齿的信息，记录着牙齿在该区域内的分布情况。所述牙位信息为记录每个牙齿的编号。所述修复类型信息为需要修复的牙位信息、修复类型、齿色、牙齿设计等相关信息。所述牙龈区域为牙龈所在区域。所述底座区域为牙齿的底座所在区域以及底座的信息。
所述将所述牙齿粗网格三维模型输入预设的识别模型进行识别，获得齿科识别数据之前包括：建立初始识别模型，将牙齿的网格三维模型作为训练集对初始识别模型进行训练，获得识别模型，所述识别模型的输入为所述牙齿粗网格三维模型，输出为所述牙齿粗网格三维模型中的齿科识别数据。
其中，所述牙齿的网格三维模型可以为粗网格三维模型，也可以是精网格三维模型。
具体地，将牙齿的网格三维模型作为训练集对初始识别模型进行训练，所述初始识别模型通过学习样本数据的内在规律和表示层次，对所述牙齿粗网格三维模型进行识别，经过大量深度学习的训练后，生成识别模型。进一步地，所述识别模型还能够通过后续识别所述牙齿粗网格三维模型的过程中进行深度学习。
步骤S106，根据所述齿科识别数据，分离提取出所述牙齿粗网格三维模型中扫描杆区域对应的第一粗网格数据。
其中，所述扫描杆区域为扫描杆所在区域。所述扫描杆为三维扫描仪用于扫描齿科模型的标准体配件，可将扫描杆插入牙颌中，通过扫描颌上的标准扫描杆，可以更好的定位种植体的位置。
具体地，分析所述齿科识别数据，获得牙齿区域、修复类型信息、牙龈区域以及底座区域；根据所述牙齿区域、所述牙龈区域和所述底座区域，获得扫描杆区域；根据所述扫描杆区域，分离提取出所述牙齿粗网格三维模型中扫描杆区域对应的第一粗网格数据。在一个实施例中，三维扫描仪中预先确定牙齿粗网格三维模型中存在扫描杆区域，根据扫描杆区域分离提取出所述牙齿粗网格三维模型中扫描杆区域对应的第一粗网格数据。在本实施例中，三维扫描仪多角度扫描牙齿模型，获得牙齿模型的粗网格数据。根据用户指令对所述齿科识别数据进行分析，获得扫描杆区域，通过切割的方式将扫描杆区域中一个或多个不同角度的第一粗网格数据分离出来，单独进行融合处理，将一个或多个第一粗网格数据合并成第一精网格。单独分离出来的扫描杆数据可以在扫描种植模型的时候，用于后续的数字化牙齿设计。
步骤S108，获取牙齿粗网格三维模型中扫描杆区域外其他区域对应的第二粗网格数据。
具体地，分析所述齿科识别数据，获得牙齿区域、修复类型信息、牙龈区域以及底座区域；根据所述牙齿区域、所述牙龈区域和所述底座区域，获得扫描杆区域；根据所述扫描杆区域，分离提取出所述牙齿粗网格三维模型中扫描杆区域外其他区域对应的第二粗网格数据。在本实施例中，三维扫描仪多角度扫描牙齿模型，获得牙齿模型的粗网格数据。根据用户指令对所述齿科识别数据进行分析，获得扫描杆区域，通过切割的方式将扫描杆区域外的其他区域一个或多个不同角度的第二粗网格数据分离出来，单独进行融合处理，将一个或多个第二粗网格数据合并成第二精网格。
步骤S110，根据所述第一粗网格数据以及第二粗网格数据，生成第一精网格和第二精网格，然后合并生成整体多分辨率网格模型。
具体地，将扫描杆区域内的第一粗网格数据中单独进行融合处理，获得第一精网格。将扫描杆区域外的第二粗网格数据中单独进行融合处理，获得第二精网格。第一精网格应该确保所生成的数据的细节尽可能的保留，使建立的整体多分辨率网格模型的重要区域的质量更好。第二精网格应该确保在可用细节的情况下，尽可能的快速完成融合处理，使建立的整体多分辨率网格模型效率更高。如果需要对扫描杆区域进行分离，那么这种方法就无需单独将扫描杆区域进行分离再处理，通过在扫描过程中自动识别扫描杆的数据，并且进行提取对应区域的粗网格数据进行处理，独立生产扫描杆数据。其余对应区域的粗网格数据进行处理，生产颌数据。
现有的齿科数字化扫描过程中，为了提高模型融合和后处理的效率，需要尽可能的减少多余的数据量，所以在扫描软件中允许对扫描完成后的数据进行删除操作，以达到这个目的；同时有些软件还会设置一个切割平面用于在数据扫描过程中，对多余的数据进行实时的去除，但是由于设置的裁切高度都是根据经验调整或者需要客户进行手动调整，会存在裁切不准确的情况，无法做到自动调节。
所述方法还包括：分析所述齿科识别数据，获得牙齿区域和底座区域；根据所述牙齿区域，获得牙齿包围盒；根据所述牙齿包围盒以及预设偏差值，获得所述牙齿粗网格三维模型的裁切高度。
其中，所述牙齿包围盒为沿着牙齿的边缘形成的长方体。所述偏差值为剪裁的估值，通过计算一个或多个牙齿模型的剪裁高度获得的估值。
具体地，分析所述齿科识别数据，获得牙齿区域和底座区域，根据所述牙齿区域，获得牙齿包围盒。识别所述牙齿包围盒，获得所述包围盒高度。根据所述包围盒高度以及预设的偏差值进行计算，获得所述牙齿粗网格三维模型的裁切高度。其中，所述包围盒高度与世界坐标系的Z轴偏差小于90度。进一步地，根据所述裁切高度将所述牙齿粗网格三维模型进行裁切，并显示裁剪平面。在本实施例中，通过识别所述牙齿包围盒，获得所述包围盒高度，将所述包围盒高度减去偏差值，获得所述牙齿粗网格三维模型的裁切高度。通过在扫描过程中识别牙齿区域和底座区域，根据识别结果自动设定一个裁切高度，可以做到实现自动裁剪，且适用性更广。
现有的齿科数字化扫描过程中，通过三维扫描仪获取的扫描数据，都是根据三维扫描仪厂家各自建立的数据坐标系(例如德国exocad公司的牙齿设计软件或者丹麦的3shape公司的牙齿设计软件)，但是根据这些数据坐标系输入到数字化牙齿设计软件都需要符合一定的坐标系规则。所以扫描软件需要通过坐标调整来进行牙齿模型的坐标系变换。由于扫描仪在获取扫描模型时，建立的坐标系是不确定的，所以这个变换过程会出现概率性的失败，导致这些数据导入进去后，还需要进行手动坐标系纠正。
所述方法还包括：分析所述齿科识别数据，获得牙齿区域和牙位信息；根据所述牙齿区域和所述牙位信息，获得旋转坐标系；根据旋转坐标系将所述牙齿粗网格三维模型或所述整体多分辨率网格模型旋转至目标位置。
其中，所述牙位信息包括牙列信息、前牙信息和后牙信息。
具体地，分析所述齿科识别数据，获得牙齿区域和牙位信息。计算所述牙列信息，通过牙弓计算方法获得牙弓曲线；根据所述牙弓曲线以及所述牙齿区域，获得牙齿粗网格三维模型的Z轴方向；根据所述前牙信息和所述后牙信息以及所述牙齿区域，获得牙齿粗网格三维模型的X轴方向和Y轴方向；根据所述Z轴方向、所述X轴方向和所述Y轴方向，生成旋转坐标系。根据旋转坐标系将所述牙齿粗网格三维模型或所述整体多分辨率网格模型旋转至目标位置。在本实施例中，通过牙列信息计算出牙弓曲线，从而获得牙齿粗网格三维模型的Z轴方向，设定Z轴方向与牙弓曲线所在的平面垂直。根据前牙信息和后牙信息，通过牙弓计算方法获得牙弓曲线平面内的X轴方向，X轴方向朝向牙齿门牙的中间。最后根据右手坐标系法则，确定Y轴方向。根据所述Z轴方向、所述X轴方向和所述Y轴方向，生成旋转坐标系。根据旋转坐标系和牙齿粗网格三维模型原有的世界坐标系做一个变化，把牙齿粗网格三维模型转换到旋转坐标系下的目标位置。通过在扫描过程中识别牙齿区域和牙位信息，建立一个以牙齿排列方向的旋转坐标系，根据旋转坐标系旋转牙齿粗网格三维模型可以有效提升坐标转换的成功率。
现有的齿科数字化扫描过程中，需要建立一个完整的订单信息，该信息包含本次修复需要的必要信息，一般可以分为2类，第一类是指病人的基本信息，主要是编号、名称等；第二类是指修复类型信息包含需要修复的牙位信息，修复类型，齿色，牙齿设计相关信息。而修复类型信息是开展扫描必须要提前确认的信息，所以在扫描前必须填充完整才能由扫描软件根据这些信息创建必要的扫描流程来完成数据采集工作。
所述方法还包括：根据所述齿科识别数据，生成订单信息。
具体地，先进行扫描操作，分析所述齿科识别数据，获得牙位信息和修复类型信息；根据所述牙位信息和所述修复类型，再生成订单信息。用户可以根据扫描得到的所述订单信息与一开始填报第一类信息进行校对。其中，订单信息包括病人信息和修复类型信息，病人信息是基于人员的输入病人的基本情况，修复类型信息包含需要修复的牙位信息，修复类型，齿色，牙齿设计相关信息。在一个实施例中，通过识别模型对牙齿粗网格三维模型进行分析识别，能够准确的提取出牙位信息和修复类型信息，根据所述牙位信息和所述修复类型，生成订单信息。无需提前输入订单信息，自动扫描牙齿粗网格三维模型获得订单信息。
通过上述步骤，通过分别对牙齿粗网格三维模型中扫描杆区域外的粗网格数据和牙齿粗网格三维模型中扫描杆区域的粗网格数据进行融合处理，解决了模型细节保留和整体融合效率之间的平衡问题。
本实施例还提供了一种牙齿扫描方法。图2是根据本申请实施例的另一种牙齿扫描方法的流程图，如图2所示，该流程包括如下步骤：
步骤S301，获取三维扫描仪采集的图片。
步骤S302，由图片进行三维重建，获取点云。
步骤S303，将多片点云拼接优化。
具体地，将多片点云在世界坐标系中进行拼接优化。
步骤S304，快速融合建立牙齿粗网格三维模型。
具体地，将多个点云进行融合处理，建立牙齿粗网格三维模型。
步骤S305，通过识别模型识别牙齿粗网格三维模型，获得齿科识别数据。
具体地，根据所述齿科识别数据可以分别进行四种操作。
第一种：
步骤S306，基于牙位信息和修复类型，生成订单信息。
步骤S307，订单校对。
具体地，分析所述齿科识别数据，获得牙位信息和修复类型信息；根据所述牙位信息和所述修复类型，生成订单信息。用户可以根据扫描得到的所述订单信息与病人一开始填报的信息进行校对。
第二种：
步骤S308，基于修复类型信息、牙齿区域、牙龈区域和底座区域。
具体地，基于修复类型信息、牙齿区域、牙龈区域和底座区域，获得扫描杆区域。
步骤S309，将扫描杆区域的第一粗网格数据进行融合处理，生成第一精网格。
步骤S310，其他区域的第二粗网格数据进行融合处理，生成第二精网格。
具体地步骤S309和步骤S310可以同时进行处理。
步骤S311，将第一精网格和第二精网格，合并成一个整体多分辨率网格模型。
第三种：
步骤S312，基于牙齿区域，确定牙齿区域的牙齿包围盒。
步骤S313，根据裁剪的偏差值和包围盒高度，确定裁剪高度。
具体地，获取牙齿包围盒最低高度Zmin，将包围盒最低高度Zmin减去偏差值d，获得裁剪高度CutZ(CutZ＝Zmin-d)。
步骤S314，根据裁剪高度CutZ，在模型场景中显示裁剪平面。
具体地，根据所述裁切高度将所述牙齿粗网格三维模型进行裁切，并显示裁剪平面。
第四种：
步骤S315，基于牙位信息和牙齿区域，确定牙齿粗网格三维模型的旋转坐标系。
步骤S316，根据旋转坐标系，确定转换的目标位置。
步骤S317，对牙齿粗网格三维模型进行旋转变换，变换目标位置。
需要说明的是，在上述流程中或者附图的流程图中示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行，并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。
本实施例还提供了一种牙齿扫描装置，该装置用于实现上述实施例及优选实施方式，已经进行过说明的不再赘述。如以下所使用的，术语“模块”、“单元”、“子单元”等可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能并被构想的。
图3是根据本申请实施例的牙齿扫描装置的结构框图，如图3所示，该装置包括：扫描模块310、识别模块320、第一提取模块330、第二提取模块340以及建模模块350。
扫描模块310，设置为获取牙齿粗网格三维模型。
识别模块320，设置为将所述牙齿粗网格三维模型输入至识别模型，获得齿科识别数据。
第一提取模块330，设置为根据所述齿科识别数据，分离提取出所述牙齿粗网格三维模型中扫描杆区域对应的第一粗网格数据。
第二提取模块340，设置为获取牙齿粗网格三维模型中扫描杆区域外其他区域对应的第二粗网格数据。
建模模块350，设置为根据所述第一粗网格数据以及第二粗网格数据，生成第一精网格和第二精网格，然后合并生成整体多分辨率网格模型。
建模模块350还被设置为将一个或多个所述第一粗网格数据进行融合处理，获得第一精网格；将一个或多个所述第二粗网格数据进行融合处理，获得第二精网格；根据所述第一精网格和所述第二精网格，合并生成整体多分辨率网格模型。
识别模块320还被设置为建立初始识别模型，将牙齿的网格三维模型作为训练集对识别模型进行训练，获得识别模型，所述识别模型的输入为所述牙齿粗网格三维模型，输出为所述牙齿粗网格三维模型中的齿科识别数据。
图4是根据本申请实施例的牙齿扫描装置的优选结构框图，如图4所示，该装置包括图3所示的所有模块，此外还包括：订单模块410、裁切模块420以及旋转模块430。
裁切模块420设置为根据所述牙齿区域，获得牙齿包围盒；根据所述牙齿包围盒，获得所述牙齿粗网格三维模型的裁切高度。
裁切模块420还被设置为识别所述牙齿包围盒，获得所述包围盒高度；根据所述包围盒高度以及预设偏差值，获得所述牙齿粗网格三维模型的裁切高度。
旋转模块430设置为分根据所述牙齿区域和所述牙位信息，获得旋转坐标系；根据旋转坐标系将所述牙齿粗网格三维模型或所述整体多分辨率网格模型旋转至目标位置。
旋转模块430还被设置为计算所述前牙区域和后牙区域上牙齿的牙列信息，通过牙弓计算方法获得牙弓曲线；根据所述牙弓曲线，获得牙齿粗网格三维模型的Z轴方向；根据所述前牙区域和所述牙弓曲线，获得牙齿粗网格三维模型的X轴方向和Y轴方向；根据所述Z轴方向、所述X轴方向和所述Y轴方向，生成旋转坐标系。
订单模块410设置为根据所述齿科识别数据，生成订单信息。
需要说明的是，上述各个模块可以是功能模块也可以是程序模块，既可以通过软件来实现，也可以通过硬件来实现。对于通过硬件来实现的模块而言，上述各个模块可以位于同一处理器中；或者上述各个模块还可以按照任意组合的形式分别位于不同的处理器中。
需要说明的是，上述各个模块可以是功能模块也可以是程序模块，既可以通过软件来实现，也可以通过硬件来实现。对于通过硬件来实现的模块而言，上述各个模块可以位于同一处理器中；或者上述各个模块还可以按照任意组合的形式分别位于不同的处理器中。
另外，结合图1描述的本申请实施例牙齿扫描方法可以由牙齿扫描设备来实现。图5为根据本申请实施例的牙齿扫描设备的硬件结构示意图。
牙齿扫描设备可以包括处理器81以及存储有计算机程序指令的存储器82。
具体地，上述处理器81可以包括中央处理器(CPU)，或者特定集成电路(Application Specific Integrated Circuit，简称为ASIC)，或者可以被配置成实施本申请实施例的一个或多个集成电路。
其中，存储器82可以包括用于数据或指令的大容量存储器。举例来说而非限制，存储器82可包括硬盘驱动器(Hard Disk Drive，简称为HDD)、软盘驱动器、固态驱动器(Solid State Drive，简称为SSD)、闪存、光盘、磁光盘、磁带或通用串行总线(Universal Serial Bus，简称为USB)驱动器或者两个或更多个以上这些的组合。在合适的情况下，存储器82可包括可移除或不可移除(或固定)的介质。在合适的情况下，存储器82可在数据处理装置的内部或外部。在特定实施例中，存储器82是非易失性(Non-Volatile)存储器。在特定实施例中，存储器82包括只读存储器(Read-Only Memory，简称为ROM)和随机存取存储器(Random Access Memory，简称为RAM)。在合适的情况下，该ROM可以是掩模编程的ROM、可编程ROM(Programmable Read-Only Memory，简称为PROM)、可擦除PROM(Erasable Programmable Read-Only Memory，简称为EPROM)、电可擦除PROM(Electrically Erasable Programmable Read-Only Memory，简称为EEPROM)、电可改写ROM(Electrically Alterable Read-Only Memory，简称为EAROM)或闪存(FLASH)或者两个或更多个以上这些的组合。在合适的情况下，该RAM可以是静态随机存取存储器(Static Random-Access Memory，简称为SRAM)或动态随机存取存储器(Dynamic Random Access Memory，简称为DRAM)，其中，DRAM可以是快速页模式动态随机存取存储器(Fast Page Mode Dynamic Random Access Memory，简称为FPMDRAM)、扩展数据输出动态随机存取存储器(Extended Date Out Dynamic Random Access Memory，简称为EDODRAM)、同步动态随机存取内存(Synchronous Dynamic Random-Access Memory，简称SDRAM)等。
存储器82可以用来存储或者缓存需要处理和/或通信使用的各种数据文件，以及处理器81所执行的可能的计算机程序指令。
处理器81通过读取并执行存储器82中存储的计算机程序指令，以实现上述实施例中的任意一种牙齿扫描方法。
在其中一些实施例中，牙齿扫描设备还可包括通信接口83和总线80。其中，如图5所示，处理器81、存储器82、通信接口83通过总线80连接并完成相互间的通信。
通信接口83用于实现本申请实施例中各模块、装置、单元和/或设备之间的通信。 通信端口83还可以实现与其他部件例如：外接设备、图像/数据采集设备、数据库、外部存储以及图像/数据处理工作站等之间进行数据通信。
总线80包括硬件、软件或两者，将牙齿扫描设备的部件彼此耦接在一起。总线80包括但不限于以下至少之一：数据总线(Data Bus)、地址总线(Address Bus)、控制总线(Control Bus)、扩展总线(Expansion Bus)、局部总线(Local Bus)。举例来说而非限制，总线80可包括图形加速接口(Accelerated Graphics Port，简称为AGP)或其他图形总线、增强工业标准架构(Extended Industry Standard Architecture，简称为EISA)总线、前端总线(Front Side Bus，简称为FSB)、超传输(Hyper Transport，简称为HT)互连、工业标准架构(Industry Standard Architecture，简称为ISA)总线、无线带宽(InfiniBand)互连、低引脚数(Low Pin Count，简称为LPC)总线、存储器总线、微信道架构(Micro Channel Architecture，简称为MCA)总线、外围组件互连(Peripheral Component Interconnect，简称为PCI)总线、PCI-Express(PCI-X)总线、串行高级技术附件(Serial Advanced Technology Attachment，简称为SATA)总线、视频电子标准协会局部(Video Electronics Standards Association Local Bus，简称为VLB)总线或其他合适的总线或者两个或更多个以上这些的组合。在合适的情况下，总线80可包括一个或多个总线。尽管本申请实施例描述和示出了特定的总线，但本申请考虑任何合适的总线或互连。
该牙齿扫描设备可以基于获取到的牙齿扫描数据，执行本申请实施例中的牙齿扫描方法，从而实现结合图1描述的牙齿扫描方法。
另外，结合上述实施例中的牙齿扫描方法，本申请实施例可提供一种计算机可读存储介质来实现。该计算机可读存储介质上存储有计算机程序指令；该计算机程序指令被处理器执行时实现上述实施例中的任意一种牙齿扫描方法。
以上所述实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请专利的保护范围应以所附权利要求为准。
工业实用性
本发明实施例提供的方案，可以应用于对牙齿扫描的过程中。通过本发明实施例解决了现有技术无法协调模型细节保留和整体融合效率之间平衡的技术问题，实现对扫描杆的自动化提取，提高了牙齿扫描效率。

Claims (11)

  1. 一种牙齿扫描方法，包括：
    获取牙齿粗网格三维模型；
    将所述牙齿粗网格三维模型输入至识别模型，获得齿科识别数据；
    根据所述齿科识别数据，分离提取出所述牙齿粗网格三维模型中扫描杆区域对应的第一粗网格数据；
    获取牙齿粗网格三维模型中扫描杆区域外其他区域对应的第二粗网格数据；
    根据所述第一粗网格数据以及第二粗网格数据，生成第一精网格和第二精网格，然后合并生成整体多分辨率网格模型。
  2. 根据权利要求1所述的牙齿扫描方法，其中，所述根据所述第一粗网格数据以及第二粗网格数据，生成第一精网格和第二精网格，然后合并生成整体多分辨率网格模型包括：
    将一个或多个所述第一粗网格数据进行融合处理，获得第一精网格；
    将一个或多个所述第二粗网格数据进行融合处理，获得第二精网格；
    根据所述第一精网格和所述第二精网格，合并生成整体多分辨率网格模型。
  3. 根据权利要求1所述的牙齿扫描方法，其中，所述将所述牙齿粗网格三维模型输入至预设的识别模型中，获得齿科识别数据之前包括：
    建立初始识别模型，将牙齿的网格三维模型作为训练集对识别模型进行训练，获得识别模型，所述识别模型的输入为所述牙齿粗网格三维模型，输出为所述牙齿粗网格三维模型中的齿科识别数据。
  4. 根据权利要求1所述的牙齿扫描方法，其中，所述方法还包括：
    所述齿科识别数据包括：牙齿区域、牙位信息、修复类型信息、牙龈区域以及底座区域中至少一项；
    根据所述牙齿区域，获得牙齿包围盒；
    根据所述牙齿包围盒，获得所述牙齿粗网格三维模型的裁切高度。
  5. 根据权利要求4所述的牙齿扫描方法，其中，所述根据所述牙齿包围盒，获得所述牙齿粗网格三维模型的裁切高度包括：
    识别所述牙齿包围盒，获得所述包围盒高度；
    根据所述包围盒高度以及预设偏差值，获得所述牙齿粗网格三维模型的裁切高度。
  6. 根据权利要求1所述的牙齿扫描方法，其中，所述方法还包括：
    所述齿科识别数据包括：牙齿区域、牙位信息、修复类型信息、牙龈区域以及底座区域中至少一项；
    根据所述牙齿区域和所述牙位信息，获得旋转坐标系；
    根据旋转坐标系将所述牙齿粗网格三维模型或所述整体多分辨率网格模型旋转至目标位置。
  7. 根据权利要求6所述的牙齿扫描方法，其中，所述根据所述牙齿区域和所述牙位信息，获得旋转坐标系包括：所述牙位信息包括牙齿的牙列信息，所述牙齿区域包括前牙区域以及后牙区域；
    计算所述前牙区域和后牙区域上牙齿的牙列信息，通过牙弓计算方法获得牙弓曲线；
    根据所述牙弓曲线，获得牙齿粗网格三维模型的Z轴方向；
    根据所述前牙区域和所述牙弓曲线，获得牙齿粗网格三维模型的X轴方向和Y轴方向；
    根据所述Z轴方向、所述X轴方向和所述Y轴方向，生成旋转坐标系。
  8. 根据权利要求1所述的牙齿扫描方法，其中，所述方法还包括：
    根据所述齿科识别数据，生成订单信息。
  9. 一种牙齿扫描装置，包括：
    扫描模块，设置为获取牙齿粗网格三维模型；
    识别模块，设置为将所述牙齿粗网格三维模型输入至识别模型，获得齿科识别数据；
    第一提取模块，设置为根据所述齿科识别数据，分离提取出所述牙齿粗网格三维模型中扫描杆区域对应的第一粗网格数据；
    第二提取模块，设置为获取牙齿粗网格三维模型中扫描杆区域外其他区域对应的第二粗网格数据；
    建模模块，设置为根据所述第一粗网格数据以及第二粗网格数据，生成第一 精网格和第二精网格，然后合并生成整体多分辨率网格模型。
  10. 一种计算机设备，包括存储器、处理器以及存储在所述存储器上并可在所述处理器上运行的计算机程序，其中，所述处理器执行所述计算机程序时实现如权利要求1至8中任一项所述的牙齿扫描方法。
  11. 一种计算机可读存储介质，其上存储有计算机程序，其中，该程序被处理器执行时实现如权利要求1至8中任一项所述的牙齿扫描方法。
PCT/CN2021/093685 2020-05-29 2021-05-13 牙齿扫描方法、装置、计算机设备和计算机可读存储介质 WO2021238673A1 (zh)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN202010476785 2020-05-29
CN202010476785.5 2020-05-29
CN202010691617.8 2020-07-17
CN202010691617.8A CN111798571A (zh) 2020-05-29 2020-07-17 牙齿扫描方法、装置、系统和计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2021238673A1 true WO2021238673A1 (zh) 2021-12-02

Family

ID=72807633

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/093685 WO2021238673A1 (zh) 2020-05-29 2021-05-13 牙齿扫描方法、装置、计算机设备和计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN111798571A (zh)
WO (1) WO2021238673A1 (zh)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115062697A (zh) * 2022-06-09 2022-09-16 江西日月明测控科技股份有限公司 轨道不平顺识别方法、系统、计算机设备及可读存储介质
CN115179553A (zh) * 2022-07-27 2022-10-14 沈阳京盛正和医学科技有限公司 一种牙科3d打印排版软件的排版方法及系统
CN115192227A (zh) * 2022-07-08 2022-10-18 先临三维科技股份有限公司 牙齿标架调整方法、装置、设备及存储介质
CN115984529A (zh) * 2023-03-20 2023-04-18 佛山科学技术学院 口腔内牙齿三维模型自动分割方法
CN115984470A (zh) * 2022-12-30 2023-04-18 江苏创英医疗器械有限公司 一种基于图像识别技术的种植牙建模方法及系统
CN116524118A (zh) * 2023-04-17 2023-08-01 杭州雅智医疗技术有限公司 基于三维牙齿cbct数据和口腔扫描模型的多模态渲染方法
CN116543912A (zh) * 2023-04-26 2023-08-04 维视医疗信息科技(山东)有限公司 一种基于云平台的齿科协同设计系统

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111798571A (zh) * 2020-05-29 2020-10-20 先临三维科技股份有限公司 牙齿扫描方法、装置、系统和计算机可读存储介质
CN112790887A (zh) * 2020-12-31 2021-05-14 深圳市维新登拓医疗科技有限公司 口腔成像方法、系统及装置、可读存储介质
CN113256773B (zh) * 2021-05-10 2022-10-28 青岛小鸟看看科技有限公司 表面网格扫描及显示方法、系统及装置
CN113610956B (zh) * 2021-06-17 2024-05-28 深圳市菲森科技有限公司 一种口内扫描中特征匹配种植体的方法、装置及相关设备
CN116244730B (zh) * 2022-12-14 2023-10-13 思看科技(杭州)股份有限公司 一种数据保护方法、装置和存储介质
CN118247445A (zh) * 2024-05-30 2024-06-25 先临三维科技股份有限公司 数据处理方法、装置、设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105287039A (zh) * 2015-10-12 2016-02-03 深圳市康泰健牙科器材有限公司 一种口腔内种植体的扫描方法及系统
EP3298983A1 (en) * 2016-09-21 2018-03-28 Global Dental Science LLC System for registering implant orientation directly from a dental impression
CN108629838A (zh) * 2018-03-20 2018-10-09 北京正齐口腔医疗技术有限公司 三维牙冠网格模型的孔洞修补方法及装置
US20190223990A1 (en) * 2016-10-05 2019-07-25 MIS Implants Technologies Ltd. Scan post, bite pillar, reference pillar and related methods for recording dental implant position
CN111798571A (zh) * 2020-05-29 2020-10-20 先临三维科技股份有限公司 牙齿扫描方法、装置、系统和计算机可读存储介质

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8199988B2 (en) * 2008-05-16 2012-06-12 Geodigm Corporation Method and apparatus for combining 3D dental scans with other 3D data sets
US9083960B2 (en) * 2013-01-30 2015-07-14 Qualcomm Incorporated Real-time 3D reconstruction with power efficient depth sensor usage
US9510757B2 (en) * 2014-05-07 2016-12-06 Align Technology, Inc. Identification of areas of interest during intraoral scans
CN105046750B (zh) * 2015-08-24 2017-08-15 杭州美齐科技有限公司 一种自动分割全颌牙齿三角网格模型的方法
WO2017079660A1 (en) * 2015-11-04 2017-05-11 Intel Corporation High-fidelity 3d reconstruction using facial features lookup and skeletal poses in voxel models
CN105748163B (zh) * 2016-02-05 2018-07-31 杭州美齐科技有限公司 一种计算机辅助牙齿无托槽隐形矫治器设计方法
CN108269300B (zh) * 2017-10-31 2019-07-09 先临三维科技股份有限公司 牙齿三维数据重建方法、装置和系统
CN208541294U (zh) * 2018-02-08 2019-02-26 北京富瑞嘉义齿有限公司 一种用于口腔扫描定位的扫描杆
CN108648283B (zh) * 2018-04-02 2022-07-05 北京正齐口腔医疗技术有限公司 牙齿分割方法及装置
CN109009509B (zh) * 2018-09-12 2021-10-01 深圳市康泰健牙科器材有限公司 一种数字化口腔模型的制作方法和系统
CN109387159A (zh) * 2018-09-30 2019-02-26 先临三维科技股份有限公司 确定印模模型的三维扫描数据的方法及装置
CN109410320A (zh) * 2018-09-30 2019-03-01 先临三维科技股份有限公司 三维模型重建方法、装置、计算机设备和存储介质
CN109801357B (zh) * 2018-12-04 2023-10-31 先临三维科技股份有限公司 显示三维数字模型的方法及装置、存储介质、处理器

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105287039A (zh) * 2015-10-12 2016-02-03 深圳市康泰健牙科器材有限公司 一种口腔内种植体的扫描方法及系统
EP3298983A1 (en) * 2016-09-21 2018-03-28 Global Dental Science LLC System for registering implant orientation directly from a dental impression
US20190223990A1 (en) * 2016-10-05 2019-07-25 MIS Implants Technologies Ltd. Scan post, bite pillar, reference pillar and related methods for recording dental implant position
CN108629838A (zh) * 2018-03-20 2018-10-09 北京正齐口腔医疗技术有限公司 三维牙冠网格模型的孔洞修补方法及装置
CN111798571A (zh) * 2020-05-29 2020-10-20 先临三维科技股份有限公司 牙齿扫描方法、装置、系统和计算机可读存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
WANG DANGXIAO;JIAO JIAN;ZHANG YURU;ZHAO XIAOHAN: "Computer Haptics: Haptic Modeling and Rendering in Virtual Reality Environments", JOURNAL OF COMPUTER-AIDED DESIGN & COMPUTER GRAPHICS, vol. 28, no. 6, 15 June 2016 (2016-06-15), pages 881 - 885, XP055871570, ISSN: 1003-9775 *

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115062697A (zh) * 2022-06-09 2022-09-16 江西日月明测控科技股份有限公司 轨道不平顺识别方法、系统、计算机设备及可读存储介质
CN115062697B (zh) * 2022-06-09 2024-03-22 江西日月明测控科技股份有限公司 轨道不平顺识别方法、系统、计算机设备及可读存储介质
CN115192227A (zh) * 2022-07-08 2022-10-18 先临三维科技股份有限公司 牙齿标架调整方法、装置、设备及存储介质
CN115179553A (zh) * 2022-07-27 2022-10-14 沈阳京盛正和医学科技有限公司 一种牙科3d打印排版软件的排版方法及系统
CN115984470A (zh) * 2022-12-30 2023-04-18 江苏创英医疗器械有限公司 一种基于图像识别技术的种植牙建模方法及系统
CN115984470B (zh) * 2022-12-30 2023-11-28 江苏创英医疗器械有限公司 一种基于图像识别技术的种植牙建模方法及系统
CN115984529A (zh) * 2023-03-20 2023-04-18 佛山科学技术学院 口腔内牙齿三维模型自动分割方法
CN115984529B (zh) * 2023-03-20 2023-07-18 佛山科学技术学院 口腔内牙齿三维模型自动分割方法
CN116524118A (zh) * 2023-04-17 2023-08-01 杭州雅智医疗技术有限公司 基于三维牙齿cbct数据和口腔扫描模型的多模态渲染方法
CN116524118B (zh) * 2023-04-17 2023-12-22 杭州雅智医疗技术有限公司 基于三维牙齿cbct数据和口腔扫描模型的多模态渲染方法
CN116543912A (zh) * 2023-04-26 2023-08-04 维视医疗信息科技(山东)有限公司 一种基于云平台的齿科协同设计系统
CN116543912B (zh) * 2023-04-26 2024-03-15 山东山大华天软件有限公司 一种基于云平台的齿科协同设计系统

Also Published As

Publication number Publication date
CN111798571A (zh) 2020-10-20

Similar Documents

Publication Publication Date Title
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
CN110363858B (zh) 一种三维人脸重建方法及系统
US20220218449A1 (en) Dental cad automation using deep learning
US11735306B2 (en) Method, system and computer readable storage media for creating three-dimensional dental restorations from two dimensional sketches
DE102019106666A1 (de) Dentale CAD-Automatisierung unter Verwendung von tiefem Lernen
WO2021228207A1 (zh) 齿科扫描方法、装置、计算机设备和计算机可读存储介质
KR20210068077A (ko) 3d모델 생성 방법, 장치, 기기 및 저장매체
DE112014001417T5 (de) Verfahren und Vorrichtung zur Formanalyse, zum Speichern und Abrufen von 3D-Modellen mit Anwendung im automatischen Zahnrestaurationsdesign
KR102288816B1 (ko) 인공지능 기반 치아 수복을 위한 3d 보철물 제작 방법 및 애플리케이션
CN113689538A (zh) 一种视频生成方法、装置、电子设备及存储介质
KR102344521B1 (ko) 진단 및 진료계획 수립 방법 및 이를 위한 3차원 치과영상 제공장치
US20230394687A1 (en) Oral image processing device and oral image processing method
CN115457198A (zh) 牙齿模型生成方法、装置、电子设备和存储介质
CN113344950A (zh) 一种深度学习结合点云语义的cbct图像牙齿分割方法
CN114638838A (zh) 牙齿模型生成方法、装置、设备及存储介质
CN117745939A (zh) 三维数字化模型的获取方法、装置、设备及存储介质
CN117456088A (zh) 三维模型的获取方法、装置、设备及存储介质
CN110269715B (zh) 一种基于ar的根管监测方法及系统
WO2024020560A2 (en) Dental restoration automation
EP4177845A1 (en) Method and apparatus for generating digital model
CN114998549A (zh) 中药材三维数字模型的制作方法与计算机可读取介质
KR20220056760A (ko) 구강 이미지 처리 장치, 및 구강 이미지 처리 방법
KR20220032451A (ko) 치과 치료를 위한 정보 제공 방법 및 그를 수행하는 전자 장치
CN111710426A (zh) 牙齿模型补洞方法、装置、系统和计算机可读存储介质
KR102401135B1 (ko) 디지털 치과 치료 시뮬레이션 방법 및 그 장치

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: 21813268

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21813268

Country of ref document: EP

Kind code of ref document: A1