A tooth center positioning method of an oral scanning dental mold, a storage medium and an electronic device

Abstract

The application provides a tooth center positioning method of an oral scanning dental mold, a storage medium and an electronic device, and the method comprises the following steps: acquiring an oral scanning dental mold image, generating a tooth depth image according to the relief degree information of each tooth in the oral scanning dental mold image; segmenting the tooth depth image, identifying a plurality of first tooth information, and adding identification information to each first tooth information; processing the first tooth information with the same identification information respectively, determining the maximum connected domain of the first tooth information with the same identification information, and obtaining the second tooth information corresponding to each identification information; and determining the center point coordinates corresponding to the second tooth information according to the coordinate positions of the pixel points in the second tooth information. The above scheme is based on the relief degree information of the tooth for processing when positioning the tooth center, so that the positioned center is more accurate, and the accuracy of subsequent operations is improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to a tooth center positioning method, storage medium and electronic equipment for oral scanning dental models. Background Art

[0002] With the continuous development of digital dental technology, oral auxiliary diagnosis and treatment systems based on 3D digital technology rely on the establishment of a 3D digital model of the patient's teeth and gums. This is achieved by traditionally creating a plaster model by occluding the patient in silicone rubber and then scanning the plaster model, or by using a digital intraoral scanner to directly obtain a 3D digital tooth and gum model of the patient. The resulting tooth model data is highly accurate.

[0003] Tooth center location is a crucial step in oral scan diagnosis, providing crucial support for subsequent 3D dental arch curve generation, tooth segmentation, and tooth posture positioning. Existing tooth center location methods fail to account for the contours of individual teeth, resulting in inaccurate tooth center locations. This impacts the accuracy of subsequent operations, such as 3D dental arch curve generation, tooth segmentation, and tooth posture positioning. Summary of the Invention

[0004] Therefore, it is necessary to provide a technical solution for generating dental models to solve the problem that the existing tooth center positioning method is not accurate enough, which affects the accuracy of subsequent image processing.

[0005] In a first aspect, a method for locating the center of a tooth using an oral scan dental model comprises the following steps:

[0006] S1: Acquire an oral scan dental model image, and generate a tooth depth image based on the undulation information of each tooth in the oral scan dental model image;

[0007] S2: Segmenting the tooth depth image to identify a plurality of first tooth information, and adding identification information to each of the first tooth information; different first tooth information corresponds to different identification information;

[0008] S3: processing the first tooth information having the same identification information respectively, determining the maximum connected domain of the first tooth information having the same identification information, and obtaining the second tooth information corresponding to each identification information;

[0009] S4: Determine the coordinates of the center point corresponding to the second tooth information according to the coordinate positions of the pixel points in the second tooth information.

[0010] In some embodiments, the oral scan dental model image is a three-dimensional image, and the three-dimensional image is placed in a three-dimensional space coordinate system, and the three-dimensional space coordinate system includes a plurality of grids;

[0011] The generating the tooth depth image according to the relief degree information of each tooth in the mouth scanning dental model image comprises:

[0012] S11: generating a two-dimensional image with pixel value size of each pixel point being 0;

[0013] S12: performing normalization processing on the z coordinate value of the center point of each grid in the mouth scanning dental model image in the tooth height direction;

[0014] S13: sequentially judging whether the pixel value size of the center point of each grid in the mouth scanning dental model image is greater than the pixel value size of the corresponding coordinate point on the two-dimensional image to which the center point of the grid is projected, and if yes, setting the pixel value size of the corresponding coordinate point on the two-dimensional image as the z coordinate value of the center point of the grid in the mouth scanning dental model image;

[0015] S14: traversing all grids in the mouth scanning dental model image to obtain the tooth depth image.

[0016] In some embodiments, the mouth scanning dental model image is a three-dimensional image, the three-dimensional image is placed in a three-dimensional space coordinate system, and the three-dimensional space coordinate system comprises a plurality of grids;

[0017] The generating the tooth depth image according to the relief degree information of each tooth in the mouth scanning dental model image comprises:

[0018] S15: generating a two-dimensional image with pixel value size of each pixel point being 0;

[0019] S16: calculating the distance between the center point of each grid in the mouth scanning dental model image and the center coordinate of each grid in the two-dimensional image one by one, and taking the z coordinate value of the center point of the grid in the mouth scanning dental model image in the tooth height direction as the pixel value of the center coordinate of the corresponding grid in the two-dimensional image;

[0020] S17: traversing all grids on the two-dimensional image to obtain the tooth depth image.

[0021] In some embodiments, the segmenting the tooth depth image and identifying a plurality of first tooth information comprises:

[0022] S21: acquiring a plurality of three-dimensional dental model images, rotating the acquired three-dimensional dental model images in a current coordinate system along a predetermined plane by a predetermined angle to obtain a three-dimensional dental model image training set; the three-dimensional dental model image training set comprises images of each three-dimensional dental model image before and after rotation at different angles;

[0023] S22: randomly cropping the three-dimensional dental model image training set, and generating a corresponding tooth depth image according to the cropped image to obtain a tooth depth image training set;

[0024] S23: input the tooth depth image training set into a neural network model for tooth information segmentation training, to obtain a trained neural network model;

[0025] S24: input the tooth depth information generated by the mouth scanning model into the trained neural network model, to identify a plurality of first tooth information.

[0026] In some embodiments, the first tooth information with the same identification information is processed respectively, and the maximum connected domain of the first tooth information with the same identification information is determined including:

[0027] The first tooth information with the same identification information is sequentially subjected to expansion processing and erosion processing, so as to determine the maximum connected domain of the first tooth information with the same identification information.

[0028] The expansion processing includes: taking each pixel point contained in the first tooth information with a certain same identification information as the center, setting the identification information of the neighborhood pixel point of each pixel point as the current same identification information.

[0029] The erosion processing includes: judging whether the identification information of the neighborhood pixel point of each pixel point with a certain same identification information after the expansion processing is consistent, if yes, the pixel point is retained; otherwise, the pixel point is removed.

[0030] In some embodiments, the first tooth information with the same identification information is sequentially subjected to expansion processing and erosion processing including:

[0031] According to the distribution position of the first tooth information with a certain same identification information, the range of a plurality of regions of the first tooth information with the same identification information is determined; the pixel points in the same region are sequentially connected.

[0032] The distance between each region edge and other region edges is calculated respectively, the pixel points in the two regions with the closest edge distance are subjected to first degree expansion processing and erosion processing, and the pixel points in other regions are subjected to second degree expansion processing and erosion processing; the first degree is higher than the second degree.

[0033] In some embodiments, the expansion processing and the erosion processing include:

[0034] Any one of the following: first expansion processing, then erosion processing; first expansion processing, then erosion processing, and then second expansion processing, then erosion processing; first twice expansion processing, then twice erosion processing; first three times expansion processing, then three times erosion processing; first expansion processing, then erosion processing.

[0035] In some embodiments, the mouth scan impression image is a mouth scan impression image after the correction; the mouth scan impression image before the correction is recorded as a first mouth scan impression image, and the mouth scan impression image after the correction is recorded as a second mouth scan impression image, and the second mouth scan impression image is obtained according to the following manner:

[0036] S51: identifying the first mouth scan impression image in the first coordinate system, and segmenting a plurality of tooth images on the first mouth scan impression image;

[0037] S52: dividing all the extracted tooth images into at least three tooth image groups, and calculating second center of gravity coordinates of the at least three tooth image groups; each tooth image group contains one or more tooth images; the tooth image groups include a first tooth image group, a second tooth image group, and a third tooth image group; the second center of gravity coordinates of the first tooth image group are recorded as A, the second center of gravity coordinates of the second tooth image group are recorded as B, and the second center of gravity coordinates of the third tooth image group are recorded as C; the midpoint of BC is recorded as D point;

[0038] S53: taking the midpoint of triangle ABC as the coordinate origin O of the second coordinate system, taking the vector OD as the Y axis of the second coordinate system, taking the normal vector of the plane on which triangle ABC is located as the Z axis of the second coordinate system, and determining the X of the second coordinate system according to the Y axis and the Z axis of the second coordinate system;

[0039] S54: calculating a transformation matrix of the first coordinate system and the second coordinate system, correcting the position of the first mouth scan impression image in the first coordinate system according to the transformation matrix, and obtaining a second mouth scan impression image.

[0040] In a second aspect, the present application further provides a storage medium, the storage medium storing a computer program, and the computer program is executed by a processor to realize the method steps of the first aspect of the present application.

[0041] In a third aspect, the present application further provides an electronic device, which includes a processor and a storage medium, and the storage medium is the storage medium of the second aspect.

[0042] The processor is used to execute the computer program stored in the storage medium to realize the method steps of the first aspect.

[0043] Different from the prior art, the present application provides a tooth center positioning method of an oral scanning dental mold, a storage medium and an electronic device, the method comprising the following steps: acquiring an oral scanning dental mold image, generating a tooth depth image according to the relief degree information of each tooth in the oral scanning dental mold image; segmenting the tooth depth image, identifying a plurality of first tooth information, and adding identification information to each first tooth information; processing the first tooth information with the same identification information respectively, determining the maximum connected domain of the first tooth information with the same identification information, and obtaining the second tooth information corresponding to each identification information; and determining the center point coordinates corresponding to the second tooth information according to the coordinate positions of the pixel points in the second tooth information. The above scheme is based on the relief degree information of the tooth for processing when positioning the tooth center, which can make the positioned center more accurate and improve the accuracy of subsequent operations. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 Flow chart of the tooth center positioning method of the oral scanning dental mold according to the first embodiment of the present application;

[0045] Figure 2 Flow chart of the tooth center positioning method of the oral scanning dental mold according to the second embodiment of the present application;

[0046] Figure 3 Flow chart of the tooth center positioning method of the oral scanning dental mold according to the third embodiment of the present application;

[0047] Figure 4 Flow chart of the tooth center positioning method of the oral scanning dental mold according to the fourth embodiment of the present application;

[0048] Figure 5 Flow chart of the tooth center positioning method of the oral scanning dental mold according to the fifth embodiment of the present application;

[0049] Figure 6 Flow chart of the tooth center positioning method of the oral scanning dental mold according to the sixth embodiment of the present application;

[0050] Figure 7 Schematic diagram of the oral scanning dental mold image according to an embodiment of the present application;

[0051] Figure 8 Schematic diagram of the tooth depth image according to an embodiment of the present application;

[0052] Figure 9 Schematic diagram of the tooth depth image after segmentation and identification processing according to an embodiment of the present application;

[0053] Figure 10A diagram of a tooth depth image after inflation corrosion processing according to an embodiment of the present application;

[0054] Figure 11 A diagram of first tooth information before maximum connected region confirmation according to an embodiment of the present application;

[0055] Figure 12 A diagram of second tooth information after maximum connected region confirmation according to an embodiment of the present application;

[0056] Figure 13 A diagram of a center point of second tooth information according to an embodiment of the present application;

[0057] Figure 14 A diagram of a pixel point distribution position of first tooth information having the same identification information before inflation processing according to an embodiment of the present application;

[0058] Figure 15 A diagram of a pixel point distribution position of first tooth information having the same identification information after inflation processing according to an embodiment of the present application;

[0059] Figure 16 A diagram of a pixel point distribution position of first tooth information having the same identification information during corrosion processing according to an embodiment of the present application;

[0060] Figure 17 A diagram of a pixel point distribution position of second tooth information having the same identification information after corrosion processing according to an embodiment of the present application;

[0061] Figure 18 A diagram of a pixel point distribution position of first tooth information having the same identification information after inflation processing according to another embodiment of the present application;

[0062] Figure 19 A diagram of a pixel point distribution position of first tooth information having the same identification information during corrosion processing according to another embodiment of the present application;

[0063] Figure 20 A diagram of an electronic device according to an embodiment of the present application;

[0064] Reference numerals:

[0065] 10, electronic device;

[0066] 101, processor;

[0067] 102, storage medium. DETAILED DESCRIPTION

[0068] To explain the possible application scenarios, technical principles, specific implementation schemes, and the purposes and effects that can be achieved of the present application in detail, the following will be described in detail in combination with the specific embodiments listed and the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present application, and therefore only serve as examples, and cannot limit the protection scope of the present application.

[0069] In this paper, the term "embodiment" means that the specific features, structures or characteristics described in combination with the embodiment can be included in at least one embodiment of the present application. The term "embodiment" appearing at various places in the specification does not necessarily refer to the same embodiment, and does not particularly limit its independence or association with other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, each technical feature mentioned in each embodiment can be combined in any way to form a corresponding implementable technical solution.

[0070] Unless otherwise defined, the meanings of the technical terms used herein are the same as those commonly understood by those skilled in the art to which the present application belongs; the use of related terms in this paper is only for the purpose of describing specific embodiments, and is not intended to limit the present application.

[0071] In the description of the present application, the phrase "and / or" is a description of the logical relationship between the objects, which means that there can be three relationships, for example, A and / or B, which means that there are three cases: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this paper generally represents that the associated objects before and after are a "or" logical relationship.

[0072] In the present application, terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual quantity, primary and secondary or order relationship between the entities or operations.

[0073] Without more limitations, in the present application, the phrases "include", "contain", "have" or other similar expressions used in the sentence are intended to cover non-exclusive inclusion, and these expressions do not exclude the presence of other elements in the process, method or product including the elements, so that the process, method or product including a series of elements can not only include those limited elements, but also include other elements not explicitly listed, or also include the elements inherent to such process, method or product.

[0074] Consistent with the understanding in the Examination Guidelines, in this application, expressions such as "greater than," "less than," and "exceed" are understood to exclude the number itself; expressions such as "above," "below," and "within" are understood to include the number itself. Furthermore, in the description of the embodiments of this application, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this manner, such as "multiple groups," "multiple times," etc., unless otherwise specifically defined.

[0075] like Figure 1 As shown, in a first aspect, the present invention provides a method for locating the center of a tooth using an oral scan dental model, the method comprising the following steps:

[0076] S1: Acquire an oral scan dental model image, and generate a tooth depth image based on the undulation information of each tooth in the oral scan dental model image;

[0077] S2: Segmenting the tooth depth image to identify a plurality of first tooth information, and adding identification information to each of the first tooth information; different first tooth information corresponds to different identification information;

[0078] S3: processing the first tooth information having the same identification information respectively, determining the maximum connected domain of the first tooth information having the same identification information, and obtaining the second tooth information corresponding to each identification information;

[0079] S4: Determine the coordinates of the center point corresponding to the second tooth information according to the coordinate positions of the pixel points in the second tooth information.

[0080] In step S1, the oral scanned dental model image is a three-dimensional image, and the three-dimensional image is placed in a three-dimensional space coordinate system. The three-dimensional image can be generated by scanning the human oral cavity with an oral scanner, or by running a computer program built into a mobile terminal or a cloud server to scan the human oral cavity. Figure 7 shown.

[0081] Typically, an oral scan dental cast image contains multiple tooth images, and the tooth undulation information refers to the degree of concavity and convexity of each tooth along the height direction of the tooth. Assuming that the bottom surface of the oral scan dental cast image is the xoy plane located in the three-dimensional space coordinate system, the tooth undulation information is expressed as the difference in coordinate values ​​of the pixel points contained in each tooth image in the Z-axis direction of the three-dimensional space coordinate system.

[0082] Generating a tooth depth image based on the undulation information of each tooth in the dental model image includes: if the undulation information of the tooth is greater, the difference between the pixel point of the tooth and the background color on the tooth depth image will be more obvious. Figure 8As shown, the tooth depth image corresponding to the lower jaw mouth scanning tooth mold image is shown in FIG. 2B, and the tooth depth image corresponding to the upper jaw mouth scanning tooth mold image is shown in FIG. 2C. Figure 8 As shown in the image, the brightness of the middle teeth is higher than that of other positions, indicating that the fluctuation information of the middle teeth is higher than that of other positions.

[0083] In step S2, the identification information is preferably tooth number information, which is numbered according to the arrangement direction of each first tooth information. The tooth number information can be represented by numbers, letters or other self-defined graphics. The tooth number sequence can be arranged from left to right, from right to left or from the middle to both sides. In other embodiments, the identification information can also be tooth brightness identification or color identification, for example, different teeth are represented by different colors according to the arrangement sequence.

[0084] In step S3, the maximum connected domain of each first tooth information with the same identification information can be determined by comparing the area size of the pixel point region, and the connected domain with smaller area is deleted, so as to remove the erroneous pixel points of the first tooth information in the tooth depth image segmentation. The first tooth information before the maximum connected domain screening is shown in FIG. 3A. Figure 11 As shown, the first tooth information after the maximum connected domain screening is shown in FIG. 3B. Figure 12

[0085] In step S4, the center point coordinates corresponding to the second tooth information are determined according to the following method:

[0086] (1) Calculate the two-dimensional coordinate values of all pixel points in a certain second tooth information, and then obtain the maximum and minimum horizontal and vertical coordinate values, respectively. The average of the maximum horizontal coordinate value and the minimum horizontal coordinate value is taken as the horizontal coordinate value of the center point corresponding to the current second tooth information, and the average of the maximum vertical coordinate value and the minimum vertical coordinate value is taken as the vertical coordinate value of the center point corresponding to the current second tooth information.

[0087] (2) Calculate the two-dimensional coordinate values of all pixel points in a certain second tooth information, and then take the average of the horizontal coordinates of all pixel points as the horizontal coordinate value of the center point corresponding to the current second tooth information, and take the average of the vertical coordinates of all pixel points as the vertical coordinate value of the center point corresponding to the current second tooth information.

[0088] (3) Calculate the two-dimensional coordinate values of all edge pixel points in a certain second tooth information, and then take the average of the horizontal coordinates of all edge pixel points as the horizontal coordinate value of the center point corresponding to the current second tooth information, and take the average of the vertical coordinates of all edge pixel points as the vertical coordinate value of the center point corresponding to the current second tooth information.

[0089] The determined center point position of the second tooth information is shown in FIG. 4B. Figure 13 ​As shown in FIG. 1, the method comprises the following steps. Figure 13 In the method, the white point position inside the circle is the center point position corresponding to the second tooth information.

[0090] In some embodiments, the method further comprises: after determining the center point of each second tooth information, drawing a dental arch curve according to the center points of all second tooth information, and performing smoothing processing on the dental arch curve.

[0091] In some embodiments, the three-dimensional space coordinate system comprises a plurality of grids. Generally, the intraoral scan dental model image is modeled in the form of a grid, and the grid is the smallest unit of the three-dimensional space coordinate system. The more the grids, the higher the accuracy of subsequent image analysis and calculation of the coordinate system.

[0092] As shown in FIG. 1, the method comprises the following steps. Figure 2 generating a tooth depth image according to the relief degree information of each tooth in the intraoral scan dental model image comprises:

[0093] S11: generating a two-dimensional image in which the pixel value of each pixel point is 0;

[0094] S12: performing normalization processing on the z coordinate value of the center point of each grid in the intraoral scan dental model image in the tooth height direction;

[0095] S13: sequentially judging whether the pixel value of the center point of each grid in the intraoral scan dental model image is greater than the pixel value of the corresponding coordinate point on the two-dimensional image to which the center point of the grid is projected, and if so, setting the pixel value of the corresponding coordinate point on the two-dimensional image to the z coordinate value of the center point of the grid in the intraoral scan dental model image;

[0096] S14: traversing all grids in the intraoral scan dental model image to obtain the tooth depth image.

[0097] Preferably, before step S12, the method further comprises: magnifying the x and y coordinate values of the center point of each grid in the intraoral scan dental model image according to a certain proportion. Generally, the x and y coordinate values of the center point of each grid in the three-dimensional space coordinate system are not coordinated in proportion with the x and y coordinate values of the center point of each grid in the two-dimensional image. If the two are directly mapped, the three-dimensional model will be too concentrated in a certain part of the two-dimensional image, and cannot uniformly fill the entire image. Therefore, before mapping, the x and y coordinate values of the center point of each grid in the intraoral scan dental model image are magnified according to a certain proportion, so that the mapped intraoral scan dental model image can be more uniformly expanded in the two-dimensional image.

[0098] If the x, y coordinate values of the plurality of grid center points in the intraoral scanning dental mold image are mapped to the same grid center point in the two-dimensional image, the pixel value of the grid center point in the two-dimensional image is the z coordinate value corresponding to the grid center point with the larger pixel value in the intraoral scanning dental mold image.

[0099] Through steps S11-S14, the intraoral scanning dental mold image in the three-dimensional space coordinate system can be projected into a two-dimensional image, and the relief information of each tooth in the intraoral scanning dental mold image is reflected in the pixel value of the two-dimensional image. The tooth with larger relief information has larger pixel value in the projected two-dimensional image. The image before projection is shown in FIG. 2, and the image after projection is shown in FIG. 3. Figure 7 Figure 8

[0100] As shown in FIG. 4, in another embodiment, the generating of the tooth depth image according to the relief information of each tooth in the intraoral scanning dental mold image comprises: Figure 3

[0101] S15: generating a two-dimensional image with pixel values of all pixel points being 0;

[0102] S16: calculating the distance between the center point of each grid in the intraoral scanning dental mold image and the center coordinate of each grid in the two-dimensional image, and taking the z coordinate value of the center point of the grid in the intraoral scanning dental mold image with the shortest distance along the tooth height direction as the pixel value of the center coordinate of the corresponding grid in the two-dimensional image;

[0103] S17: traversing all grids in the two-dimensional image to obtain the tooth depth image.

[0104] In this embodiment, by calculating the distance between the grids in the three-dimensional image and the grids in the two-dimensional image, each grid in the three-dimensional image is projected onto the grid in the two-dimensional image with the shortest distance. The projected two-dimensional image matches the shape formed by the vertical projection of the three-dimensional image. The center point pixel of each grid in the two-dimensional image is assigned to the z coordinate value of the center point of the grid in the intraoral scanning dental mold image with the shortest distance along the tooth height direction, so that the relief information of each tooth in the intraoral scanning dental mold image is reflected in the pixel value of the two-dimensional image. The tooth with larger relief information has larger pixel value in the projected two-dimensional image. The image before projection is shown in FIG. 5, and the image after projection is shown in FIG. 6. Figure 7 Figure 8

[0105] As shown in FIG. 7, the segmenting of the tooth depth image to identify a plurality of first tooth information comprises: Figure 4

[0106] ​​​​​​S21: Obtain a plurality of three-dimensional dental mold images, rotate the obtained three-dimensional dental mold images by a predetermined angle along a predetermined plane in a current coordinate system to obtain a three-dimensional dental mold image training set; the three-dimensional dental mold image training set includes images of each three-dimensional dental mold image before and after rotation by different angles;

[0107] S22: Randomly crop the three-dimensional dental mold image training set, and generate a corresponding tooth depth image according to the cropped image to obtain a tooth depth image training set;

[0108] S23: Input the tooth depth image training set into a neural network model for tooth information segmentation training to obtain a trained neural network model;

[0109] S24: Input the tooth depth information generated by the oral scanning dental mold image into the trained neural network model to identify a plurality of first tooth information.

[0110] In the embodiment, the neural network model includes but is not limited to unet++ model, unet model, deeplabv3 model, etc. Preferably, the neural network model adopts unet++ model. The above scheme realizes the enhancement of the training data by rotating the three-dimensional dental mold image by a certain angle and randomly cutting, which can effectively improve the recognition accuracy and robustness of the trained neural network model. The image after tooth segmentation is shown in Figure 9

[0111] In some embodiments, the first tooth information with the same identification information is processed respectively, and the maximum connected domain of the first tooth information with the same identification information is determined to include:

[0112] The first tooth information with the same identification information is sequentially subjected to expansion processing and erosion processing, so as to determine the maximum connected domain of the first tooth information with the same identification information;

[0113] The expansion processing includes: taking each pixel point contained in the first tooth information with a certain same identification information as the center, setting the identification information of the neighborhood pixel point of each pixel point as the current same identification information;

[0114] The erosion processing includes: judging whether the identification information of the neighborhood pixel point of each pixel point with a certain same identification information after the expansion processing is consistent, if yes, retaining the pixel point; otherwise, eliminating the pixel point.

[0115] ​Through the inflation processing and the corrosion processing, the case that the first tooth information with the same identification information is mistakenly divided into multiple (such as two) first tooth information when the first tooth information is segmented and identified can be effectively solved, so that the first tooth information with the same identification information is reconnected into one region, and the accuracy of the maximum connected domain determination is effectively improved.

[0116] The following will be described in detail Figures 14-17 The inflation processing and the corrosion processing related to the present application will be described in detail:

[0117] As shown in Figure 14 , it is a pixel point distribution position schematic diagram of the first tooth information with the same identification information before the inflation processing related to an embodiment of the present application. Figure 14 The number "6" in the figure represents the first tooth information with the number information 6. As can be seen from Figure 14 , the first tooth information with the number 6 identified is mainly distributed in the upper left, upper right and lower regions of the image. Among them, the number of pixel points in the upper left and upper right is small, which can be filtered out in the subsequent maximum connected domain size judgment, and there are two rows and three columns of pixel point distribution regions on the left and right sides of the lower region, which may be the tooth information with the number 6 being divided into two blocks when segmented and identified. The purpose of the inflation and corrosion processing operation is to reconnect the two regions together, so that the calculation is based on all the most likely pixel points of the tooth information with the number 6 when positioning the center point, and the accuracy of the center positioning is improved.

[0118] As shown in Figure 15 , it is a pixel point distribution position schematic diagram of the first tooth information with the same identification information after the inflation processing related to an embodiment of the present application. In the inflation processing operation, the identification information of the pixel points in the 8-neighborhood (8-neighborhood is respectively the upper, lower, left, right, upper left, lower left, upper right and lower right of the center pixel point) adjacent to each pixel point of the first tooth information with the number 6 is set to "6", that is, each pixel point is expanded by one circle, and the expanded pixel point distribution is regarded as part of the first tooth information with the number 6, and then the corrosion operation can be performed. The pixel point region expanded by the inflation processing is represented by filled shadow A in Figure 15 .

[0119] As shown in Figure 16 , it is a pixel point distribution position schematic diagram of the first tooth information with the same identification information during the corrosion processing related to an embodiment of the present application. In the corrosion processing operation, the pixel points in the 8-neighborhood (8-neighborhood is respectively the upper, lower, left, right, upper left, lower left, upper right and lower right of the center pixel point) adjacent to each pixel point of the first tooth information with the number 6 are set to "0", that is, the pixel points in the 8-neighborhood are removed, and the pixel point distribution after the removal is regarded as part of the first tooth information with the number 6. Figure 15The pixel points after the expansion processing are judged one by one, if it is judged that there is a pixel point which is not numbered as 6 in the 8-neighborhood centered on a certain pixel point, the pixel point is subjected to the erosion processing (i.e. the pixel point is removed), the pixel point region removed after the erosion processing is represented by the filled shadow B in Figure 16 .

[0120] As shown in Figure 17 , it is a schematic diagram of the pixel point distribution position included in the second tooth information with the same identification information after the erosion processing according to an embodiment of the present application. As can be seen from Figure 17 , after the expansion processing and the erosion processing, the two regions originally separated by the lower part are connected together, thus effectively overcoming the situation that the same numbered tooth is divided into multiple teeth.

[0121] As shown in Figure 5 , the expansion processing and the erosion processing on the first tooth information with the same identification information in sequence include:

[0122] Firstly, step S31 is entered: according to the distribution position of the first tooth information with a certain identification information, the range of the first tooth information with the identification information is determined; the pixel points in the same region are connected in sequence;

[0123] Then, step S32 is entered: the distance between the edges of each region and the edges of other regions is calculated respectively, the pixel points in the two regions with the closest edges are subjected to the first degree of expansion processing and erosion processing, and the pixel points in other regions are subjected to the second degree of expansion processing and erosion processing; the first degree is higher than the second degree.

[0124] The difference between this embodiment and the previous embodiment is that the pixel points in different regions are subjected to different degrees of expansion and erosion processing by detecting the closest distance of the edge pixel points of the different regions with the same number. Generally, if a tooth is divided into two teeth, the distance between the two teeth after the division will not be too far, and the two teeth are subjected to a greater degree of expansion and erosion processing operation, which can make the two teeth more likely to be connected together compared to the connection with other regions, thereby improving the accuracy of tooth segmentation and recognition.

[0125] As shown in Figure 18 and Figure 19 , since the edge pixel points of the two regions below in Figure 14 are separated by 1 (one pixel point), which is the closest two pixel regions corresponding to the current tooth information numbered as 6, when the expansion and erosion processing is performed, the first degree of expansion processing and erosion processing is performed on each pixel point in the two regions, and the second degree of expansion processing and erosion processing is performed on the pixel points in Figure 14The pixels in the upper left and upper right regions are subjected to a second degree of dilation and erosion.

[0126] During the corrosion process, if the pixel has touched the edge of the image during the expansion process and the first degree of expansion has not been fully performed, the second degree of corrosion will still be performed on this part of the pixel after the expansion process. In short, if the two closest pixel points are expanded by two circles, then during the corrosion process, the pixel will also be processed by judging whether there are pixels with different numbers within two circles of its neighborhood. If the two closest pixel points are expanded by one circle, then during the corrosion process, the pixel will also be processed by judging whether there are pixels with different numbers within one circle of its neighborhood. The pixel area amplified by the expansion process is Figure 18 The filled shadow A indicates that the pixel area removed by corrosion is in Figure 19 Indicated by filled shadow B.

[0127] In some embodiments, the expansion and corrosion processes include:

[0128] The image can be expanded once and then etched, expanded once and then etched, expanded twice and then etched twice, expanded three times and then etched three times, or expanded once and then etched. In short, multiple expansions can be performed before multiple etches, or expansions and etched can be performed alternately. The image after expansion and etch is as follows: Figure 10 shown.

[0129] exist Figure 6 As shown, the oral scanned dental model image is the oral scanned dental model image after being straightened; the oral scanned dental model image before straightening is recorded as the first oral scanned dental model image, and the oral scanned dental model image after straightening is recorded as the second oral scanned dental model image, and the second oral scanned dental model image is obtained according to the following method:

[0130] S51: Recognizing a first dental scanned model image in a first coordinate system, and segmenting the first dental scanned model image into a plurality of dental images;

[0131] S52: Divide all the extracted dental images into at least three dental image groups, and calculate the second centroid coordinates of the at least three dental image groups; each dental image group includes one or more dental images; the dental image groups include a first dental image group, a second dental image group, and a third dental image group; mark the second centroid coordinate of the first dental image group as A, mark the second centroid coordinate of the second dental image group as B, and mark the second centroid coordinate of the third dental image group as C; the midpoint of BC is marked as point D;

[0132] S53: Taking the midpoint of triangle ABC as the coordinate origin O of the second coordinate system, taking vector OD as the Y axis of the second coordinate system, taking the normal vector of the plane where triangle ABC lies as the Z axis of the second coordinate system, and determining the X axis of the second coordinate system according to the Y axis and Z axis of the second coordinate system;

[0133] S54: Calculate the transformation matrix between the first coordinate system and the second coordinate system, and perform positive rotation on the position of the first dental scan image in the first coordinate system according to the transformation matrix to obtain a second dental scan image.

[0134] The coordinate systems of the dental model images generated by dental scanners produced by different manufacturers are often different, which leads to the wide variation in the angles of the scanned dental model images. Figure 6 The method shown can be used to normalize oral scanned dental model images at different angles to facilitate subsequent processing.

[0135] For example, the first dental scan image before conversion is the dental scan image of the mandibular teeth. The first dental scan image includes three areas along the direction of tooth arrangement: left, middle, and right. The area where the middle teeth are located is the first dental image group, the second dental image group is located on the left side of the first dental image group, and the third dental image group is located on the right side of the first dental image group. The left one of the two middle teeth is recorded as left 1 and the right one is recorded as right 1. The teeth extending to the left along the dental arch curve starting from left 1 are left 2, left 3... and so on; the teeth extending to the right along the dental arch curve starting from right 1 are right 2, right 3... and so on.

[0136] Assume that the calculated average center of gravity of mandibular teeth 1, 2, 1, and 2 is A, the average center of gravity of left 4, 5, 6, and 7 is B, and the average center of gravity of right 4, 5, 6, and 7 is C. D is the midpoint between B and C. The second coordinate system is determined as follows: the center point of ABC is the coordinate system origin O, the unit vector OD is the Y axis, the cross product of vector AB and vector BC is the Z axis, and the cross product of Y and Z is the X axis. This establishes a new spatial coordinate system (i.e., the second coordinate system).

[0137] Of course, in other embodiments, the origin of the second coordinate system may also be the focus of the three perpendicular bisectors or angle bisectors of triangle ABC. If the three selected second barycentric coordinates are densely distributed, for example, located on the left or right side of the mandible, then the coordinate origin of the second coordinate system can be determined based on the average shape of the current first scanned dental model image. For example, if the distribution direction of the three second barycentric coordinates is all biased to the left relative to the center of the tooth, then when determining the origin of the second coordinate system, it is preferred to determine the origin on the central axis of the center of the tooth or to the right of the central axis. Conversely, if the distribution direction of the three second barycentric coordinates is all biased to the right relative to the center of the tooth, then when determining the origin of the second coordinate system, it is preferred to determine the origin on the central axis of the center of the tooth or to the left of the central axis.

[0138] In some embodiments, the first dental scan image includes a dental scan image of a complete set of teeth or a dental scan image of a partial set of teeth. In short, the first dental scan image to be converted can be a dental scan image of a complete set of teeth in the upper or lower jaw of a human body, or a dental scan image of a partial set of teeth in the upper or lower jaw of a human body, as long as the number of teeth contained in the first dental scan image is greater than three.

[0139] In a second aspect, the present invention further provides a storage medium storing a computer program, which implements the method steps of the first aspect of the present invention when executed by a processor.

[0140] like Figure 20 As shown, in the third aspect, the present invention also provides an electronic device 10, including a processor 101 and a storage medium 102, wherein the storage medium 102 is the storage medium as in the second aspect; the processor 101 is used to execute the computer program stored in the storage medium 102 to implement the method steps as in the first aspect.

[0141] In this embodiment, the electronic device is a computer device, including but not limited to: oral scanners, personal computers, servers, general-purpose computers, special-purpose computers, network devices, embedded devices, programmable devices, smart mobile terminals, smart home devices, wearable smart devices, in-vehicle smart devices, etc. Storage media include but are not limited to: RAM, ROM, magnetic disks, tapes, optical disks, flash memory, USB flash drives, mobile hard drives, memory cards, memory sticks, network server storage, network cloud storage, etc. Processors include but are not limited to CPUs (central processing units), GPUs (graphics processing units), MCUs (microprocessors), etc.

[0142] Those skilled in the art should understand that each of the above-described embodiments can be provided as a method, device, or computer program product. These embodiments can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Each of the above-described embodiments involves all or part of the steps of the method, which can be instructed by a program to relevant hardware, and the program can be stored in a storage medium readable by a computer device, for executing all or part of the steps of the above-described embodiments.

[0143] The above-described embodiments are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a computer device to generate a machine, so that the instructions executed by the processor of the computer device generate a process for implementing the specified function in each flow or multiple flows and / or blocks in one or more blocks. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that performs the function specified in each flow or multiple flows and / or blocks in one or more blocks.

[0144] These computer program instructions can also be stored in a computer device readable storage medium that can direct the computer device to work in a specific manner, so that the instructions stored in the computer device readable storage medium generate a product including instruction apparatus, which implements the specified function in each flow or multiple flows and / or blocks in one or more blocks. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that performs the function specified in each flow or multiple flows and / or blocks in one or more blocks.

[0145] These computer program instructions can also be loaded into a computer device, so that a series of operation steps are performed on the computer device to generate a computer implemented process, so that the instructions executed on the computer device provide a process for implementing the specified function in each flow or multiple flows and / or blocks in one or more blocks. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that performs the function specified in each flow or multiple flows and / or blocks in one or more blocks.

[0146] Although the above-described embodiments have been described, those skilled in the art can make additional changes and modifications to the embodiments once they understand the basic inventive concept, so the above is only an embodiment of the application, and does not limit the patent protection scope of the application, and any equivalent structure or equivalent flow transformation made by using the content of the specification and drawings, or directly or indirectly applied to other related technical fields, are also included in the patent protection scope of the application.

Claims

1. A method for locating the center of a tooth using an oral scan dental model, characterized in that: The following steps are involved: S1: Acquire an oral scan dental model image, and generate a tooth depth image based on the undulation information of each tooth in the oral scan dental model image, wherein the undulation information of the tooth refers to the concavity and convexity of each tooth along the height direction of the tooth; S2: Segmenting the tooth depth image to identify a plurality of first tooth information, and adding identification information to each of the first tooth information; different first tooth information corresponds to different identification information; S3: processing the first tooth information having the same identification information respectively, determining the maximum connected domain of the first tooth information having the same identification information, and obtaining the second tooth information corresponding to each identification information; S4: Determine the coordinates of the center point corresponding to the second tooth information according to the coordinate positions of the pixel points in the second tooth information.

2. The method for locating the center of a tooth using an oral scan dental model according to claim 1, wherein: The oral scan dental model image is a three-dimensional image, and the three-dimensional image is placed in a three-dimensional space coordinate system, and the three-dimensional space coordinate system includes multiple grids; Generating a tooth depth image according to the fluctuation degree information of each tooth in the oral scan dental model image includes: S11: Generate a two-dimensional image in which the pixel values ​​of all pixels are 0; S12: normalizing the z-coordinate value of the center point of each grid in the dental model image along the tooth height direction; S13: sequentially determining whether the pixel value of the center point of each grid in the dental model image is greater than the pixel value of the corresponding coordinate point projected from the current center point of the grid on the two-dimensional image; if so, setting the pixel value of the corresponding coordinate point on the two-dimensional image as the z-coordinate value of the center point of the grid in the dental model image; S14: traverse all grids in the oral scan dental model image to obtain the tooth depth image.

3. The tooth center positioning method of oral scanning dental model according to claim 1, characterized in that: The oral scan dental model image is a three-dimensional image, and the three-dimensional image is placed in a three-dimensional space coordinate system, and the three-dimensional space coordinate system includes multiple grids; Generating a tooth depth image according to the fluctuation degree information of each tooth in the oral scan dental model image includes: S15: Generate a two-dimensional image in which the pixel values ​​of all pixels are 0; S16: Calculate the distance between the center point of each grid in the dental model image and the center coordinate of each grid in the two-dimensional image one by one, and use the z coordinate value of the center point of the grid in the dental model image with the shortest distance along the tooth height direction as the pixel value of the center coordinate of the corresponding grid in the two-dimensional image; S17: Traverse all grids on the two-dimensional image to obtain the tooth depth image.

4. The method for locating the center of a tooth using an oral scan dental model according to claim 1, wherein: The segmenting of the tooth depth image to identify the plurality of first tooth information includes: S21: Acquire a plurality of three-dimensional dental model images, and rotate the acquired three-dimensional dental model images by a predetermined angle along a predetermined plane in a current coordinate system to obtain a three-dimensional dental model image training set; the three-dimensional dental model image training set includes images of each three-dimensional dental model image before and after rotation at different angles; S22: randomly cropping the three-dimensional dental model image training set, and generating corresponding dental depth images based on the cropped images to obtain a dental depth image training set; S23: Inputting the tooth depth image training set into the neural network model to perform tooth information segmentation training to obtain a trained neural network model; S24: Input the tooth depth information generated by the oral scan dental model image into the trained neural network model to identify multiple first tooth information.

5. The tooth center positioning method of oral scanning dental model according to claim 1, characterized in that: The first tooth information having the same identification information is processed respectively to determine the maximum connected domain of the first tooth information having the same identification information, including: performing dilation processing and erosion processing on the first tooth information having the same identification information in sequence, thereby determining a maximum connected domain of the first tooth information having the same identification information; The expansion process includes: taking each pixel point included in the first tooth information having the same identification information as the center, setting the identification information of the neighboring pixel points of each pixel point as the current same identification information; The corrosion process includes: determining whether the identification information of neighboring pixel points of each pixel point having the same identification information after the expansion process is consistent, and if so, retaining the neighboring pixel point; otherwise, eliminating the neighboring pixel point.

6. The method for locating the center of a tooth using an oral scan dental model according to claim 5, wherein: Sequentially performing expansion processing and corrosion processing on the first tooth information having the same identification information includes: According to the distribution position of the first tooth information having the same identification information, a plurality of area ranges of the first tooth information of the identification information are determined; and the pixel points in the same area are connected in sequence; The distances between the edges of each region and the edges of other regions are calculated respectively, and a first degree of dilation and erosion is performed on the pixels in the two regions with the closest edge distance, and a second degree of dilation and erosion is performed on the pixels in other regions; the first degree is higher than the second degree.

7. The method for locating the center of a tooth using an oral scan dental model according to claim 5 or 6, wherein: The expansion treatment and corrosion treatment include: Any of the following: performing an expansion treatment first and then an etching treatment, performing an expansion treatment first and then an etching treatment, performing an expansion treatment first and then an etching treatment, performing two expansion treatments first and then two etching treatments, or performing three expansion treatments first and then three etching treatments.

8. The tooth center positioning method of oral scanning dental model according to claim 1, characterized in that: The oral scanned dental model image is a normalized oral scanned dental model image; the oral scanned dental model image before normalization is recorded as the first oral scanned dental model image, and the oral scanned dental model image after normalization is recorded as the second oral scanned dental model image, and the second oral scanned dental model image is obtained according to the following method: S51: Recognizing a first dental scanned model image in a first coordinate system, and segmenting the first dental scanned model image into a plurality of dental images; S52: Divide all the extracted tooth images into at least three tooth image groups, and calculate the second centroid coordinates of the at least three tooth image groups; each tooth image group contains one or more tooth images; The dental image group includes a first dental image group, a second dental image group and a third dental image group; The second centroid coordinate of the first dental image group is marked as A, the second centroid coordinate of the second dental image group is marked as B, and the second centroid coordinate of the third dental image group is marked as C; the midpoint of BC is marked as point D; S53: Taking the centroid of triangle ABC as the coordinate origin O of the second coordinate system, vector OD as the Y axis of the second coordinate system, and the normal vector of the plane where triangle ABC lies as the Z axis of the second coordinate system, determine the X axis of the second coordinate system according to the Y axis and Z axis of the second coordinate system; S54: Calculate the transformation matrix between the first coordinate system and the second coordinate system, and perform positive rotation on the position of the first dental scan image in the first coordinate system according to the transformation matrix to obtain a second dental scan image.

9. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method steps according to any one of claims 1 to 8 are implemented.

10. An electronic device, characterized in that: comprising a processor and a storage medium, wherein the storage medium is the storage medium according to claim 9; The processor is configured to execute the computer program stored in the storage medium to implement the method steps according to any one of claims 1 to 8.

Images