Orthodontic effect model construction method and system based on three-dimensional reconstruction

Abstract

The invention relates to the technical field of oral cavity image screening, in particular to an orthodontic effect model construction method and system based on three-dimensional reconstruction. A main image and an auxiliary image of an oral cavity structure are shot; obtaining an edge distance parameter value according to the position relationship between the shooting point of the secondary image and the interior of the oral cavity; obtaining an angle comprehensive value according to the edge distance parameter values of the shooting points of any two auxiliary images; according to the gray features and edge distribution in all the corresponding areas of the auxiliary images and the main image, the normal included angle between the auxiliary images and the overall gray features of the auxiliary images and the main image, the comprehensive score of the auxiliary images is obtained; screening the secondary images according to the comprehensive score to obtain a high-quality secondary image; and performing three-dimensional modeling. According to the method, the high-quality secondary image capable of performing information supplementation on the main image is selected, so that the model construction is accurately performed on the oral cavity structure of the patient.

Description

Technical Field

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

[0002] Currently, in the field of oral orthodontics, methods such as CBCT, intraoral scanners, facial scanners, and traditional impression taking and model scanning are mainly used to obtain 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 constantly improving. For example, algorithms based on deep learning can better handle three-dimensional reconstruction problems in complex scenarios, improving the reconstruction accuracy and efficiency; some algorithms specifically for the characteristics of oral orthodontics are also emerging continuously, such as reconstruction algorithms that consider factors such as tooth arrangement rules and occlusion relationships, making the reconstructed oral models more in line with the clinical needs of orthodontics. More and more oral medical institutions are beginning to introduce three-dimensional reconstruction technology for clinical practice in oral orthodontics. In some large oral hospitals and specialized clinics, three-dimensional reconstruction has become one of the routine means for orthodontic diagnosis and treatment. Doctors can more intuitively understand the patient's oral condition through three-dimensional models, formulate more personalized treatment plans, and improve the treatment effect and patient satisfaction.

[0003] In the prior art, a certain number of sub-images usually need to be taken to complete the information complementation of the oral structure with the main image. However, in actual situations, the taken sub-images may have a large amount of information redundancy or lack key information for three-dimensional modeling, so that the model construction of the patient's oral structure cannot be accurately carried out. Summary of the Invention

[0004] To solve the technical problem that the captured secondary images may have a large amount of information redundancy or lack key information for three-dimensional modeling, making it impossible to accurately construct a model of 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 specific technical solutions are as follows: A method for constructing an oral orthodontic effect model based on three-dimensional reconstruction, the method includes: collecting all oral images of the patient and the shooting points corresponding to each oral image; obtaining the main image and secondary images among all oral images according to the position differences of the shooting points; obtaining the viewing angle between the shooting points of any two secondary images; obtaining the normal angle between any two secondary images; arbitrarily selecting one secondary image as the reference secondary image; obtaining the margin parameter value when the reference secondary image corresponding to the shooting point shoots the oral image according to the positional relationship between the shooting point corresponding to the reference secondary image and the inside of the oral cavity; obtaining the angle comprehensive value of the shooting points corresponding to any two secondary images according to the margin parameter values of the shooting points corresponding to any two secondary images; obtaining all corresponding regions of the reference secondary image and the main image; obtaining the comprehensive score of the reference secondary image according to the edge pixel point distribution characteristics of each corresponding region in the reference secondary image and the main image, the gray-scale similarity between the reference secondary image and the main image, the angle comprehensive value between the reference secondary image and the shooting points of each other secondary image, and the normal angle between the reference secondary image and the characteristic plane of the shooting points of each other secondary image; screening all secondary images according to the comprehensive score to obtain all high-quality secondary images; performing three-dimensional modeling of the patient's oral cavity according to all high-quality secondary images and the main image.

[0005] Further, 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 in the upper jaw of the static oral structure as the left edge distance, and obtaining the distance between different shooting points and the rightmost tooth in the upper jaw of the static oral structure as the right edge distance; obtaining the straight line between the leftmost tooth and the rightmost tooth in the upper jaw of the oral structure as the internal oral segment.

[0006] Obtaining the margin parameter value according to the margin parameter value calculation formula, the margin parameter value calculation formula is as follows: In the formula, represents the serial number of the reference secondary image; represents the margin parameter value when the shooting point corresponding to the reference secondary image shoots the oral image; represents the left edge distance of the shooting point corresponding to the reference secondary image; represents the right edge distance of the shooting point corresponding to the reference secondary image; represents the length of the internal oral segment; represents the focal length between the main image shooting point and the shooting focus; represents the first distance; represents the tangent function.

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

[0008] Further, the method for obtaining the gray - scale similarity includes: taking the same regions of the oral structures in the main image and the sub - image as the corresponding regions between the main image and the sub - image; obtaining the gray - scale similarity according to the gray - scale similarity calculation formula, and the gray - scale similarity calculation formula is as follows: In the formula, represents the gray - scale similarity between the reference sub - image and the main image; represents the number of corresponding regions between the reference sub - image and the main image; represents the average gray - scale value within the th corresponding region in the reference sub - image; represents the average gray - scale value of the reference sub - image; represents the average gray - scale value within the th corresponding region in the main image; represents the average gray - scale value of the main image.

[0009] Further, the method for obtaining the comprehensive score includes: obtaining the comprehensive score according to the comprehensive score calculation formula, and the comprehensive score calculation formula is as follows: In the formula, represents the comprehensive score of the reference sub - image; represents the gray - scale similarity between the reference sub - image and the main image; represents the ratio of the number of edge pixel points in the th corresponding region of the reference sub - image to the total number of pixel points in the th corresponding region; represents the ratio of the number of edge pixel points in the th corresponding region of the main image to the total number of pixel points in the th corresponding region; represents the number of other sub - images except the reference sub - image; represents the comprehensive angle value of the shooting points corresponding to the reference sub - image and the th other sub - image; represents the maximum value of the comprehensive angle values of the shooting points corresponding to the reference sub - image and other sub - images; represents the normal angle between the reference sub - image and the th other sub - image; represents the preset angle threshold; represents the natural logarithm function; represents the exponential function with the natural constant as the base.

[0010] Further, the method for obtaining the high-quality sub-images includes: sorting all the sub-images in descending order according to the comprehensive score 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 backward as the high-quality sub-images among all the sub-images.

[0011] An orthodontic effect model construction system based on three-dimensional reconstruction, the system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of the above method are implemented.

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

[0013] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of the above method for constructing an 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 on the oral structure, the present invention first takes oral images from multiple angles to obtain information on 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; in order to facilitate subsequent analysis of the spatial distribution of different shooting points, first analyze and obtain the line-of-sight angle between the shooting points of any two sub-images and the normal angle between any two sub-images; since the information richness and information focus in the oral images obtained from different shooting angles are different, so analyze the edge distance parameter when shooting the oral image at the shooting point corresponding to the reference sub-image to reflect the performance degree of different shooting points for the oral structure information; correspond the line-of-sight angle of the shooting points of any two sub-images with the edge distance parameter of the shooting points of any two sub-images, and reflect the supplementary effect of the sub-images shot at different shooting points on the main image through the size of the edge distance parameter; in addition to the shooting angle of the sub-image, the gray-scale information and edge distribution of the teeth in the sub-image can also reflect the image information difference between the sub-image and the main image, and screen the shot sub-images through the image information difference; perform three-dimensional modeling with the high-quality sub-images screened. 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 of the Drawings

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0016] Figure 1 Flowchart of a method for constructing an orthodontic effect model based on three-dimensional reconstruction provided by an embodiment of the present invention; Figure 2 Block diagram of a system for constructing an orthodontic effect model based on three-dimensional reconstruction provided by an embodiment of the present invention; Figure 3 Schematic diagram of taking the main view of the oral structure provided by an embodiment of the present invention; Figure 4 Schematic diagram of taking the auxiliary view of the oral structure provided by an embodiment of the present invention. Detailed implementation manners

[0017] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features, and effects of a method and system for constructing an orthodontic effect model based on three-dimensional reconstruction proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

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

[0019] The following specifically describes the specific solutions of a method and system for constructing an orthodontic effect model based on three-dimensional reconstruction provided by the present invention in conjunction with the accompanying drawings.

[0020] Please refer to Figure 1 , which shows a method for constructing an orthodontic effect model based on three-dimensional reconstruction provided by an embodiment of the present invention. The method includes: Step S1: Collect all oral images of the patient and the shooting points corresponding to each oral image; obtain the main view and the auxiliary view in all oral images according to the position differences of the shooting points.

[0021] The embodiments of the present invention are mainly applied to the scenario of three-dimensional modeling of the oral structure of patients. In order to perform three-dimensional modeling of the oral structure, oral images from multiple angles are first taken to obtain information about the oral structure of the patient. In order to analyze the degree of information supplementation of each oral image for modeling in the subsequent process, the shooting points of each oral image are analyzed. Oral images from different angles are obtained by changing the shooting angle, and each oral image is marked according to the different positions of the shooting points. Therefore, in the embodiments of the present invention, the main image and the sub-images in all oral images are obtained according to 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 installed at a preset distance in the horizontal direction in front of the oral structure, specifically as Figure 3 shown. Point z is the center point position of the upper incisor region in the oral structure. The position at a preset distance in the horizontal direction in front of point z is point V, which can clearly capture all the frontal information of the oral structure and use it as the main image in the oral image. Then, as Figure 4 shown, the high-definition camera is continuously offset by 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 oneself and are not limited here. At this time, the movement trajectories of different shooting points are equivalent to moving on the spherical surface with the center point position of the upper incisor region in the oral structure as the center of the sphere and the preset distance as the radius, and the movement path of the shooting point only exists in the spherical surface area outside the center point position of the upper incisor region in the oral structure.

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

[0024] Step S2: Obtain the line-of-sight angle between the shooting points of any two sub-images; obtain the normal angle between any two sub-images; select any one sub-image as the reference sub-image; obtain the edge distance parameter value when the reference sub-image corresponding shooting point shoots the oral image according to the positional relationship between the shooting point corresponding to the reference sub-image and the inside of the oral cavity; obtain the angle comprehensive value of the shooting points corresponding to any two sub-images according to the edge distance parameter values of the shooting points corresponding to any two sub-images; obtain all the corresponding regions between the reference sub-image and the main image; obtain the comprehensive score of the reference sub-image according to the edge pixel point distribution characteristics of each corresponding region between the reference sub-image and the main image, the gray-scale similarity between the reference sub-image and the main image, the angle comprehensive value of the reference sub-image and the shooting points of each other sub-image, and the normal angle between the reference sub-image and the feature plane of the shooting points of each other sub-image.

[0025] 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; in order to facilitate subsequent analysis of the spatial distribution of different shooting points, in the embodiments of the present invention, the line-of-sight angle between the shooting points of any two sub-images and the normal angle between any two sub-images are first analyzed and obtained.

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

[0027] The information richness and information focus in the oral images obtained from different shooting angles are different. For example, when shooting from the leftmost side of the teeth, the information in the left region of the oral structure will be clearer, and more details can be obtained, while some hidden details in the right region of the oral structure will be ignored due to the angle and distance problems. Therefore, the closer the shooting point is to one boundary of the teeth, the clearer the details captured, and a higher edge distance parameter value will be obtained. The farther the shooting point is from the other boundary of the teeth, the more likely some hidden details will be lost. So, in the embodiments of the present invention, the edge distance parameter corresponding to the shooting point of the reference sub-image when shooting the oral image is first analyzed to reflect the performance degree of different shooting points for the oral structure information.

[0028] Preferably, in one embodiment of the present invention, the method for obtaining the edge distance parameter 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 leftmost tooth in the maxilla of the static oral structure as the left edge distance, and obtaining the distance between different shooting points and the rightmost tooth in the maxilla of the static oral structure as the right edge distance; obtaining the straight line between the leftmost tooth and the rightmost tooth in the maxilla of the oral structure as the internal oral line segment.

[0029] The edge distance parameter is obtained according to the edge distance parameter calculation formula, and the edge distance parameter calculation formula is as follows: In the formula, represents the serial number of the reference sub-image; represents the edge distance parameter when the shooting point corresponding to the reference sub-image shoots the oral image; represents the left edge distance of the shooting point corresponding to the reference sub-image; represents the right edge distance of the shooting point corresponding to the reference sub-image; represents the length of the internal oral line segment; represents the focal length between the shooting point of the main image and the shooting focus; represents the first distance; represents the tangent function.

[0030] In the calculation formula of the margin parameter value, represents the vertical distance between the main image shooting point and the line segment representing the oral cavity interior, represents the straight-line distance between the main image shooting point and the leftmost tooth or the rightmost tooth of the upper jaw, and this is used as the second distance, which is a fixed value; by using the function to limit the function value, if the left edge distance or the right edge distance of the reference sub-image shooting point is farther from the second distance, at this time or is greater than 1, then at this time the information supplement effect of the reference sub-image on the main image is limited, and the margin parameter value will decrease; when or is less than 1, at this time the left edge distance or the right edge distance of the reference sub-image shooting point is closer to the second distance, at this time the information supplement effect of the reference sub-image on the main image is better, and the margin parameter value will increase.

[0031] At this time, the viewing angle between the shooting points of any two sub-images is corresponded with the margin parameter value of the shooting points of any two sub-images, and the information supplement effect of the sub-images taken at different shooting points on the main image is reflected by the size of the margin parameter value.

[0032] Preferably, in an embodiment of the present invention, the method for obtaining the angle comprehensive value includes: taking the average value of the margin parameter values of the shooting points corresponding to two feature sub-images as the angle comprehensive value of the shooting points corresponding to any two feature sub-images, wherein the larger the angle comprehensive value, the greater the information supplement effect of the sub-image corresponding to the viewing angle of its shooting point on the main image.

[0033] In addition to the shooting angle of the sub-image, the gray-scale information and edge distribution of the teeth in the sub-image can also reflect the image information difference between the sub-image and the main image, and the sub-images taken are screened through the image information difference. Therefore, in the embodiment of the present invention, according to the gray-scale features in all corresponding regions of the reference sub-image and the main image, as well as the overall gray-scale features of the reference sub-image and the main image, the gray-scale similarity between the reference sub-image and the main image is obtained; according to the edge pixel point distribution features in each corresponding region of the reference sub-image and the main image, the angle comprehensive value of the shooting points of the reference sub-image and each other sub-image, and the normal angle between the reference sub-image and the feature plane of each other sub-image shooting point, the comprehensive score of the reference sub-image is obtained.

[0034] Preferably, in an embodiment of the present invention, the method for obtaining the gray-scale similarity includes: taking the same region of the oral cavity structure in the main image and the sub-image as the corresponding region between the main image and the sub-image; obtaining the gray-scale similarity according to the gray-scale similarity calculation formula, and the gray-scale similarity calculation formula is as follows: In the formula, represents the grayscale similarity between the reference sub - image and the main image; represents the number of corresponding regions between the reference sub - image and the main image; represents the grayscale mean value within the th corresponding region in the reference sub - image; represents the grayscale mean value of the reference sub - image; represents the grayscale mean value within the th corresponding region in the main image; represents the grayscale mean value 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 through the Pearson correlation coefficient formula. Among them, the Pearson correlation coefficient formula is a well - known technical means for those skilled in the art and will not be elaborated here.

[0036] Preferably, in an embodiment of the present invention, the method for obtaining the comprehensive score includes: obtaining the comprehensive score according to the comprehensive score calculation formula, and the comprehensive score calculation formula is as follows: In the formula, represents the comprehensive score of the reference sub - image; represents the grayscale similarity between the reference sub - image and the main image; represents the ratio of the number of edge pixel points in the th corresponding region of the reference sub - image to the total number of pixel points in the th corresponding region; represents the ratio of the number of edge pixel points in the th corresponding region of the main image to the total number of pixel points in the th corresponding region; represents the number of other sub - images other than the reference sub - image; represents the angular comprehensive value of the shooting point corresponding to the reference sub - image and the th other sub - image; represents the maximum value of the angular comprehensive values of the shooting points corresponding to the reference sub - image and other sub - images, which can be directly obtained by the prior art; represents the normal angle between the reference sub - image and the th other sub - image; represents the preset angle threshold; represents the logarithmic function with the natural constant as the base; represents the exponential function with the natural constant as the base.

[0037] In the comprehensive score calculation formula, the proportion of the number of edge pixel points in each corresponding region of the reference sub - image The larger the ratio between them indicates that the edge information of the secondary image is greater than that of the primary image at this time. At this time, the score of the reference secondary image should be increased, that is The larger it is, the greater the score of the reference secondary image at this time; since the shooting points of the two secondary images are too far apart, it will cause the information between the secondary images to be unable to complement each other, and additional secondary images need to be added to complete the information supplement. Therefore, a preset angle threshold is set. When the normal angle between the reference secondary image and any one secondary image is greater than the preset angle threshold, it is considered at this time that the normal angle between the secondary images will not generate information redundancy. So, the closer the angle comprehensive value between the reference secondary image and any one secondary image is to the maximum value, it indicates that the reference secondary image and this secondary image can obtain more oral structure information The larger it is, the greater the score of the reference secondary image at this time; when the normal angle between the reference secondary image and any one secondary image is less than the preset angle threshold, the shooting points of the two secondary images are closer at this time, and a large amount of information redundancy will be generated in the secondary images. When The smaller it is, the score of the reference secondary image should be adjusted smaller. So, through to is adjusted, that is The larger it is, the greater the score of the reference secondary image at this time.

[0038] In an 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 by itself and is not limited here.

[0039] Thus, the comprehensive score of each secondary image is obtained.

[0040] Step S3: Screen all secondary images according to the comprehensive score to obtain all high-quality secondary images; perform three-dimensional modeling of the patient's oral cavity based on all high-quality secondary images and the primary image.

[0041] Preferably, in an embodiment of the present invention, the method for obtaining high-quality secondary images includes: sorting all secondary images from high to low according to the comprehensive score to obtain a secondary image sequence; in the secondary image sequence, starting from the first secondary image, select a preset number of secondary images in sequence backward as the high-quality secondary images among all secondary images. In an embodiment of the present invention, the preset number is set to 10. It should be noted that the preset number can be set by itself and is not limited here.

[0042] Since the three-dimensional modeling technology is a well-known technical means in the art, it is not limited and elaborated here.

[0043] Thus, the three-dimensional modeling of the oral structure is completed.

[0044] In summary, collect all oral images of the patient and the shooting points corresponding to each oral image; obtain the main image and the sub-images among all oral images according to the position differences of the shooting points; obtain the line-of-sight angles between the shooting points of any two sub-images; obtain the normal angles of any two sub-images; select any one sub-image as the reference sub-image; obtain the margin parameter value when the shooting point corresponding to the reference sub-image shoots the oral image according to the positional relationship between the shooting point corresponding to the reference sub-image and the inside of the oral cavity; obtain the comprehensive angle value of the shooting points corresponding to any two sub-images according to the margin parameter values of the shooting points corresponding to any two sub-images; obtain all corresponding regions between the reference sub-image and the main image; obtain the gray-scale similarity between the reference sub-image and the main image according to the gray-scale characteristics in all corresponding regions between the reference sub-image and the main image, as well as the overall gray-scale characteristics of the reference sub-image and the main image; obtain the comprehensive score of the reference sub-image according to the distribution characteristics of the edge pixel points in each corresponding region between the reference sub-image and the main image, the comprehensive angle value of the shooting points of the reference sub-image and each other sub-image, and the normal angle of the characteristic plane of the shooting points of the reference sub-image and each other sub-image; screen all sub-images according to the comprehensive score to obtain all high-quality sub-images; perform three-dimensional modeling on the patient's oral cavity according to all high-quality sub-images and the main image.

[0045] Please refer to Figure 2 , which shows the structural block diagram of the second object of the present invention, a system for constructing an orthodontic effect model based on three-dimensional reconstruction. The system includes the following modules: an image acquisition module, configured to collect all oral images of the patient and the shooting points corresponding to each oral image; obtain the main image and the sub-images among all oral images according to the position differences of the shooting points; a scoring module, configured to obtain the line-of-sight angles between the shooting points of any two sub-images; obtain the normal angles of any two sub-images; select any one sub-image as the reference sub-image; obtain the margin parameter value when the shooting point corresponding to the reference sub-image shoots the oral image according to the positional relationship between the shooting point corresponding to the reference sub-image and the inside of the oral cavity; obtain the comprehensive angle value of the shooting points corresponding to any two sub-images according to the margin parameter values of the shooting points corresponding to any two sub-images; obtain all corresponding regions between the reference sub-image and the main image; obtain the gray-scale similarity between the reference sub-image and the main image according to the gray-scale characteristics in all corresponding regions between the reference sub-image and the main image, as well as the overall gray-scale characteristics of the reference sub-image and the main image; obtain the comprehensive score of the reference sub-image according to the distribution characteristics of the edge pixel points in each corresponding region between the reference sub-image and the main image, the comprehensive angle value of the shooting points of the reference sub-image and each other sub-image, and the normal angle of the characteristic plane of the shooting points of the reference sub-image and each other sub-image; a three-dimensional modeling module, configured to screen all sub-images according to the comprehensive score to obtain all high-quality sub-images; perform three-dimensional modeling on the patient's oral cavity according to all high-quality sub-images and the main image.

[0046] The third object of the embodiments of the present invention is to provide a computer device, including 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.

[0047] The fourth object of the embodiments of the present invention is to provide a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for constructing an oral orthodontic effect model based on three-dimensional reconstruction are implemented.

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

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

Claims

1. A method for constructing an orthodontic effect model based on three-dimensional reconstruction, characterized in that, The method includes: collecting all oral images of the patient and the shooting points corresponding to each oral image; obtaining the main image and the sub-images among all oral images according to the position differences of the shooting points; obtaining the line-of-sight angles between the shooting points of any two sub-images; obtaining the normal angles of any two sub-images; randomly selecting one sub-image as the reference sub-image; obtaining the margin parameter value when the oral image is shot at the shooting point corresponding to the reference sub-image according to the positional relationship between the shooting point corresponding to the reference sub-image and the inside of the oral cavity; obtaining the angle comprehensive value of the shooting points corresponding to any two sub-images according to the margin parameter values of the shooting points corresponding to any two sub-images; obtaining all corresponding regions of the reference sub-image and the main image; obtaining the comprehensive score of the reference sub-image according to the edge pixel point distribution characteristics of each corresponding region in the reference sub-image and the main image, the gray-scale similarity between the reference sub-image and the main image, the angle comprehensive value of the shooting points of the reference sub-image and each other sub-image, and the normal angle between the reference sub-image and the characteristic plane of the shooting point of each other sub-image; screening all sub-images according to the comprehensive score to obtain all high-quality sub-images; performing three-dimensional modeling of the patient's oral cavity according to all high-quality sub-images and the main image.

2. The method for constructing an orthodontic effect model based on three-dimensional reconstruction according to claim 1, wherein 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 distances between different shooting points and the leftmost tooth in the upper jaw of the static oral structure as the left edge distances, and obtaining the distances between different shooting points and the rightmost tooth in the upper jaw of the static oral structure as the right edge distances; obtaining the straight line between the leftmost tooth and the rightmost tooth in the upper jaw of the oral structure as the internal oral segment; obtaining the margin parameter value according to the margin parameter value calculation formula, and the margin parameter value calculation formula is as follows: In the formula, represents the serial number of the reference sub-image; represents the margin parameter value when the oral image is shot at the shooting point corresponding to the reference sub-image; represents the left edge distance of the shooting point corresponding to the reference sub-image; represents the right edge distance of the shooting point corresponding to the reference sub-image; represents the length of the internal oral segment; represents the focal length between the main image shooting point and the shooting focus; represents the first distance; represents the tangent function.

3. A method for constructing an 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 value of the margin parameter values of the shooting points corresponding to two characteristic sub-images as the angle comprehensive value of the shooting points corresponding to any two characteristic sub-images.

4. A method for constructing an orthodontic effect model based on three-dimensional reconstruction according to claim 1, characterized in that, The method for obtaining the grayscale similarity includes: taking the same regions of the oral structures in the main image and the secondary image as the corresponding regions between the main image and the secondary image; obtaining the grayscale similarity according to the grayscale similarity calculation formula, and the grayscale similarity calculation formula is as follows: In the formula, represents the grayscale similarity between the reference secondary image and the main image; represents the number of corresponding regions between the reference secondary image and the main image; represents the grayscale mean value within the -th corresponding region in the reference secondary image; represents the grayscale mean value of the reference secondary image; represents the grayscale mean value within the -th corresponding region in the main image; represents the grayscale mean value of the main image.

5. A method for constructing an 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 the comprehensive score calculation formula, and the comprehensive score calculation formula is as follows: In the formula, represents the comprehensive score of the reference sub - figure; represents the grayscale similarity between the reference sub - figure and the main figure; represents the proportion of the number of edge pixel points in the th corresponding area of the reference sub - figure to the total number of pixel points in the th corresponding area; represents the proportion of the number of edge pixel points in the th corresponding area of the main figure to the total number of pixel points in the th corresponding area; represents the number of other sub - figures except the reference sub - figure; represents the angular comprehensive value of the shooting points corresponding to the reference sub - figure and the th other sub - figure; represents the maximum value of the angular comprehensive values of the shooting points corresponding to the reference sub - figure and other sub - figures; represents the normal angle between the reference sub - figure and the th other sub - figure; represents the preset angle threshold; represents the logarithmic function with the natural constant as the base; represents the exponential function with the natural constant as the base.

6. The method for constructing an orthodontic effect model based on three-dimensional reconstruction according to claim 1, characterized in that, The method for obtaining the high-quality sub-images includes: sorting all sub-images in descending order according to the comprehensive score 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 backward as the high-quality sub-images among all sub-images.

7. An orthodontic effect model construction system 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, it implements the steps of the method according to any one of claims 1 to 6.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of a method for constructing an oral orthodontic effect model based on three-dimensional reconstruction according to any one of claims 1 to 6.

9. A computer device, 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, it implements the steps of a method for constructing an oral orthodontic effect model based on three-dimensional reconstruction according to any one of claims 1 to 6.

Images