Method, device and equipment for detecting orthodontic effect and storage medium

Abstract

The present disclosure relates to a tooth correction effect detection method, device, equipment and storage medium, the tooth correction effect detection method comprising: acquiring a tooth image, the tooth image comprising a target tooth; identifying the target tooth in the tooth image based on a pre-trained neural network model, and determining feature information of the target tooth; determining pose information of the target tooth according to the feature information and a tooth model corresponding to the target tooth; mapping the tooth model into the tooth image based on the pose information, and generating a detection result of a target tooth correction effect based on the tooth image. The method provided by the present disclosure can automatically obtain relevant data of the tooth correction effect in real time during the tooth diagnosis and treatment process, detect the tooth correction effect, and is simple and easy to operate and implement. Moreover, it is convenient for subsequent medical staff to understand the tooth correction situation and timely adjust the correction scheme.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of information processing, and particularly relates to a tooth correction effect detection method and device, equipment and a storage medium. BACKGROUND

[0002] With the development of society, orthodontic treatment as a way of oral aesthetic treatment is paid more and more attention by people. Among them, "three-dimensional digital orthodontics" as a new digital correction technology is widely used. In the process of oral tooth treatment, the doctor generally collects the tooth image of the user through the handle of the intraoral scanner, then views the tooth image displayed on the display, and judges the tooth loss or defect of the user after diagnosis.

[0003] In the traditional orthodontic treatment process, the user needs to scan the user's teeth through the intraoral scanner at each review to obtain the current tooth model of the user and process it, and then compare it with the preset model to obtain the error report and the treatment effect. However, this process is time-consuming and costly, which will cause waste of manpower and material resources. SUMMARY

[0004] In order to solve the above technical problems, the present disclosure provides a tooth correction effect detection method, device, equipment and medium. In the process of tooth diagnosis and treatment, the tooth correction effect can be detected in real time and automatically by collecting tooth images, which is simple and easy to implement.

[0005] In a first aspect, the present disclosure provides a tooth correction effect detection method, comprising:

[0006] obtaining a tooth image, wherein the tooth image includes a target tooth;

[0007] identifying the target tooth in the tooth image based on a pre-trained neural network model to determine feature information of the target tooth;

[0008] determining pose information of the target tooth according to the feature information and a tooth model corresponding to the target tooth;

[0009] mapping the tooth model into the tooth image based on the pose information, and generating a detection result of the target tooth correction effect based on the tooth image.

[0010] Optionally, before the tooth image is obtained, the method further comprises:

[0011] obtaining tooth scanning data, and constructing a three-dimensional tooth model according to the tooth scanning data, wherein the three-dimensional tooth model includes a tooth model corresponding to at least one tooth;

[0012] The tooth scanning data is acquired by a three-dimensional scanner.

[0013] Optionally, the feature information includes a number of the target tooth; and each tooth model included in the three-dimensional tooth model has a number.

[0014] Optionally, the determining of the pose information of the target tooth according to the feature information and the tooth model corresponding to the target tooth includes:

[0015] acquiring a tooth model with the same number as the target tooth in the three-dimensional tooth model;

[0016] determining the pose information of the target tooth according to the feature information and the tooth model.

[0017] Optionally, the feature information further includes a coordinate of the target tooth.

[0018] Optionally, the determining of the pose information of the target tooth according to the feature information and the tooth model includes:

[0019] determining a coordinate system of the tooth model, and converting the coordinate of the target tooth into the coordinate system;

[0020] determining the pose information of the target tooth in the coordinate system based on the converted coordinate of the target tooth and the pose information of the tooth model.

[0021] Optionally, the pose information includes orientation and position information.

[0022] Optionally, the determining of the pose information of the target tooth in the coordinate system based on the converted coordinate of the target tooth and the pose information of the tooth model includes:

[0023] fitting a contour line of the target tooth and a contour line of the tooth model based on the converted coordinate of the target tooth and the position information of the tooth model, to determine the position information of the target tooth;

[0024] determining the orientation of the target tooth according to the orientation of the tooth model;

[0025] obtaining the pose information of the target tooth in the coordinate system according to the orientation and the position information of the target tooth.

[0026] Optionally, the feature information further includes a feature point, and the feature point is used to identify a local feature of the target tooth.

[0027] Optionally, after the pose information of the target tooth is determined, the method further includes:

[0028] obtain other tooth images including the target tooth, and update the pose information according to a first feature point in feature information corresponding to the other tooth images and a second feature point in feature information corresponding to the tooth image.

[0029] Optionally, the mapping the tooth model into the tooth image based on the pose information and generating the detection result of the orthodontic effect of the target tooth based on the tooth image comprises:

[0030] mapping the tooth model into the tooth image based on the pose information to obtain a mapping image;

[0031] calculating a pixel difference between the tooth image and the mapping image;

[0032] generating the detection result of the orthodontic effect of the target tooth according to the pixel difference.

[0033] In a second aspect, the embodiments of the present disclosure provide a detection device for orthodontic effect, comprising:

[0034] an obtaining unit configured to obtain a tooth image, wherein the tooth image includes a target tooth;

[0035] an identifying unit configured to identify the target tooth in the tooth image based on a pre-trained neural network model, and determine feature information of the target tooth;

[0036] a determining unit configured to determine pose information of the target tooth according to the feature information and a tooth model corresponding to the target tooth;

[0037] a detecting unit configured to map the tooth model into the tooth image based on the pose information, and generate a detection result of an orthodontic effect of the target tooth based on the tooth image.

[0038] In a third aspect, the embodiments of the present disclosure provide an electronic device, comprising:

[0039] a memory;

[0040] a processor; and

[0041] a computer program;

[0042] wherein the computer program is stored in the memory and configured to be executed by the processor to implement the above-mentioned detection method for orthodontic effect.

[0043] In a fourth aspect, the embodiments of the present disclosure provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the above-mentioned detection method for orthodontic effect.

[0044] The method for detecting the tooth correction effect provided in the embodiments of the present disclosure comprises: acquiring a tooth image; identifying the tooth image based on a pre-trained neural network model to determine feature information of a target tooth in the tooth image; determining pose information of the target tooth according to the feature information and a tooth model corresponding to the target tooth; mapping the tooth model into the tooth image based on the pose information, and generating a detection result of a target tooth correction effect based on the tooth image. The method provided in the present disclosure only needs to capture a two-dimensional image including teeth during the tooth diagnosis and treatment process. The two-dimensional tooth can be acquired by a terminal or other device with a shooting function. The user can complete the detection at home without using a professional intraoral scanner. Therefore, the user does not need to frequently visit the doctor, and can only acquire the relevant data of the tooth correction effect in real time and automatically by capturing the image of the current corrected tooth, detect the tooth correction effect, and the operation is simple and convenient to implement. Meanwhile, it is also convenient for the subsequent medical staff to understand the correction process and timely adjust the correction scheme. BRIEF DESCRIPTION OF DRAWINGS

[0045] The accompanying drawings, which are incorporated into and form a part of the specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure.

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, for those skilled in the art, other drawings can also be obtained based on these drawings without creative labor.

[0047] Figure 1 A flowchart of a method for detecting a tooth correction effect provided in the embodiments of the present disclosure;

[0048] Figure 2 A schematic diagram of an application scenario provided in the embodiments of the present disclosure;

[0049] Figure 3 A schematic diagram of a tooth image provided in the embodiments of the present disclosure;

[0050] Figure 4 A schematic diagram of a tooth model provided in the embodiments of the present disclosure;

[0051] Figure 5 A flowchart of a method for detecting a tooth correction effect provided in the embodiments of the present disclosure;

[0052] Figure 6 A structural schematic diagram of a device for detecting a tooth correction effect provided in the embodiments of the present disclosure;

[0053] Figure 7A structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0054] In order to enable a more clear understanding of the above-mentioned objects, features and advantages of the present disclosure, the schemes of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0055] In the following description, a large number of specific details are set forth in order to facilitate a thorough understanding of the present disclosure, but the present disclosure can also be implemented in other manners different from those described herein; obviously, the embodiments described in the specification are only a part of the embodiments of the present disclosure, and not all the embodiments.

[0056] With the development of society, orthodontic treatment as a way of oral aesthetic treatment is more and more valued by people. Orthodontic treatment mainly guides the periodontal tissue reconstruction by applying orthodontic force to the teeth, so as to change the position of the teeth in the alveolar bone. Orthodontic treatment can improve the malocclusion caused by crowded dentition, abnormal tooth arrangement, etc., so as to achieve long-term stability of periodontal tissue. As a new digital orthodontic technology, "three-dimensional digital orthodontic" is widely used. It is more accurate than traditional orthodontics for misaligned teeth, and is favored by people with beautiful teeth for its more natural effect, shorter correction time, no rebound, etc. In the process of oral tooth treatment, the doctor generally collects the tooth image of the user through the handle of the intraoral scanner, then views the tooth image displayed on the display, and judges the tooth loss or defect of the user after diagnosis. In the traditional orthodontic treatment process, the user needs to come to the hospital for reexamination many times, and needs to scan the user's teeth through the intraoral scanner at each reexamination to obtain the current tooth model of the user and process it, and then compare it with the preset model to check whether the tooth correction matches the pre-designed scheme, so as to obtain the error report and treatment effect, but this process is time-consuming and labor-intensive, and the reexamination cost is high, and the user's cooperation degree is not high, and the phenomenon of delayed reexamination often occurs, which leads to an increase in the failure rate of the correction scheme and affects the final treatment effect, and it is also a waste of manpower and material resources.

[0057] In view of the above technical problems, the present embodiment provides a tooth correction effect detection method. In the process of tooth diagnosis and treatment, the current correction effect of the tooth is analyzed based on the tooth image and the expected model by real-time shooting of the tooth image, which is simple to operate and can also provide correction data for relevant medical personnel, so as to facilitate subsequent adjustment according to the correction data, and frequent reexamination is not required, which to some extent reduces the waste of manpower and material resources. Specifically, one or more of the following embodiments are described in detail.

[0058] Figure 1A method for detecting a tooth correction effect is provided in the embodiments of the present disclosure, which is used for detecting a current correction effect of teeth, so as to facilitate understanding of the tooth correction. The method specifically comprises the following steps S110 to S140 as shown in the figure: Figure 1

[0059] In S110, a tooth image is acquired, and the tooth image includes a target tooth.

[0060] Specifically, the method for detecting the tooth correction effect can be executed by a terminal or a server. Specifically, the terminal or the server can detect the correction effect of the target tooth by using a tooth model and a tooth image. The target tooth refers to a single tooth, and a tooth image can include multiple teeth. When detecting each tooth, the tooth can be referred to as the target tooth. For example, in an application scenario, as shown in the figure, Figure 2 the server 22 includes a tooth model. The server 22 receives a tooth image transmitted by the terminal 21, and then detects the correction effect of the tooth based on the tooth image and the tooth model. The tooth image can be obtained by the terminal 21 through shooting. Alternatively, the tooth image is obtained by the terminal 21 from other devices. Alternatively, the tooth image is obtained by the terminal 21 through image processing on a preset image. The preset image can be obtained by the terminal 21 through shooting, or the preset image can be obtained by the terminal 21 from other devices. Here, the other devices are not specifically limited. In another application scenario, the terminal 21 includes a tooth model. After the terminal 21 acquires a tooth image, the terminal 21 detects the correction effect of the tooth according to the tooth image and the tooth model.

[0061] It can be understood that the method for detecting the tooth correction effect provided in the embodiments of the present disclosure is not limited to the above-mentioned several possible scenarios. Hereinafter, the terminal 21 will be taken as an example to execute the method for detecting the tooth correction effect.

[0062] It can be understood that the terminal acquires a tooth image including a target tooth through a collecting device. The tooth image includes at least one complete tooth. If the tooth image includes multiple teeth, the correction effect of each tooth needs to be analyzed. The tooth image is shown in the figure, Figure 3 Figure 3 A schematic diagram of a tooth image is provided in the embodiments of the present disclosure, Figure 3 the tooth image 310 includes two teeth, and the outlines of the two teeth are clear. The two teeth are denoted as tooth 311 and tooth 312. Figure 3 ​​The middle tooth image 320 includes teeth 321. It can be understood that the acquisition device can be embedded in a terminal or used as an external device combined with the terminal. The terminal can be a mobile phone or a tablet computer. The embedded terminal can be a device provided with the terminal itself, such as a camera configured by the terminal. The camera captures a two-dimensional image of the teeth or captures video data of a tooth. Each frame of the video data is a two-dimensional tooth image. The external device can be a device with acquisition function, such as an oral cavity imaging instrument. The oral cavity imaging instrument also captures the image of each frame of the teeth in the oral cavity. The specific external device is not limited. It can be understood that the method of obtaining the tooth image is not limited and can be selected according to user needs.

[0063] Optionally, the terminal needs to obtain a tooth model before obtaining the tooth image. The method specifically includes: obtaining tooth scanning data, and constructing a three-dimensional tooth model according to the tooth scanning data. The three-dimensional tooth model includes at least one tooth model corresponding to a tooth. The tooth scanning data is obtained by a three-dimensional scanner.

[0064] Optionally, the tooth model corresponding to each tooth in the three-dimensional tooth model is numbered.

[0065] It can be understood that the terminal will scan the teeth by a three-dimensional scanning device before shooting the tooth image to obtain tooth scanning data. For example, the teeth of a user need to be corrected. Relevant medical personnel uses a three-dimensional scanner to scan all the teeth of the user to generate tooth scanning data. A tooth model of the user before correction is constructed according to the tooth scanning data. All single tooth models constitute a three-dimensional tooth model of the user. The pose of each tooth model before correction can also be adjusted to obtain a three-dimensional tooth model after correction. All tooth models in the three-dimensional tooth model after correction constitute an expected model. The expected model is the most ideal effect model after correction. The following embodiments are described by taking the tooth model after correction as an example. After obtaining the tooth model after correction of each tooth, because the entire three-dimensional tooth model is obtained by scanning data, a neural network model is used to divide the three-dimensional tooth model (three-dimensional tooth model) of the user into single tooth models. That is, the three-dimensional tooth model is composed of multiple single tooth models, and each tooth model is numbered. The numbering facilitates the positioning of the single tooth model. For example, the user includes 28 teeth, and each tooth needs to be corrected. The 28 single tooth models in the tooth model are numbered and can be respectively recorded as 1 to 28. It can be understood that only the single tooth model that needs to be corrected can be numbered, and the remaining teeth that do not need to be corrected are not numbered.

[0066] For example, referring to Figure 4 , Figure 4 A schematic diagram of a tooth model provided by the embodiment of the present disclosure, Figure 4The three-dimensional tooth model is a three-dimensional model, Figure 4 The tooth model 411 and the tooth model 412 correspond to the tooth 311 and the tooth 312 in the tooth 300 respectively, that is, the tooth model corresponding to the tooth 311 after correction is 411, the tooth model corresponding to the tooth 312 after correction is 412, and the tooth model corresponding to the tooth 321 in the tooth image 320 after correction is 413. Figure 3

[0067] S120, identifying the target tooth in the tooth image based on the pre-trained neural network model to determine the feature information of the target tooth.

[0068] Optionally, the feature information includes feature points, coordinates of the target tooth, and a number of the target tooth.

[0069] Understandably, on the basis of the above S110, after the terminal acquires the tooth image, the tooth image is identified based on the pre-trained neural network model to determine the feature information of the target tooth in the tooth image. The pre-trained neural network model can be a model with feature extraction and identification functions, and the specific model is not limited as long as it can identify the tooth to obtain the feature information; wherein the feature information includes feature points, numbers, and coordinates of the tooth image. If the tooth image includes multiple teeth, the feature information of each tooth in the multiple teeth is identified, and a feature information including features of all teeth can also be obtained. One feature information can also be understood as the feature information corresponding to the tooth image. Specifically, see Figure 3 , Figure 3 The tooth image 310 includes the tooth 311 and the tooth 312, and the tooth image 320 includes the tooth 321. If a single tooth is detected, the tooth 311 and the tooth 312 in the tooth image 310 can both be recorded as target teeth, and the tooth 321 in the tooth image 320 can be recorded as a target tooth. The following embodiments take the tooth 321 as an example to illustrate the target tooth. The feature information corresponding to the tooth 321 includes feature points of the tooth 321. The feature points can be points where the image gray value changes sharply on the tooth image or points with large curvature on the edge of the tooth image. The coordinates of the tooth 321 can specifically refer to a plurality of coordinate points included in the contour line (edge line) of the tooth 321. The number of the tooth 321 is used to determine a specific single tooth model in the pre-constructed three-dimensional tooth model, that is, the number of the tooth 321 is the same as the number of a single tooth model in the three-dimensional tooth model, so as to determine the tooth model corresponding to the target tooth. The tooth model corresponding to the tooth 321 is 412 in the tooth model 412. Figure 4

[0070] S130, determining the pose information of the target tooth according to the feature information and the tooth model corresponding to the target tooth.

[0071] ​​It can be understood that, on the basis of S120, the tooth model corresponding to the target tooth is determined according to the number in the feature information corresponding to the target tooth, and then the pose information of the target tooth is determined according to the feature points and / or coordinates in the feature information and the related information of the tooth model. The pose information includes orientation and spatial position information. The orientation refers to the posture of the tooth, for example, the posture of the tooth being upward or downward relative to the three-dimensional tooth model. The spatial position information can also be understood as three-dimensional coordinate information.

[0072] Optionally, after the pose information of the target tooth is determined, the method further includes: acquiring other tooth images including the target tooth, and updating the pose information according to the first feature points in the feature information corresponding to the other tooth images and the second feature points in the feature information corresponding to the tooth images.

[0073] It can be understood that, if only one image including the target tooth is acquired, the pose information of the target tooth is directly calculated according to the coordinates in the feature information and the related information of the tooth model corresponding to the target tooth; if multiple images including the target tooth are acquired, after the pose information is calculated according to the coordinates in the feature information corresponding to any one of the multiple tooth images and the related information of the tooth model, the pose information is updated based on the feature points corresponding to the multiple tooth images, that is, the determined pose information is optimized by matching the feature points determined in different tooth images, so as to improve the accuracy. The feature points corresponding to the multiple tooth images include the first feature points included in the above-mentioned any one of the tooth images, and the second feature points corresponding to the remaining tooth images of the multiple tooth images except the any one of the tooth images; or, multiple pose information of the target tooth can also be calculated according to the feature information calculated from the multiple tooth images, for example, 10 tooth images including tooth 321 are acquired, 10 pose information corresponding to tooth 321 is calculated respectively according to the coordinates in the feature information corresponding to each of the 10 tooth images, and then the 10 pose information determined above is jointly optimized according to the feature points in the feature information corresponding to the 10 tooth images to obtain the optimal pose information, so as to improve the accuracy of the detection result.

[0074] S140, mapping the tooth model into the tooth image based on the pose information, and generating a detection result of the orthodontic effect of the target tooth based on the tooth image.

[0075] It can be understood that, on the basis of S130 above, the terminal determines the pose information, and projects the tooth model corresponding to the target tooth number in the tooth image onto the tooth image according to the pose information. The pose information obtained by including only one target tooth in the tooth image can also be understood as the pose information corresponding to the tooth image, that is, the correspondence between the target tooth in the tooth image and the tooth model is established, and then the correspondence between the image coordinate system of the tooth image and the world coordinate system of the tooth model is established. Then, the tooth model is projected into the tooth image, and a detection result of the target tooth correction effect is generated based on the mapped tooth image. It can be understood that the projected tooth image includes a two-dimensional tooth model and a target tooth, the image is a two-dimensional image, the tooth model is a three-dimensional tooth model, and the three-dimensional tooth model is mapped to a two-dimensional tooth image. The tooth model included in the tooth image is a two-dimensional tooth model. The tooth model and the target tooth overlap in a large area, but there is a difference in the pixel points. The difference can reflect the correction of the tooth in the correction process. The detection result can be whether the correction effect meets the expectation, for example, see Figure 3 The tooth model is projected into the tooth image 320 to obtain a mapping image 330. The mapping image 330 includes a two-dimensional tooth model 331 and a target tooth 321. The two-dimensional tooth model 331 covers most of the target tooth 321. The pixel difference between the tooth image and the mapping image can also be calculated. The difference between the target tooth in the tooth image and the tooth model in the mapping image reflects the correction of the tooth in the correction process. The detection result can be whether the correction effect meets the expectation. After obtaining the detection result, the relevant data and the detection result involved in the detection process can be sent to relevant medical personnel for inspection. The relevant medical personnel can judge whether the detection result meets the expectation, so as to facilitate subsequent rapid understanding of the correction and timely adjustment of the correction method.

[0076] Optionally, the above mapping of the tooth model into the tooth image based on the pose information and generating a detection result of the target tooth correction effect based on the tooth image specifically includes: mapping the tooth model into the tooth image based on the pose information to obtain a mapping image; calculating the pixel difference between the tooth image and the mapping image; and generating a detection result of the target tooth correction effect according to the pixel difference.

[0077] It can be understood that the generation of the detection result in S140 above specifically includes the following implementation process: mapping the tooth model corresponding to the target tooth into the tooth image based on the pose information of the tooth image to obtain a mapping image, see Figure 3 , Figure 3The tooth 321 is included in the tooth image 320, after the pose information of the tooth 321 is obtained, the tooth model 413 corresponding to the tooth 321 is mapped into the tooth image 320 according to the pose information, and the mapped tooth image is denoted as 330. The mapped image 330 includes the two-dimensional tooth model 331 after mapping and the target tooth 321 which is mostly covered by the tooth model 331. After the mapped image 330 is obtained, the pixel difference between the target tooth 321 and the tooth model 331 in the mapped image 330 is calculated, or the pixel difference between the tooth image 320 and the mapped image 330 is directly calculated, that is, the fitting error of the target tooth 321 and the tooth model 331 is calculated. Finally, the pixel difference is analyzed to analyze whether the tooth correction meets the expectation, that is, whether the current correction of the tooth meets the tooth model after correction constructed above, that is, whether the current correction of the tooth meets the tooth model or whether the correction error occurs, and then the detection result of the target tooth correction effect is generated according to the pixel difference and the analysis result.

[0078] The method for detecting the tooth correction effect provided by the embodiment of the present disclosure includes: acquiring a tooth image, the tooth image including a target tooth; identifying the target tooth in the tooth image based on a pre-trained neural network model to determine feature information of the target tooth; determining pose information of the target tooth according to the feature information and a tooth model corresponding to the target tooth; mapping the tooth model into the tooth image based on the pose information, and generating a detection result of a target tooth correction effect based on the tooth image. The method provided by the present disclosure can be used in the tooth diagnosis and treatment process. The user can collect the tooth image by using a mobile terminal, which can be a mobile phone. The user can complete the detection at home without using a professional intraoral scanner. Therefore, the user can obtain the related data of the tooth correction effect in real time and conveniently, and analyze the tooth correction effect by using a real-time automatic comparison method to generate the detection result. The operation is simple and convenient to implement. The related medical staff can remotely diagnose to improve the medical compliance of the user and timely adjust the correction scheme to improve the success rate of orthodontic correction.

[0079] On the basis of the above-mentioned embodiment, according to the feature information and the tooth model corresponding to the target tooth, the pose information of the target tooth is determined, specifically including the following steps S510 to S520 as shown in the figure: Figure 5

[0080] S510, acquiring a tooth model with the same number as the target tooth in the three-dimensional tooth model.

[0081] ​It can be understood that after the terminal constructs the three-dimensional tooth model according to the tooth scanning data, the tooth model with the same number as the target tooth is selected in the three-dimensional tooth model, the three-dimensional tooth model includes all single tooth models of the teeth to be corrected by the user, and each single tooth model has a number, for example, Figure 3 The number of the target tooth 321 in the tooth image 320 is 16, and the single tooth model with the same number 16 is obtained in the three-dimensional tooth model, that is, the tooth model 413 in the above Figure 4 .

[0082] S520, according to the feature information and the tooth model, determining the pose information of the target tooth.

[0083] It can be understood that on the basis of the above S510, after determining the tooth model corresponding to the target tooth, the pose information of the target tooth is determined according to the coordinates in the feature information and the related information of the tooth model.

[0084] Optionally, according to the feature information and the tooth model, the pose information of the target tooth is determined, specifically including: determining the coordinate system of the tooth model, and converting the coordinates of the target tooth to the coordinate system; based on the converted coordinates of the target tooth and the pose information of the tooth model, determining the pose information of the target tooth in the coordinate system.

[0085] It can be understood that according to the feature information and the tooth model, the pose information of the target tooth is determined, specifically including the following steps: determining the coordinate system of the tooth model, which is specifically a world coordinate system, which is determined by a three-dimensional scanner that scans the tooth; after determining the coordinate system, the coordinates of the target tooth are converted to the world coordinate system, the coordinates corresponding to the tooth image are the image coordinate system, and the coordinates of the target tooth in the tooth image are also the image coordinate system. The conversion between the image coordinate system and the world coordinate system is also realized, that is, the entire tooth image is unified to the world coordinate system, which is convenient for determining the pose information of the target tooth in the world coordinate system; then based on the converted coordinates of the target tooth and the pose information of the tooth model in the world coordinate system, the pose information of the target tooth in the world coordinate system is determined. The coordinates of the target tooth specifically refer to the plurality of coordinates constituting the contour line or the edge line of the target tooth in the tooth image.

[0086] Optionally, based on the converted coordinates of the target tooth and the pose information of the tooth model, the pose information of the target tooth in the coordinate system is determined, specifically including: based on the converted coordinates of the target tooth and the position information of the tooth model, fitting the contour line of the target tooth and the contour line of the tooth model to determine the position information of the target tooth; determining the orientation of the target tooth according to the orientation of the tooth model; obtaining the pose information of the target tooth in the coordinate system according to the orientation and the position information of the target tooth.

[0087] It can be understood that the above determining the pose information of the target tooth in the coordinate system based on the converted coordinates of the target tooth and the pose information of the tooth model specifically includes the following steps: the pose information includes position information and orientation, the position information is a spatial three-dimensional coordinate, and the orientation is used to determine the posture of the tooth in the entire tooth model; fitting the contour line of the target tooth and the contour line of the tooth model based on the converted two-dimensional coordinates of the contour line of the target tooth and the position information of the tooth model in the world coordinate system, to determine the position information of the target tooth in the coordinate system; then determining the orientation of the target tooth in the coordinate system according to the orientation in the pose information of the tooth model; and finally obtaining the pose information of the target tooth in the coordinate system according to the orientation of the target tooth and the position information of the target tooth. After the pose information of the target tooth is determined, the conversion relationship between the tooth image and the tooth model is established, which facilitates subsequent mapping of the tooth model into the tooth image and analysis of the correction effect.

[0088] The method for detecting the tooth correction effect provided in the embodiments of the present disclosure can obtain the tooth model with the same number as the target tooth in the three-dimensional tooth model, that is, the tooth model is positioned to determine the tooth model corresponding to the target tooth. Then, the pose information of the target tooth in the coordinate system of the tooth model is determined according to the coordinates of the contour line of the target tooth in the feature information and the pose information of the tooth model, thereby establishing the relationship between the tooth model and the target tooth. This facilitates subsequent mapping of the tooth model into the tooth image according to the pose information and analysis of the correction effect of each tooth.

[0089] Figure 6 The structure diagram of the detection device for tooth correction effect provided in the embodiments of the present disclosure is shown. The detection device for tooth correction effect provided in the embodiments of the present disclosure can execute the processing flow provided in the detection method for tooth correction effect, as shown in Figure 6 The detection device for tooth correction effect 600 includes:

[0090] The acquisition unit 610 is configured to acquire a tooth image, and the tooth image includes a target tooth.

[0091] The recognition unit 620 is configured to recognize the target tooth in the tooth image based on a pre-trained neural network model, and determine feature information of the target tooth.

[0092] The determination unit 630 is configured to determine pose information of the target tooth according to the feature information and a tooth model corresponding to the target tooth.

[0093] The detection unit 640 is configured to map the tooth model into the tooth image based on the pose information, and generate a detection result of a correction effect of the target tooth based on the tooth image.

[0094] Optionally, the apparatus 600 further comprises a constructing unit, configured to, before the acquiring of the tooth image, specifically configured to:

[0095] acquire tooth scanning data, and construct a three-dimensional tooth model according to the tooth scanning data, wherein the three-dimensional tooth model comprises at least one tooth model corresponding to a tooth;

[0096] The tooth scanning data is acquired by a three-dimensional scanner.

[0097] Optionally, in the apparatus 600, the feature information comprises a number of the target tooth; and each tooth model in the three-dimensional tooth model has a number.

[0098] Optionally, in the determining unit 630, the determining of the pose information of the target tooth according to the feature information and the tooth model corresponding to the target tooth is specifically configured to:

[0099] acquire a tooth model with the same number as the target tooth in the three-dimensional tooth model;

[0100] determine the pose information of the target tooth according to the feature information and the tooth model.

[0101] Optionally, in the apparatus 600, the feature information further comprises a coordinate of the target tooth.

[0102] Optionally, in the determining unit 630, the determining of the pose information of the target tooth according to the feature information and the tooth model is specifically configured to:

[0103] determine a coordinate system of the tooth model, and convert the coordinate of the target tooth into the coordinate system;

[0104] determine the pose information of the target tooth in the coordinate system based on the converted coordinate of the target tooth and the pose information of the tooth model.

[0105] Optionally, in the apparatus 600, the pose information comprises orientation information and position information.

[0106] Optionally, in the determining unit 630, the determining of the pose information of the target tooth in the coordinate system based on the converted coordinate of the target tooth and the pose information of the tooth model is specifically configured to:

[0107] fit a contour line of the target tooth and a contour line of the tooth model based on the converted coordinate of the target tooth and the position information of the tooth model, and determine the position information of the target tooth;

[0108] determine an orientation of the target tooth according to the orientation of the tooth model;

[0109] obtain pose information of the target tooth in the coordinate system according to the orientation of the target tooth and the position information.

[0110] Optionally, the feature information in the apparatus 600 further includes feature points, and the feature points are used to identify local features of the target tooth.

[0111] Optionally, the apparatus 600 further includes an updating unit, and the updating unit is configured to, after the pose information of the target tooth is determined, specifically:

[0112] obtain another tooth image including the target tooth, and update the pose information according to a first feature point in feature information corresponding to the another tooth image and a second feature point in feature information corresponding to the tooth image.

[0113] Optionally, the detection unit 640 is configured to, after the tooth model is mapped into the tooth image based on the pose information and the detection result of the orthodontic effect of the target tooth is generated based on the tooth image, specifically:

[0114] map the tooth model into the tooth image based on the pose information to obtain a mapping image;

[0115] calculate a pixel difference between the tooth image and the mapping image;

[0116] generate the detection result of the orthodontic effect of the target tooth according to the pixel difference.

[0117] Figure 6 The detection apparatus for the orthodontic effect of the tooth in the embodiments can be used to execute the technical solutions of the method embodiments, and has similar implementation principles and technical effects, which will not be described here.

[0118] Figure 7 A structural schematic diagram of an electronic device is provided in the embodiments of the present disclosure. The electronic device provided in the embodiments of the present disclosure can execute the detection method for the orthodontic effect of the tooth provided in the above embodiments, as shown in the following figure. Figure 7 As shown in the figure, the electronic device 700 includes a processor 710, a communication interface 720 and a memory 730; wherein a computer program is stored in the memory 730 and is configured to be executed by the processor 710 to execute the detection method for the orthodontic effect of the tooth as described above.

[0119] In addition, the embodiments of the present disclosure further provide a computer readable storage medium, and a computer program is stored on the computer readable storage medium, and the computer program is executed by a processor to implement the detection method for the orthodontic effect of the tooth described in the above embodiments.

[0120] In addition, the disclosure also provides a computer program product, which comprises a computer program or instructions, and the computer program or instructions are executed by a processor to realize the method for detecting the tooth correction effect as described above.

[0121] It should be noted that, in this document, relational terms such as“first” and“second”, and the like, are used solely to distinguish one entity or action from another entity or action, without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms“comprises”,“comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by“comprises... a” does not, without more limitations, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the recited element.

[0122] The above description is merely that of specific embodiments of the disclosure, enabling a person skilled in the art to understand or implement the disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the disclosure. Therefore, the disclosure will not be limited to these embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of detecting the effect of orthodontic treatment, characterized in that, The method comprises: obtaining a tooth image, wherein the tooth image comprises a target tooth, and the target tooth refers to a single tooth; identifying the target tooth in the tooth image based on a pre-trained neural network model to determine feature information of the target tooth; determining pose information of the target tooth according to the feature information and a tooth model corresponding to the target tooth, wherein the tooth model is a corrected tooth model, and the pose information comprises orientation and spatial position information; mapping the tooth model into the tooth image based on the pose information, and generating a detection result of a correction effect of the target tooth based on the tooth image, which comprises: mapping the tooth model into the tooth image based on the pose information to obtain a mapping image; calculating a pixel difference between the tooth image and the mapping image; and generating the detection result of the correction effect of the target tooth according to the pixel difference. The feature information further comprises coordinates of the target tooth; and the determination of the pose information of the target tooth according to the feature information and the tooth model comprises: determining a coordinate system of the tooth model, and converting the coordinates of the target tooth into the coordinate system; and determining the pose information of the target tooth in the coordinate system based on the converted coordinates of the target tooth and the pose information of the tooth model, so as to map the tooth model into the tooth image.

2. The method of claim 1, wherein, Before the tooth image is obtained, the method further comprises: obtaining tooth scanning data, and constructing a three-dimensional tooth model according to the tooth scanning data, wherein the three-dimensional tooth model comprises at least one tooth model corresponding to a tooth; The tooth scanning data is obtained by a three-dimensional scanner.

3. The method of claim 2, wherein, The feature information comprises a number of the target tooth, and each tooth model in the three-dimensional tooth model has a number; and the determination of the pose information of the target tooth according to the feature information and the tooth model corresponding to the target tooth comprises: obtaining a tooth model with the same number as the target tooth in the three-dimensional tooth model; determining the pose information of the target tooth according to the feature information and the tooth model.

4. The method of claim 3, wherein, The determination of the pose information of the target tooth in the coordinate system based on the converted coordinates of the target tooth and the pose information of the tooth model comprises: fitting a contour line of the target tooth and a contour line of the tooth model based on the converted coordinates of the target tooth and the position information of the tooth model to determine position information of the target tooth; determining the orientation of the target tooth according to the orientation of the tooth model; obtaining the pose information of the target tooth in the coordinate system according to the orientation and the position information of the target tooth.

5. The method of claim 1, wherein, The feature information further comprises feature points, and the feature points are used to identify local features of the target tooth. After the pose information of the target tooth is determined, the method further comprises: Obtain other tooth images including the target tooth, and update the pose information according to first feature points in feature information corresponding to the other tooth images and second feature points in feature information corresponding to the tooth image.

6. A device for detecting the effect of orthodontic treatment of teeth, characterized in that Comprise: An acquisition unit is configured to acquire a tooth image, wherein the tooth image includes a target tooth, and the target tooth refers to a single tooth; An identification unit is configured to identify the target tooth in the tooth image based on a pre-trained neural network model, and determine feature information of the target tooth; wherein the feature information further includes coordinates of the target tooth; A determination unit is configured to determine pose information of the target tooth according to the feature information and a tooth model corresponding to the target tooth; wherein the tooth model is a corrected tooth model; and the pose information includes orientation and spatial position information; A detection unit is configured to map the tooth model into the tooth image based on the pose information, and generate a detection result of a correction effect of the target tooth based on the tooth image, including: mapping the tooth model into the tooth image based on the pose information to obtain a mapping image; calculating a pixel difference between the tooth image and the mapping image; and generating a detection result of the correction effect of the target tooth according to the pixel difference; The determination unit is configured to: Determine a coordinate system of the tooth model, and convert the coordinates of the target tooth to the coordinate system; determine the pose information of the target tooth in the coordinate system based on the converted coordinates of the target tooth and the pose information of the tooth model, so as to map the tooth model into the tooth image.

7. An electronic device, comprising: Comprise: A memory; A processor; And A computer program; The computer program is stored in the memory and is configured to be executed by the processor to implement the tooth correction effect detection method of any one of claims 1 to 5.

8. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the tooth correction effect detection method of any one of claims 1 to 5.

Images