Method for automatically generating partial denture from three-dimensional oral data and computer-readable recording medium having recorded thereon program for executing same

Abstract

A method for automatically generating a partial denture from three-dimensional oral data comprises the steps of: receiving three-dimensional oral data; generating transformed oral data on the basis of the three-dimensional oral data; determining a boundary line on the basis of the transformed oral data; and generating gingival data on the basis of the transformed oral data and the boundary line. The step of generating gingival data comprises the steps of: determining a gingival region on the basis of the boundary line; generating gingival voxel data on the basis of the gingival region; generating a transformed distance field on the basis of the gingival voxel data by using a first artificial intelligence neural network; and generating the gingival data on the basis of the transformed distance field.

Description

A method for automatically generating a partial denture from three-dimensional oral data and a computer-readable recording medium having recorded thereon a program for executing the method on a computer

[0001] The present invention relates to a method for automatically generating partial dentures from three-dimensional oral data and a computer-readable recording medium having recorded thereon a program for executing the method on a computer. More specifically, the present invention relates to a method for automatically generating dentures from three-dimensional oral data using deep learning and a computer-readable recording medium having recorded thereon a program for executing the method.

[0002] Dentures are custom-made prosthetics developed to compensate for the absence of teeth in a patient's mouth. Dentures may include artificial teeth and gums, which correspond to artificial gums. The accuracy of the gums can be crucial to the perfection of the denture.

[0003] The method of making dentures is gradually changing from the method of making a mold of the oral cavity using alginate and then making the prosthesis manually to the digital method of obtaining oral data using a 3D scanner, designing the prosthesis using a computer, and then 3D printing it.

[0004] One object of the present invention is to provide a method for automatically generating a partial denture from three-dimensional oral data.

[0005] However, the problem to be solved by the present invention is not limited to the problem mentioned above, and may be expanded in various ways without departing from the spirit and scope of the present invention.

[0006] A method for automatically generating a partial denture from three-dimensional oral data according to embodiments of the present invention includes the steps of receiving three-dimensional oral data, generating transformed oral data based on the three-dimensional oral data, determining a boundary line based on the transformed oral data, and generating gingival data based on the transformed oral data and the boundary line. The step of generating the gingival data includes the steps of determining a gingival area based on the boundary line, generating gingival voxel data based on the gingival area, generating a transformed distance field based on the gingival voxel data using a first artificial intelligence neural network, and generating the gingival data based on the transformed distance field.

[0007] In one embodiment, the gingival region is partitioned into a plurality of unit grids, and the gingival voxel data can be generated based on a first equation. The first equation is It could be. is the distance is a function representing a signed distance field (SDF) according to , BA is the gum area, d(x) is a positive scalar value according to the distance, and -d(x) may be a negative scalar value according to the distance.

[0008] In one embodiment, an isosurface of the above-described transformation distance field can be determined. The gingival data corresponding to the isosurface can be generated.

[0009] In one embodiment, the equivalent surface can be generated based on the positive scalar value of the transformed distance field.

[0010] In one embodiment, the first artificial intelligence neural network may be a U-network model including an encoder unit that receives the gum voxel data, a decoder unit that outputs the gum data, and a bridge unit that connects the encoder unit and the decoder unit.

[0011] In one embodiment, a method for automatically generating a partial denture from three-dimensional oral data may further include a step of generating partial denture data based on the converted tooth data and the gingival data. The converted tooth data may be generated using a second artificial intelligence neural network.

[0012] In one embodiment, the transformation distance field may be generated based on the transformed tooth data and a target area including the gingival area. The gingival area may be partitioned into a plurality of unit grids. The transformation distance field may be generated based on a second equation. The second equation may be It could be. is the distance is a function representing a signed distance field (SDF) according to , TA is the target area, d(x) is a positive scalar value according to the distance, and -d(x) may be a negative scalar value according to the distance.

[0013] In one embodiment, an isosurface of the transformed distance field can be determined based on tooth voxel data and the transformed distance field. Partial denture data corresponding to the isosurface can be generated.

[0014] In one embodiment, the tooth voxel data may be generated based on a third equation. The third equation is It could be. is the distance is a function representing a signed distance field (SDF) according to , DA is a tooth area, d(x) is a positive scalar value according to the distance, and -d(x) may be a negative scalar value according to the distance.

[0015] In one embodiment, the transformed tooth data may be three-dimensional mesh data.

[0016] In one embodiment, the step of generating the gum data may further include the step of determining whether the gum area is open data or closed data, and if the gum area is open data, the step of converting the open data into the closed data.

[0017] In one embodiment, the step of converting the open data into the closed data may convert the open data into the closed data based on the open data and the copy open data arranged at a first distance from the open data.

[0018] In one embodiment, the transformed oral data may be data that blocks out an undercut area included in the three-dimensional oral data.

[0019] In one embodiment, a computer-readable recording medium having a program recorded thereon can cause a computer to execute any one of the above methods.

[0020] According to a method for automatically generating a partial denture from three-dimensional oral data and a computer-readable recording medium having recorded thereon a program for executing the method on a computer, a partial denture is automatically generated from the three-dimensional oral data, thereby shortening the time and process for manufacturing the partial denture.

[0021] Furthermore, partial denture data can be generated based on gingival data generated using an artificial intelligence neural network. This can significantly improve the accuracy and efficiency of partial denture data. Furthermore, customized gingival tissue for partial dentures can be manufactured. Furthermore, this can enhance wearer comfort and satisfaction.

[0022] However, the effects of the present invention are not limited to the above-mentioned effects, and may be expanded in various ways without departing from the spirit and scope of the present invention.

[0023] FIG. 1 is a flowchart illustrating a method for automatically generating a partial denture from three-dimensional oral data according to one embodiment of the present invention.

[0024] Figure 2 is a diagram showing the process by which the converted oral data of Figure 1 is generated.

[0025] Figure 3 is a diagram showing the converted oral data of Figure 1.

[0026] Figure 4 is a drawing showing the transformed oral data and boundary lines of Figure 3.

[0027] Figure 5 is a flowchart illustrating a method for generating gingival data of Figure 1.

[0028] Figure 6 is a diagram showing a method for generating closed data of Figure 5.

[0029] Fig. 7 is a diagram showing closed data generated according to the method of Fig. 6.

[0030] Figure 8 is a diagram showing the gingival voxel data of Figure 5.

[0031] FIG. 9 is a diagram showing a first artificial intelligence neural network for generating the transformation distance field of FIG. 8.

[0032] Figure 10 is a drawing showing the conversion distance field of Figure 9.

[0033] Fig. 11 is a diagram showing gingival data generated based on the conversion distance field of Fig. 10.

[0034] Fig. 12 is a drawing showing an example of a method for generating the transformed tooth data of Fig. 1.

[0035] Fig. 13 is a drawing showing an example of the converted tooth data of Fig. 1.

[0036] Fig. 14 is a drawing showing partial denture data of Fig. 1.

[0037] With respect to the embodiments of the present invention disclosed in the text, specific structural and functional descriptions are merely illustrative for the purpose of explaining the embodiments of the present invention, and the embodiments of the present invention may be implemented in various forms and should not be construed as being limited to the embodiments described in the text.

[0038] The present invention is susceptible to various modifications and takes various forms. Specific embodiments are illustrated in the drawings and described in detail herein. However, this is not intended to limit the present invention to specific disclosed forms, but rather to encompass all modifications, equivalents, and alternatives falling within the spirit and technical scope of the present invention.

[0039] While terms like "first" and "second" may be used to describe various components, these components should not be limited by these terms. These terms may be used to distinguish one component from another. For example, without departing from the scope of the present invention, a first component could be referred to as a "second component," and similarly, a second component could also be referred to as a "first component."

[0040] When a component is referred to as being "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components in between. Conversely, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. Other expressions that describe the relationship between components, such as "between" and "directly between" or "adjacent to" and "directly adjacent to", should be interpreted similarly.

[0041] The terminology used in this application is only used to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, it should be understood that the terms "comprise" or "have" indicate the presence of a described feature, number, step, operation, component, part, or combination thereof, but do not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0042] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by those of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and shall not be construed in an idealized or overly formal sense unless explicitly defined herein.

[0043] Meanwhile, if a particular embodiment can be implemented differently, the functions or operations specified within a particular block may occur in a different order than specified in the flowchart. For example, two consecutive blocks may actually be executed substantially simultaneously, or, depending on the related functions or operations, the blocks may be executed in reverse order.

[0044] Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the attached drawings. Identical components in the drawings are designated by the same reference numerals, and redundant descriptions of identical components are omitted.

[0045] FIG. 1 is a flowchart illustrating a method for automatically generating a partial denture from three-dimensional oral data according to one embodiment of the present invention.

[0046] Referring to FIG. 1, a method for automatically generating a partial denture from three-dimensional oral data may include a step of receiving three-dimensional oral data (S100), a step of generating converted oral data (S200), a step of determining a boundary line of a partial denture based on the converted oral data (S300), a step of generating gingival data of the partial denture based on the converted oral data and the boundary line (S400), and a step of generating partial denture data based on the converted tooth data and the gingival data (S100).

[0047] Fig. 2 is a diagram showing the process of generating the converted oral data of Fig. 1. Fig. 3 is a diagram showing the converted oral data (COD) of Fig. 1.

[0048] Referring to FIGS. 1 to 3, the three-dimensional oral cavity data may include an undercut region (UCR). For example, a user may determine an insertion direction of the converted tooth data. For example, the insertion direction may be a first direction (D1). A second direction (D2) may be an opposite direction to the insertion direction. The undercut region (UCR) may include points where at least one point intersects a straight line extending in the second direction (D2). For example, the undercut region (UCR) may be a lower region covered by an upper, voluminous region. For example, a state in which the three-dimensional oral cavity data includes the undercut region (UCR) may be referred to as a first state (ST1).

[0049] In the present embodiment, a block-out may be performed on the undercut region (UCR). The block-out may refer to an operation of filling the undercut region (UCR). For example, the 3D oral cavity data may be 3D mesh data. Since the 3D oral cavity data may be 3D mesh data, the undercut region (UCR) may be 3D mesh data. The block-out+ may refer to an operation of filling the undercut region (UCR) with 3D mesh data. When the block-out is performed on the undercut region (UCR), converted oral cavity data (COD) may be generated. For example, the converted oral cavity data (COD) may not include the undercut region (UCR). A state in which the block-out is performed on the undercut region (UCR) may be referred to as a second state (ST2).

[0050] If the blockout is not performed in the undercut area (UCR), interference with the partial denture may occur. For example, if the blockout is not performed in the undercut area (UCR), the partial denture may not be easily removed. For example, if the blockout is not performed in the undercut area (UCR), the partial denture may not be easily fixed.

[0051] In this embodiment, the blocking out may be performed in the undercut region (UCR). For example, the converted oral data (COD) may not include the undercut region (UCR). Accordingly, interference of a partial denture generated based on the converted oral data (COD) may be reduced. For example, the partial denture generated based on the converted oral data (COD) may be easily removed. For example, the partial denture generated based on the converted oral data (COD) may be easily fixed.

[0052] Figure 4 is a drawing showing the converted oral data (COD) and boundary line (BL) of Figure 3.

[0053] Referring to FIGS. 1 to 4, a boundary line (BL) can be determined. The boundary line (BL) can be determined based on the converted oral data (COD). For example, a user can set the boundary line (BL) in the converted oral data (COD). A gingival region (DR) can be determined based on the boundary line (BL). For example, the gingival region can refer to an area in which the boundary line (BL) is set in the converted oral data (COD). For example, when the gingival region (DR) is set wide, fixation of the partial denture can be facilitated. For example, when the gingival region (DR) is set narrow, the convenience of the partial denture can be increased. For example, the convenience can refer to the comfort of the wearer of the partial denture.

[0054] Figure 5 is a flowchart illustrating a method for generating gingival data of Figure 1.

[0055] Referring to FIGS. 1 to 5, in the present embodiment, the method for generating the gingival data may include a step (S410) of determining the gingival region (DR) based on the transformed oral data (COD) and the boundary line (BL), a step (S420) of determining whether the gingival region (DR) is closed data, a step (S440) of generating gingival voxel data based on the closed data, a step (S450) of generating a transformed distance field based on the gingival voxel data using a first artificial intelligence neural network, and a step (S460) of generating gingival data based on the transformed distance field. The method for generating the gingival data may further include a step (S430) of converting the gingival region (DR) into the closed data when the gingival region (DR) is not the closed data.

[0056] Fig. 6 is a diagram illustrating a method for generating closed data of Fig. 5. Fig. 7 is a diagram illustrating closed data (CBD) generated according to the method of Fig. 6.

[0057] Referring to FIGS. 1 to 7, the gingival region (DR) may be open data (OBD). When the gingival region (DR) is the open data (OBD), the open data (OBD) may be converted into the closed data (CBD). The copied open data (COBD) may be placed at a first distance (DS1) from the open data (OBD). The closed data (CBD) may be generated based on the open data (OBD) and the copied open data (COBD). For example, the space between the open data (OBD) and the copied open data (COBD) may be filled with mesh data. For example, data triangulation may be performed on the open data (OBD) and the copied open data (COBD). For example, Delaunay triangulation can be performed on the open data (OBD) and the copied open data (COBD).

[0058] Figure 8 is a diagram showing the gingival voxel data of Figure 5.

[0059] Referring to FIGS. 1 to 8, the closed data (CBD) can be partitioned into voxels. A signed distance field (SDF) according to the first formula can be calculated based on the closed data (CBD) within the plurality of voxels.

[0060] The first formula above is It could be.

[0061] Here, is the distance is a function representing a signed distance field (SDF) according to , BA is the gum area, d(x) is a positive scalar value according to the distance, and -d(x) may be a negative scalar value according to the distance.

[0062] For example, the encoding distance function representing the encoding distance field may output a value of 0 for an area matching the gingival region (DR). The encoding distance function may output a negative scalar value for an area located inside the gingival region (DR). Additionally, the encoding distance function may output a positive scalar value for an area outside the gingival region (DR).

[0063] The encoding distance field can be generated by connecting areas with the same value of the encoding distance function with a closed curve. A transformation distance field can be generated based on the encoding distance field.

[0064] FIG. 9 is a diagram showing a first artificial intelligence neural network for generating the conversion distance field (CSDF) of FIG. 8.

[0065] Referring to FIGS. 1 to 9, the above-described conversion distance field (CSDF) can be generated using a first artificial intelligence neural network.

[0066] For example, the first artificial intelligence neural network may include a U-network model. For example, the first artificial intelligence neural network may include an encoder unit receiving the gingival voxel data (VXD), a decoder unit outputting the transform distance field (CSDF), and a bridge unit connecting the encoder unit and the decoder unit. In one embodiment, the encoder unit may receive the encoded distance field. The encoded distance field may be sampled through a plurality of blocks included in the encoding unit. Specifically, the encoded distance field may pass through a calculation block that sequentially performs a convolution operation, an instance normalization operation, and a ReLu (rectified linear unit) operation. After the number of layers increases by passing through the calculation block multiple times, a max pooling operation may be performed. The determined features may be unsampled through the decoding unit. Specifically, after the above features pass through the above operation block multiple times and the number of layers is reduced, a transposed convolution operation can be performed.

[0067] Fig. 10 is a diagram showing the conversion distance field (CSDF) of Fig. 9. Fig. 11 is a diagram showing gingival data (GID) generated based on the conversion distance field (CSDF) of Fig. 10.

[0068] Referring to FIGS. 1 to 11, a plurality of isosurfaces can be generated based on the above-described conversion distance field (CSDF). The isosurfaces can be surfaces in which areas having the same scalar values ​​of the above-described conversion distance field (CSDF) are connected.

[0069] The gingival data may be generated based on the equivalent surfaces corresponding to the scalar value of the above-described conversion distance field (CSDF) of 0. For example, an area in which the scalar value of the above-described conversion distance field has a value of 0 may be set as an area of ​​interest. The gingival data (GID) may be generated from the area of ​​interest. In one embodiment, the gingival data may be data in the form of a scalar field according to the above-described conversion distance field (CSDF).

[0070] In one embodiment, the gingival data (GID) may be generated based on the isosurfaces corresponding to the positive scalar value of the conversion distance field (CSDF). When the gingival data (GID) is generated based on the isosurfaces corresponding to the positive scalar value, the margin of the partial denture may be secured. For example, the gingival data (GID) may be generated from the region of interest by setting an area in which the value of the coded distance function is 0 as the region of interest. In one embodiment, the gingival data (GID) may be data in the form of a scalar field according to the coded distance field.

[0071] In this embodiment, the gingival data (GID) may be three-dimensional mesh data. The isosurfaces may be voxel data. The isosurfaces may be converted into the gingival data (GID) using a marching cube algorithm. The marching cube algorithm may convert the isosurface of the transformation distance field (CSDF) into three-dimensional mesh data.

[0072] According to the above marching cube algorithm, the gingival data (GID) can be generated.

[0073] Fig. 12 is a diagram showing an example of a method for generating the converted tooth data of Fig. 1. Fig. 13 is a diagram showing an example of the converted tooth data (CDD) of Fig. 1. Fig. 14 is a diagram showing the partial denture data (PDD) of Fig. 1.

[0074] Referring to FIGS. 1 to 14, in one embodiment, transformed tooth data (CDD) may be generated using a second artificial intelligence neural network. For example, the second artificial intelligence neural network may generate transformed tooth data based on three-dimensional tooth data.

[0075] For example, the 3D tooth data may be a 3D tooth library model. The 3D tooth library model is a type of sample tooth (standard tooth) used to manufacture prosthetics, implants, braces, etc., and may have a typical tooth shape. The tooth library model may have one sample tooth (standard tooth) for each tooth number. The 3D tooth library model may be a tooth model with a high degree of mesh completion. Therefore, when the 3D tooth library model is modified to manufacture prosthetics, dentures, implants, braces, etc., it may be very suitable for using a 3D printing method. Therefore, when the 3D tooth library model is aligned with the patient's oral data, it can be a suitable intermediate model for digitally manufacturing prosthetics, dentures, implants, braces, etc.

[0076] In one embodiment, the three-dimensional tooth data may be converted into two-dimensional tooth depth data. The two-dimensional tooth depth data may be data in which length information, depth information, or information contained in a point or surface of the two-dimensional tooth depth data is mapped from a specific point, a specific axis, or a specific plane.

[0077] The second artificial intelligence neural network can receive the two-dimensional tooth depth data. The second artificial intelligence neural network can generate the transformed tooth data based on the two-dimensional tooth depth data.

[0078] The second artificial intelligence neural network may include a Generative Adversarial Networks (GAN) model. The GAN model allows a generator (G) to generate tooth depth data of the 3D tooth data, and a discriminator (D) to compare the depth data with the depth data of the reference tooth data to determine which depth data is more likely to be real. By repeating the judgment process, the generator (G) may generate more realistic depth data to deceive the discriminator (D), and the discriminator (D) may learn to better discriminate real data.

[0079] In one embodiment, the transformed tooth data may be three-dimensional mesh data. In one embodiment, the transformed distance field may be generated based on the transformed tooth data and a target area including the gingival area.

[0080] In one embodiment, the conversion distance field may be generated based on a second formula. The second formula may be It could be.

[0081] Here, is the distance is a function representing a signed distance field (SDF) according to , TA is the target area, d(x) is a positive scalar value according to the distance, and -d(x) may be a negative scalar value according to the distance.

[0082] In one embodiment, tooth voxel data can be generated. The equivalent surface of the transformed distance field can be determined based on the tooth voxel data and the gingival voxel data. The transformed tooth data can be three-dimensional mesh data. The transformed tooth data can be converted into the tooth voxel data. The tooth voxel data can be voxel data. For example, the tooth voxel data can be generated based on the third equation. The third equation is It could be.

[0083] Here, is the distance is a function representing a signed distance field (SDF) according to , DA is a tooth area, d(x) is a positive scalar value according to the distance, and -d(x) may be a negative scalar value according to the distance.

[0084] The above tooth region may mean a region including the above-mentioned transformed tooth data.

[0085] The above-mentioned isosurfaces can be generated from the above-mentioned tooth voxel data and the above-mentioned transformation distance field (CSDF). The above-mentioned isosurfaces can be surfaces in which areas having the same scalar values ​​of the above-mentioned transformation distance field (CSDF) are connected.

[0086] The above isosurfaces can be generated using the above marching cube algorithm for the partial denture data. The above marching cube algorithm can convert the isosurfaces of the tooth voxel data and the transformed distance field (CSDF) into three-dimensional mesh data.

[0087] Partial denture data (PDD) can be generated based on the above tooth voxel data and the above transformed distance field (CSDF).

[0088] In this embodiment, partial denture data (PDD) can be generated based on the gingival data (GID). Accordingly, the accuracy and efficiency of the PDD can be significantly improved. Furthermore, customized gingiva for partial dentures can be manufactured. Furthermore, the comfort and satisfaction of the wearer can be enhanced.

[0089] The present invention relates to a method for automatically generating a partial denture from three-dimensional oral data and a computer-readable recording medium having recorded thereon a program for executing the method on a computer, which can reduce the effort and time required for producing a partial denture and improve the accuracy and productivity of the partial denture.

[0090] Although the present invention has been described with reference to the above embodiments, it will be understood by those skilled in the art that various modifications and changes can be made to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below.

Claims

1. A step of receiving 3D oral data; A step of generating transformed oral data based on the above three-dimensional oral data; A step of determining a boundary line based on the above-mentioned transformed oral data; and A step of generating gingival data based on the above-described transformed oral data and the above-described boundary line is included. The steps for generating the above gum data are: A step of determining the gingival area based on the above boundary line; A step of generating gingival voxel data based on the above gingival area; A step of generating a transformation distance field based on the gum voxel data using a first artificial intelligence neural network; and A method for automatically generating a partial denture from three-dimensional oral data, characterized in that it comprises a step of generating the gingival data based on the above-mentioned transformation distance field.

2. In the first paragraph, the gum area is divided into a plurality of unit grids, The above gum voxel data is, [Formula 1] (Here, is the distance A method for automatically generating a partial denture from three-dimensional oral data, characterized in that the method is generated based on a function representing a signed distance field (SDF) according to , BA is the gingival area, d(x) is a positive scalar value according to the distance, and -d(x) is a negative scalar value according to the distance.

3. In the second paragraph, the iso-surface of the conversion distance field is determined, A method for automatically generating a partial denture from three-dimensional oral data, characterized in that the gingival data corresponding to the above equivalent surface is generated.

4. A method for automatically generating a partial denture from three-dimensional oral data, characterized in that in the third paragraph, the equivalent surface is generated based on the positive scalar value of the transformation distance field.

5. In the second paragraph, the first artificial intelligence neural network, An encoder unit receiving the above gum voxel data; A decoder unit for outputting the above gum data; and A method for automatically generating a partial denture from three-dimensional oral data, characterized in that the U-network model includes a bridge section connecting the encoder section and the decoder section.

6. In paragraph 1, Further comprising a step of generating partial denture data based on the converted tooth data and the gingival data, A method for automatically generating a partial denture from three-dimensional oral data, characterized in that the above-mentioned converted tooth data is generated using a second artificial intelligence neural network.

7. A method for automatically generating a partial denture from three-dimensional oral data, characterized in that in paragraph 6, the second artificial intelligence neural network receives two-dimensional tooth depth data and generates the transformed tooth data based on the two-dimensional tooth depth data.

8. In the 6th paragraph, the conversion distance field is generated based on the conversion tooth data and the target area including the gingival area, The above gingival area is divided into multiple unit grids, The above conversion distance field is, [Second Formula] (Here, is the distance A method for automatically generating a partial denture from three-dimensional oral data, characterized in that the method is generated based on a function representing a signed distance field (SDF) according to , TA is the target area, d(x) is a positive scalar value according to the distance, and -d(x) is a negative scalar value according to the distance.

9. In paragraph 6, Based on the tooth voxel data and the above-mentioned transformation distance field, the iso-surface of the above-mentioned transformation distance field is determined, A method for automatically generating a partial denture from three-dimensional oral data, characterized in that the partial denture data corresponding to the above equivalent surface is generated.

10. In the 9th paragraph, the tooth voxel data is, [Formula 3] (Here, is the distance A method for automatically generating a partial denture from three-dimensional oral data, characterized in that the method is generated based on a function representing a signed distance field (SDF) according to , DA is a tooth area, d(x) is a positive scalar value according to the distance, and -d(x) is a negative scalar value according to the distance.

11. A method for automatically generating a partial denture from three-dimensional oral data, characterized in that the converted tooth data in the sixth paragraph is three-dimensional mesh data.

12. In the first paragraph, the step of generating the gum data comprises: A step of determining whether the above gum area is open data or closed data; and A method for automatically generating a partial denture from three-dimensional oral data, characterized in that the method further comprises a step of converting the open data into the closed data when the gingival area is the open data.

13. In the 12th paragraph, the step of converting the open data into the closed data A method for automatically generating a partial denture from three-dimensional oral data, characterized in that the open data and the copy open data arranged at a first distance and the open data are converted into the closed data based on the open data.

14. A method for automatically generating a partial denture from three-dimensional oral data, characterized in that in the first paragraph, the converted oral data is data in which an undercut area included in the three-dimensional oral data is blocked out.

15. A computer-readable recording medium having recorded thereon a program for executing the method of any one of claims 1 to 14 on a computer.

Images