Method and system for constructing oral orthodontic effect model based on three-dimensional reconstruction

Abstract

The present invention relates to the technical field of oral image screening, and in particular to a method and system for constructing an oral orthodontic effect model based on three-dimensional reconstruction. The present invention shoots a main image and a sub-image of the oral structure; obtains margin parameters based on the positional relationship between the shooting point of the sub-image and the inside of the oral cavity; obtains an angle composite value based on the margin parameters of the shooting points of any two sub-images; obtains a comprehensive score of the sub-image based on the grayscale characteristics and edge distribution in all corresponding areas of the sub-image and the main image, the normal angle between the sub-images, and the overall grayscale characteristics of the sub-image and the main image; screens the sub-images based on the comprehensive score to obtain high-quality sub-images; and then performs three-dimensional modeling. The present invention selects high-quality sub-images that can supplement the information of the main image, and then accurately constructs a model of the patient's oral structure.

Description

Technical Field

[0001] The present invention relates to the technical field of oral image screening, and in particular to a method and system for constructing an oral orthodontic effect model based on three-dimensional reconstruction. Background Art

[0002] Currently, the field of orthodontics primarily uses methods such as CBCT, intraoral scanners, facial scanners, and traditional impression-taking and model scanning to acquire three-dimensional data of a patient's oral cavity. With the development of technologies such as computer vision and machine learning, three-dimensional reconstruction algorithms are also continuously improving. For example, algorithms based on deep learning can better handle three-dimensional reconstruction problems in complex scenarios, improving reconstruction accuracy and efficiency. Algorithms tailored to the specific characteristics of orthodontics are also emerging, such as reconstruction algorithms that consider factors such as tooth arrangement patterns and occlusion relationships, making the reconstructed oral models more in line with orthodontic clinical needs. An increasing number of dental medical institutions are beginning to introduce three-dimensional reconstruction technology into orthodontic clinical practice. In some large dental hospitals and specialist clinics, three-dimensional reconstruction has become a routine method for orthodontic diagnosis and treatment. Three-dimensional models enable doctors to more intuitively understand the patient's oral condition, develop more personalized treatment plans, and improve treatment effectiveness and patient satisfaction.

[0003] In the existing technology, it is usually necessary to take a certain number of secondary images to complement the information of the oral structure with the main image. However, in actual situations, the secondary images taken may generate a large amount of information redundancy or lack key information for three-dimensional modeling, making it impossible to accurately model the patient's oral structure. Summary of the Invention

[0004] In order to solve the technical problem that the captured secondary images may generate a large amount of information redundancy or lack key information for three-dimensional modeling, making it impossible to accurately model the patient's oral structure, the purpose of the present invention is to provide a method and system for constructing an oral orthodontic effect model based on three-dimensional reconstruction. The technical scheme adopted is as follows: A method for constructing an oral orthodontic effect model based on three-dimensional reconstruction, the method comprising: collecting all oral images of the patient and the shooting points corresponding to each oral image; obtaining the main image and the secondary image in all oral images according to the position difference of the shooting points; obtaining the line of sight angle between the shooting points of any two secondary images; obtaining the normal angle of any two secondary images; selecting any secondary image as a reference secondary image; and obtaining the main image and the secondary image according to the shooting points corresponding to the reference secondary image. The method comprises the following steps: obtaining a positional relationship between the shooting point and the interior of the oral cavity, obtaining a margin parameter value of the shooting point corresponding to the reference sub-image when shooting the oral image; obtaining an angle composite value of the shooting points corresponding to any two sub-images based on the margin parameter values of the shooting points corresponding to any two sub-images; obtaining all corresponding areas of the reference sub-image and the main image; obtaining a comprehensive score of the reference sub-image based on the distribution characteristics of edge pixel points of each corresponding area in the reference sub-image and the main image, the grayscale similarity between the reference sub-image and the main image, the angle composite value of the reference sub-image and each other shooting point of the sub-image, and the normal angle between the reference sub-image and each other shooting point of the sub-image; screening all sub-images based on the comprehensive score to obtain all high-quality sub-images; and performing three-dimensional modeling of the patient's oral cavity based on all high-quality sub-images and the main image.

[0005] Furthermore, the method for obtaining the margin parameter value includes: obtaining the distance between the main image shooting point and the corresponding shooting focus as the first distance; obtaining the distance between different shooting points and the leftmost tooth of the maxillary jaw in the stationary oral structure as the left edge distance, and obtaining the distance between different shooting points and the rightmost tooth of the maxillary jaw in the stationary oral structure as the right edge distance; obtaining the straight line between the leftmost tooth and the rightmost tooth of the maxillary jaw in the oral structure as the internal line segment of the oral cavity.

[0006] The margin parameter value is obtained according to the margin parameter value calculation formula, and the margin parameter value calculation formula is as follows: Where, Indicates the serial number of the reference sub-image; Indicates the margin parameter value when taking the oral image at the shooting point corresponding to the reference sub-image; Indicates the left edge distance of the shooting point corresponding to the reference sub-image; Indicates the right edge distance of the shooting point corresponding to the reference sub-image; Indicates the length of the line segment inside the mouth; Indicates the focal length between the main image shooting point and the shooting focus; Indicates the first distance; represents the tangent function.

[0007] Furthermore, the method for obtaining the angle comprehensive value includes: taking the average of the margin parameters of the shooting points corresponding to the two feature sub-images as the angle comprehensive value of the shooting points corresponding to any two feature sub-images.

[0008] Furthermore, the grayscale similarity acquisition method includes: using the same area of the oral structure in the main image and the auxiliary image as the corresponding area between the main image and the auxiliary image; and acquiring the grayscale similarity according to a grayscale similarity calculation formula, which is as follows: Where, Indicates the grayscale similarity between the reference secondary image and the main image; Indicates the number of corresponding areas between the reference sub-image and the main image; Indicates the reference figure The grayscale mean value in the corresponding area; Represents the grayscale mean of the reference sub-image; Indicates the first The grayscale mean value in the corresponding area; Represents the grayscale mean of the main image.

[0009] Furthermore, the method for obtaining the comprehensive score includes: obtaining the comprehensive score according to a comprehensive score calculation formula, and the comprehensive score calculation formula is as follows: Where, represents the comprehensive score of the reference sub-image; Indicates the grayscale similarity between the reference secondary image and the main image; Indicates the reference figure The number of edge pixels in the corresponding area accounts for The ratio of the total number of pixels in the corresponding area; Indicates the first The number of edge pixels in the corresponding area accounts for The ratio of the total number of pixels in the corresponding area; Indicates the number of sub-images other than the reference sub-image; Indicates the reference sub-image and the The comprehensive angle value of the shooting points corresponding to the other sub-images; Indicates the maximum value of the comprehensive angle value of the reference sub-image and the shooting points corresponding to other sub-images; Indicates the reference sub-image and the The normal angle between other sub-images; Indicates the preset angle threshold; represents a logarithmic function with a natural constant as its base; Represents an exponential function with a natural constant as its base.

[0010] Furthermore, the method for obtaining high-quality sub-images includes: sorting all sub-images from high to low according to the comprehensive scores to obtain a sub-image sequence; in the sub-image sequence, starting from the first sub-image, sequentially selecting a preset number of sub-images as high-quality sub-images among all sub-images.

[0011] A system for constructing an oral orthodontic effect model based on three-dimensional reconstruction, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0012] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for constructing an oral orthodontic effect model based on three-dimensional reconstruction.

[0013] A computer device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned method for constructing an oral orthodontic effect model based on three-dimensional reconstruction are implemented.

[0014] The present invention has the following beneficial effects: in order to perform three-dimensional modeling of the oral structure, the present invention first captures oral images from multiple angles to obtain information about the patient's oral structure; since the spatial distribution of the shooting points can reflect the shooting angles of different oral images, and different shooting angles result in different oral information contained in the corresponding oral images; to facilitate subsequent analysis of the spatial distribution of different shooting points, first, the sight line angle between the shooting points of any two sub-images and the normal angle between any two sub-images are analyzed; since the oral images obtained from different shooting angles have different information richness and information focus, the margin parameters when the oral images are taken at the shooting points corresponding to the reference sub-images are analyzed to reflect the degree to which the different shooting points represent the oral structure information; the sight line angle between the shooting points of any two sub-images is matched with the margin parameters of the shooting points of any two sub-images, and the size of the margin parameters is used to reflect the complementary role of the sub-images taken at different shooting points to the main image; in addition to the shooting angle of the sub-images, the grayscale information and edge distribution of the teeth in the sub-images can also reflect the image information difference between the sub-images and the main image, and the sub-images taken are screened based on the image information difference; and three-dimensional modeling is performed using the screened high-quality sub-images. The present invention selects a high-quality secondary image that can supplement the information of the main image, thereby accurately constructing a model of the patient's oral structure. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 A flow chart of a method for constructing an oral orthodontic effect model based on three-dimensional reconstruction provided by one embodiment of the present invention; Figure 2 A block diagram of a system for constructing an orthodontic effect model based on three-dimensional reconstruction provided by one embodiment of the present invention; Figure 3 A schematic diagram of a main image of the oral structure provided by one embodiment of the present invention; Figure 4 This is a schematic diagram of shooting a secondary image of the oral structure provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0017] To further illustrate the technical means and effects employed by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail a method and system for constructing an orthodontic effect model based on three-dimensional reconstruction, including its specific implementation, structure, features, and effects. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The following describes in detail a method and system for constructing an oral orthodontic effect model based on three-dimensional reconstruction provided by the present invention with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a method for constructing an oral orthodontic effect model based on three-dimensional reconstruction provided by an embodiment of the present invention, the method comprising: step S1: collecting all oral images of the patient and the shooting points corresponding to each oral image; obtaining the main image and the sub-image in all oral images according to the position differences of the shooting points.

[0021] The embodiment of the present invention is mainly used in the scenario of three-dimensional modeling of the patient's oral structure. In order to perform three-dimensional modeling of the oral structure, oral images from multiple angles are first taken to obtain information about the patient's oral structure. In order to subsequently analyze the degree to which each oral image supplements the modeling information, the shooting point of each oral image is analyzed, and oral images at different angles are obtained by changing the shooting angle, and each oral image is marked by the different positions of the shooting points. Therefore, in the embodiment of the present invention, the main image and the secondary image in all oral images are obtained based on the position differences of the shooting points.

[0022] In one embodiment of the present invention, the oral structure is kept stationary, and a high-definition camera is set up at a preset distance in the horizontal direction in front of the oral structure. Figure 3 As shown, point z is the center point of the maxillary incisor area in the oral structure, and the position at a preset distance in the horizontal direction in front of point z is point V, which can clearly capture all the front information of the oral structure and use it as the main image in the oral image. Figure 4 As shown, the high-definition camera is continuously offset at a certain angle to obtain other oral images as sub-images until a preset number of sub-images are obtained. Among them, the preset distance is set to 1 meter, and the preset number is set to 300. It should be noted that the preset distance and the preset number can be set by yourself and are not limited here. At this time, the motion trajectory of different shooting points is equivalent to moving on a sphere with the center point of the maxillary incisor area in the oral structure as the center of the sphere and the preset distance as the radius, and the motion path of the shooting point only exists in the spherical area outside the center point of the maxillary incisor area in the oral structure.

[0023] It should be noted that in other embodiments of the present invention, the center point of the mandibular incisor area in the oral structure may also be selected as the z point, which is not limited here.

[0024] Step S2: Obtain the sight angle between the shooting points of any two sub-images; obtain the normal angle of any two sub-images; select any sub-image as a reference sub-image; obtain the margin parameter value of the shooting point corresponding to the reference sub-image when shooting the oral image based on the positional relationship between the shooting point corresponding to the reference sub-image and the interior of the oral cavity; obtain the angle composite value of the shooting points corresponding to any two sub-images based on the margin parameter value of the shooting points corresponding to any two sub-images; obtain all corresponding areas of the reference sub-image and the main image; obtain the comprehensive score of the reference sub-image based on the edge pixel distribution characteristics of each corresponding area in the reference sub-image and the main image, the grayscale similarity between the reference sub-image and the main image, the angle composite value of the reference sub-image and each other sub-image shooting point, and the normal angle between the feature plane of the reference sub-image and each other sub-image shooting point.

[0025] Since the spatial distribution of shooting points can reflect the shooting angles of different oral images, and different shooting angles result in different oral information contained in the corresponding oral images; in order to facilitate the subsequent analysis of the spatial distribution of different shooting points, the embodiment of the present invention first analyzes and obtains the line of sight angle between the shooting points of any two sub-images and the normal angle between any two sub-images.

[0026] In one embodiment of the present invention, the angle formed by the line connecting the shooting points of any two sub-images and the center point of the maxillary incisor region in the oral structure is used as the sight line angle between the shooting points of any two sub-images.

[0027] Oral images captured from different angles have different levels of information richness and focus. For example, when photographing from the leftmost side of the teeth, the information on the left side of the oral structure is clearer and more detailed, while the right side of the oral structure may overlook some hidden details due to angle and distance issues. Therefore, the closer the shooting point is to one of the tooth boundaries, the clearer the captured details and the higher the margin parameter value. The farther the shooting point is from the other tooth boundary, the more likely it is to lose some hidden details. Therefore, in this embodiment of the present invention, the margin parameter value of the oral image captured at the shooting point corresponding to the reference secondary image is first analyzed to reflect the degree of representation of oral structure information at different shooting points.

[0028] Preferably, in one embodiment of the present invention, the method for obtaining the margin parameter value includes: obtaining the distance between the main image shooting point and the corresponding shooting focus as the first distance; obtaining the distance between different shooting points and the leftmost tooth of the maxillary in the stationary oral structure as the left edge distance, obtaining the distance between different shooting points and the rightmost tooth of the maxillary in the stationary oral structure as the right edge distance; obtaining the straight line between the leftmost tooth and the rightmost tooth of the maxillary in the oral structure as the internal line segment of the oral cavity.

[0029] Obtain the margin parameter value according to the margin parameter calculation formula. The margin parameter calculation formula is as follows: Where, Indicates the serial number of the reference sub-image; Indicates the margin parameter value when taking the oral image at the shooting point corresponding to the reference sub-image; Indicates the left edge distance of the shooting point corresponding to the reference sub-image; Indicates the right edge distance of the shooting point corresponding to the reference sub-image; Indicates the length of the line segment inside the mouth; Indicates the focal length between the main image shooting point and the shooting focus; Indicates the first distance; represents the tangent function.

[0030] In the margin parameter calculation formula, Indicates the vertical distance between the main image shooting point and the line segment representing the inside of the mouth, Indicates the straight-line distance between the main image shooting point and the leftmost tooth or the rightmost tooth in the maxilla, which is used as the second distance and is a fixed value; The function limits the function value. If the left edge distance of the reference sub-image shooting point is or right edge distance Compared to the second distance, the farther or If it is greater than 1, the supplementary information of the reference sub-image to the main image will be limited, and the margin parameter value will be reduced; when or Less than 1, in this case, the left edge distance of the reference sub-image shooting point or right edge distance Compared with the second distance, the closer the reference image is, the better it is in supplementing the information of the main image, and the margin parameter value will increase.

[0031] At this time, the sight angle between the shooting points of any two sub-images is matched with the margin parameter of the shooting points of any two sub-images, and the size of the margin parameter is used to reflect the supplementary effect of the sub-images taken at different shooting points on the main image.

[0032] Preferably, in one embodiment of the present invention, the method for obtaining the angle comprehensive value includes: taking the average value of the margin parameters of the shooting points corresponding to the two characteristic sub-images as the angle comprehensive value of the shooting points corresponding to any two characteristic sub-images, wherein the larger the angle comprehensive value, the greater the information supplementary effect of the sub-image corresponding to the sight angle of the shooting point on the main image.

[0033] In addition to the shooting angle of the secondary image, the grayscale information and edge distribution of the teeth in the secondary image can also reflect the image information difference between the secondary image and the main image, and the secondary images taken are screened based on the image information difference. Therefore, in this embodiment of the present invention, the grayscale similarity between the reference secondary image and the main image is obtained based on the grayscale characteristics of all corresponding areas of the reference secondary image and the main image, as well as the overall grayscale characteristics of the reference secondary image and the main image; the comprehensive score of the reference secondary image is obtained based on the edge pixel distribution characteristics of each corresponding area in the reference secondary image and the main image, the angle composite value between the reference secondary image and each other secondary image shooting point, and the normal angle between the reference secondary image and each other secondary image shooting point.

[0034] Preferably, in one embodiment of the present invention, the grayscale similarity acquisition method includes: using the same area of the oral structure in the main image and the auxiliary image as the corresponding area between the main image and the auxiliary image; and acquiring the grayscale similarity according to a grayscale similarity calculation formula, which is as follows: Where, Indicates the grayscale similarity between the reference secondary image and the main image; Indicates the number of corresponding areas between the reference sub-image and the main image; Indicates the reference figure The grayscale mean value in the corresponding area; Represents the grayscale mean of the reference sub-image; Indicates the first The grayscale mean value in the corresponding area; Represents the grayscale mean of the main image.

[0035] In the grayscale similarity calculation formula, the grayscale similarity between the main image and the reference sub-image is calculated using the Pearson correlation coefficient formula. The Pearson correlation coefficient formula is a technical means well known to those skilled in the art and will not be described in detail here.

[0036] Preferably, in one embodiment of the present invention, the method for obtaining the comprehensive score includes: obtaining the comprehensive score according to a comprehensive score calculation formula, which is as follows: Where, represents the comprehensive score of the reference sub-image; Indicates the grayscale similarity between the reference secondary image and the main image; Indicates the reference figure The number of edge pixels in the corresponding area accounts for The ratio of the total number of pixels in the corresponding area; Indicates the first The number of edge pixels in the corresponding area accounts for The ratio of the total number of pixels in the corresponding area; Indicates the number of sub-images other than the reference sub-image; Indicates the reference sub-image and the The comprehensive angle value of the shooting points corresponding to the other sub-images; The maximum value of the comprehensive angle value of the reference sub-image and the shooting points corresponding to the other sub-images can be directly obtained by the existing technology; Indicates the reference sub-image and the The normal angle between other sub-images; Indicates the preset angle threshold; represents a logarithmic function with a natural constant as its base; Represents an exponential function with a natural constant as its base.

[0037] In the comprehensive score calculation formula, the proportion of edge pixels in each corresponding area in the reference sub-image is used. The ratio of the number of edge pixels in each corresponding area of the main image The larger the ratio is, the greater the edge information of the secondary image is, and the higher the score of the reference secondary image should be. The larger the angle is, the greater the score of the reference sub-image is. Since the shooting points of the two sub-images are too far apart, the information between the sub-images cannot be complementary, and additional sub-images need to be added to complete the information supplement. Therefore, a preset angle threshold is set. When the normal angle between the reference sub-image and any sub-image is greater than the preset angle threshold, it is considered that the normal angle between the sub-images will not produce information redundancy. Therefore, the closer the comprehensive angle value between the reference sub-image and any sub-image is to the maximum value, the more oral structure information can be obtained from the reference sub-image and the sub-image. The larger the value is, the greater the score of the reference sub-image is. When the normal angle between the reference sub-image and any sub-image is less than the preset angle threshold, the closer the shooting points of the two sub-images are, the more redundant the sub-images will be. The smaller the value, the smaller the score of the reference image should be adjusted. right Make adjustments, i.e. The larger it is, the greater the score of the reference sub-image will be.

[0038] In one embodiment of the present invention, the preset angle threshold is set to 15°. It should be noted that in other embodiments of the present invention, the preset angle threshold can be set arbitrarily and is not limited here.

[0039] At this point, the comprehensive score of each sub-image is obtained.

[0040] Step S3: All secondary images are screened according to the comprehensive scores to obtain all high-quality secondary images; and three-dimensional modeling of the patient's oral cavity is performed based on all high-quality secondary images and the main image.

[0041] Preferably, in one embodiment of the present invention, a method for obtaining high-quality secondary images includes: sorting all secondary images from high to low according to their comprehensive scores to obtain a secondary image sequence; and selecting a preset number of secondary images from the first secondary image in the secondary image sequence as high-quality secondary images from among all secondary images. In one embodiment of the present invention, the preset number is set to 10. It should be noted that the preset number can be set arbitrarily and is not limited herein.

[0042] Since three-dimensional modeling technology is a technical means well known to those skilled in the art, it will not be limited or elaborated here.

[0043] At this point, the three-dimensional modeling of the oral structure is completed.

[0044] In summary, all oral images of the patient and the shooting points corresponding to each oral image are collected; the main image and the sub-image in all oral images are obtained according to the position difference of the shooting points; the sight angle between the shooting points of any two sub-images is obtained; the normal angle of any two sub-images is obtained; any sub-image is selected as a reference sub-image; according to the position relationship between the shooting point corresponding to the reference sub-image and the inside of the oral cavity, the margin parameter value of the shooting point corresponding to the reference sub-image when shooting the oral image is obtained; according to the margin parameter value of the shooting points corresponding to any two sub-images, the angle comprehensive value of the shooting points corresponding to any two sub-images is obtained; the angle between the reference sub-image and the main image is obtained. all corresponding areas of the reference sub-image and the main image; the grayscale similarity between the reference sub-image and the main image is obtained according to the grayscale features in all corresponding areas of the reference sub-image and the main image, as well as the overall grayscale features of the reference sub-image and the main image; the comprehensive score of the reference sub-image is obtained according to the edge pixel distribution features of each corresponding area in the reference sub-image and the main image, the comprehensive angle value between the reference sub-image and each other sub-image shooting point, and the normal angle between the reference sub-image and each other sub-image shooting point; all sub-images are screened according to the comprehensive score to obtain all high-quality sub-images; and the patient's oral cavity is 3D modeled based on all high-quality sub-images and the main image.

[0045] See also Figure 2 , which shows the second purpose of the present invention, a structural block diagram of an oral orthodontic effect model construction system based on three-dimensional reconstruction, the system includes the following modules: an image acquisition module for acquiring all oral images of the patient and the shooting points corresponding to each oral image; obtaining the main image and the sub-image in all oral images according to the position difference of the shooting points; a scoring module for obtaining the sight angle between the shooting points of any two sub-images; obtaining the normal angle of any two sub-images; selecting any sub-image as a reference sub-image; obtaining the margin parameter value of the shooting point corresponding to the reference sub-image when shooting the oral image according to the position relationship between the shooting point corresponding to the reference sub-image and the inside of the oral cavity; obtaining any two sub-images according to the margin parameter value of the shooting points corresponding to the margin parameter. The comprehensive angle value of the shooting points corresponding to the two sub-images; obtaining all corresponding areas of the reference sub-image and the main image; obtaining the grayscale similarity between the reference sub-image and the main image based on the grayscale features in all corresponding areas of the reference sub-image and the main image, as well as the overall grayscale features of the reference sub-image and the main image; obtaining the comprehensive score of the reference sub-image based on the edge pixel distribution features of each corresponding area in the reference sub-image and the main image, the comprehensive angle value of the reference sub-image and each other sub-image shooting point, and the normal angle between the reference sub-image and each other sub-image shooting point; a three-dimensional modeling module, used to screen all sub-images according to the comprehensive score to obtain all high-quality sub-images; and perform three-dimensional modeling of the patient's oral cavity based on all high-quality sub-images and the main image.

[0046] The third purpose of an embodiment of the present invention is to provide a computer device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, the steps of the above-mentioned method for constructing an oral orthodontic effect model based on three-dimensional reconstruction are implemented.

[0047] The fourth object of an embodiment of the present invention is to provide a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the above-mentioned method for constructing an oral orthodontic effect model based on three-dimensional reconstruction.

[0048] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0049] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A method for constructing an oral orthodontic effect model based on three-dimensional reconstruction, characterized in that: The method comprises: collecting all oral images of a patient and the shooting points corresponding to each oral image; obtaining the main image and the sub-images in all oral images according to the position difference of the shooting points; obtaining the sight angle between the shooting points of any two sub-images; obtaining the normal angle of any two sub-images; selecting any sub-image as a reference sub-image; obtaining the margin parameter value of the shooting point corresponding to the reference sub-image when shooting the oral image according to the position relationship between the shooting point corresponding to the reference sub-image and the interior of the oral cavity; obtaining the angle composite value of the shooting points corresponding to any two sub-images according to the margin parameter value of the shooting points corresponding to any two sub-images; obtaining all corresponding areas of the reference sub-image and the main image; obtaining the angle composite value of the shooting points corresponding to any two sub-images according to the distribution characteristics of the edge pixels of each corresponding area in the reference sub-image and the main image, the grayscale similarity between the reference sub-image and the main image, and the angle composite value of the shooting points of each other sub-image. , and the normal angle between the reference sub-image and the feature plane of each other sub-image shooting point, to obtain a comprehensive score of the reference sub-image; all sub-images are screened according to the comprehensive score to obtain all high-quality sub-images; three-dimensional modeling of the patient's oral cavity is performed based on all high-quality sub-images and the main image; the method for obtaining the margin parameter value includes: obtaining the distance between the shooting point of the main image and the corresponding shooting focus as the first distance; obtaining the distance between different shooting points and the maxillary leftmost tooth in the stationary oral structure as the left edge distance, and obtaining the distance between different shooting points and the maxillary rightmost tooth in the stationary oral structure as the right edge distance; obtaining the straight line between the maxillary leftmost tooth and the rightmost tooth in the oral structure as the oral internal line segment; obtaining the margin parameter value according to the margin parameter value calculation formula, the margin parameter calculation formula is as follows: Where, Indicates the serial number of the reference sub-image; Indicates the margin parameter value when taking the oral image at the shooting point corresponding to the reference sub-image; Indicates the left edge distance of the shooting point corresponding to the reference sub-image; Indicates the right edge distance of the shooting point corresponding to the reference sub-image; Indicates the length of the line segment inside the mouth; Indicates the focal length between the main image shooting point and the shooting focus; Indicates the first distance; represents the tangent function.

2. The method for constructing an oral orthodontic effect model based on three-dimensional reconstruction according to claim 1, characterized in that: The method for obtaining the angle comprehensive value includes: taking the average of the margin parameters of the shooting points corresponding to the two feature sub-images as the angle comprehensive value of the shooting points corresponding to any two feature sub-images.

3. The method for constructing an oral orthodontic effect model based on three-dimensional reconstruction according to claim 1, characterized in that: The grayscale similarity acquisition method includes: using the same area of the oral structure in the main image and the auxiliary image as the corresponding area between the main image and the auxiliary image; and acquiring the grayscale similarity according to a grayscale similarity calculation formula, which is as follows: Where, Indicates the grayscale similarity between the reference secondary image and the main image; Indicates the number of corresponding areas between the reference sub-image and the main image; Indicates the reference figure The grayscale mean value in the corresponding area; Represents the grayscale mean of the reference sub-image; Indicates the first The grayscale mean value in the corresponding area; Represents the grayscale mean of the main image.

4. The method for constructing an oral orthodontic effect model based on three-dimensional reconstruction according to claim 1, characterized in that: The method for obtaining the comprehensive score includes: obtaining the comprehensive score according to a comprehensive score calculation formula, and the comprehensive score calculation formula is as follows: Where, represents the comprehensive score of the reference sub-image; Indicates the grayscale similarity between the reference secondary image and the main image; Indicates the reference figure The number of edge pixels in the corresponding area accounts for The ratio of the total number of pixels in the corresponding area; Indicates the first The number of edge pixels in the corresponding area accounts for The ratio of the total number of pixels in the corresponding area; Indicates the number of sub-images other than the reference sub-image; Indicates the reference sub-image and the The comprehensive angle value of the shooting points corresponding to the other sub-images; Indicates the maximum value of the comprehensive angle value of the reference sub-image and the shooting points corresponding to other sub-images; Indicates the reference sub-image and the The normal angle between other sub-images; Indicates the preset angle threshold; represents a logarithmic function with a natural constant as its base; Represents an exponential function with a natural constant as its base.

5. The method for constructing an oral orthodontic effect model based on three-dimensional reconstruction according to claim 1, characterized in that: The method for obtaining high-quality sub-images includes: sorting all sub-images from high to low according to comprehensive scores to obtain a sub-image sequence; in the sub-image sequence, starting from the first sub-image, sequentially selecting a preset number of sub-images as high-quality sub-images from all sub-images.

6. A system for constructing an oral orthodontic effect model based on three-dimensional reconstruction, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a method for constructing an oral orthodontic effect model based on three-dimensional reconstruction as described in any one of claims 1 to 5 are implemented.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for constructing an oral orthodontic effect model based on three-dimensional reconstruction as described in any one of claims 1 to 5 are implemented.

Images