Children morning examination oral cavity image communication system

Abstract

The invention relates to the technical field of medical image processing, in particular to a children morning examination oral cavity image communication system. The system comprises: an acquisition module for determining a tooth region by referring to a grayscale image and an oral grayscale image; the standard model construction module is used for analyzing image features, extracting edge and angular point features and constructing a standard model; the angular point analysis module is used for carrying out position matching on the comparison angular points and standard angular points in a standard model and determining the comprehensive offset of all the comparison angular points; screening to obtain a suspected abnormal image; the edge analysis module is used for carrying out gradient direction analysis on the edge and determining an abnormal comparison edge of the suspected abnormal image; and the communication module is used for marking and transmitting the abnormal comparison edges of all the suspected abnormal images. According to the invention, the accuracy of abnormal tooth area image analysis can be improved, and the accuracy of tooth health auxiliary evaluation of individual children is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and in particular to an oral image communication system for children's morning check-up. Background Art

[0002] At present, in order to ensure the dental health of children, morning check-ups are usually arranged to conduct routine medical examinations on the dental condition of children. Medical images are obtained by taking photos of children's teeth and analyzing them, and abnormal problems such as tooth dislocation, tartar and tooth decay can be determined based on the medical images.

[0003] In the related art, abnormal dental images are determined by matching children's dental images with standard templates. In this way, since the dental structures of children of different ages and individuals vary greatly, this will interfere with the medical detection of abnormal dental areas, resulting in low accuracy in the analysis of abnormal dental images and low accuracy in the auxiliary assessment of individual children's dental health. Summary of the invention

[0004] In order to solve the technical problem that the dental structures of children of different ages and individuals are greatly different, which interferes with the medical detection of abnormal dental areas, makes the analysis of abnormal dental images low in accuracy, and the auxiliary assessment of dental health of children is low in accuracy, the present invention provides a children's morning check-up oral image communication system, and the technical solution adopted is as follows: The present invention proposes a children's morning check-up oral image communication system, comprising: An acquisition module, used to acquire a reference grayscale image of the child's historical normal teeth and an oral grayscale image during a morning checkup, and determine a tooth region in the reference grayscale image and the oral grayscale image; A standard model construction module is used to perform image feature analysis on the tooth areas in the reference grayscale image and the oral grayscale image, extract reference edges and reference corners in the reference grayscale image and contrast edges and contrast corners in the oral grayscale image at the same scale, and construct a standard model of each child's tooth based on the reference edge curvature, the position distribution characteristics of the reference corners, and the relationship between the reference corners and the overall morphology of the teeth, wherein the standard model includes the standard corners and standard edges of each tooth; A corner point analysis module is used to match the positions of the comparison corner points with the standard corner points in the standard model, and determine the comprehensive offset of all the comparison corner points; and to screen the suspected abnormal image from the oral grayscale image according to the comprehensive offset; An edge analysis module, used to determine the directional consistency of the contrast edge in each suspected abnormal image according to the gradient direction of the contrast edge in the suspected abnormal image and the matched standard edge; and determine the abnormal contrast edge of the suspected abnormal image according to the directional consistency; The communication module is used to mark and transmit the abnormal contrast edges of all suspected abnormal images.

[0005] Furthermore, the step of determining the tooth region in the reference grayscale image and the oral grayscale image includes: Semantic segmentation is performed on the reference grayscale image and the oral grayscale image respectively to determine the tooth area.

[0006] Further, image feature analysis is performed on the tooth areas in the reference grayscale image and the oral grayscale image respectively, and reference edges and reference corners in the reference grayscale image and contrast edges and contrast corners in the oral grayscale image at the same scale are extracted, including: The reference grayscale image and the oral grayscale image are normalized based on a geometric calibration method so that the tooth regions in the reference grayscale image and the oral grayscale image are aligned to a uniform scale; Performing Canny edge detection on the reference grayscale image to obtain reference edges, the reference edges constitute a reference edge image, and then performing corner point detection to obtain reference corner points; Performing Canny edge detection on the oral grayscale image to obtain contrast edges, the contrast edges constitute a contrast edge image, and performing corner point detection on the contrast edge image to obtain contrast corner points.

[0007] Furthermore, based on the reference edge curvature, the position distribution characteristics of the reference corner points, and the relationship between the reference corner points and the overall shape of the teeth, a standard model of each child's teeth is constructed, including: Determine the curvature of the reference edge of the same child's tooth in all reference grayscale images, the position distribution of the reference corner points on the reference edge, and the distribution law of the reference corner points on the tooth contour as construction information; The construction information is input into a preset tooth image model, and model training is performed on the preset tooth image model to obtain a standard model, wherein the standard model is a standardized image model corresponding to a child's tooth area.

[0008] Furthermore, the position matching of the comparison corner points with the standard corner points in the standard model to determine the comprehensive offset of all the comparison corner points includes: The position of each contrast corner point in the oral grayscale image is mapped to the standard model at the same scale, and the model is matched according to the position of the contrast corner point and the position of the standard corner point, and the contrast corner point with the closest position is matched with the standard corner point as a pair of matching points; The mean of the Euclidean distances of all pairs of matching points is used as the first offset indicator; Calculate the difference in the number of all contrast corner points and the contrast corner points in the matching points, and normalize the maximum and minimum values ​​as the second offset index; The product of the first offset index and the second offset index is normalized to the maximum and minimum values ​​to be used as the comprehensive offset of all the compared corner points.

[0009] Further, the suspected abnormal image is obtained by screening the oral grayscale image according to the comprehensive offset, including: The oral grayscale image to which the comparison corner point having the comprehensive offset greater than the preset offset threshold belongs is taken as a suspected abnormal image.

[0010] Further, according to the gradient direction of the contrast edge in the suspected abnormal image and the matched standard edge, the direction consistency of the contrast edge in each suspected abnormal image is determined, including: When at least two comparison corner points included in a comparison edge match corresponding standard corner points in the standard edge, the comparison edge and the standard edge are regarded as matched edges; Determine the contrast gradient direction of the contrast edge and the standard gradient direction of the standard edge according to the gradient direction of each pixel in the contrast edge and the standard edge; Determine the angle value of the contrast gradient direction of the contrast edge and the standard gradient direction of the matched standard edge as the edge matching angle difference; The opposite number of the edge matching angle difference is normalized to the maximum and minimum values ​​to be used as the direction consistency.

[0011] Further, according to the gradient direction of each pixel in the contrast edge and the standard edge, determining the contrast gradient direction of the contrast edge and the standard gradient direction of the standard edge includes: Determine the gradient direction of each pixel in the contrast edge, and take the sum of the gradient directions of all pixels as the contrast gradient direction of the contrast edge; similarly, take the sum of the gradient directions of all pixels in the standard edge as the standard gradient direction of the standard edge.

[0012] Further, determining the abnormal contrast edge of the suspected abnormal image according to the directional consistency includes: The contrast edge whose direction consistency is less than a preset consistency threshold is regarded as an abnormal contrast edge.

[0013] Furthermore, the abnormal contrast edges of all suspected abnormal images are marked and transmitted, including: Taking a preset neighborhood area of ​​the abnormal contrast edge in the suspected abnormal image as an area to be analyzed; The region to be analyzed is subjected to lossless image compression and transmission.

[0014] The present invention has the following beneficial effects: In the embodiment of the present invention, by obtaining the reference grayscale image of historical normal teeth and the grayscale image of the oral cavity during the morning checkup, it is convenient to perform subsequent standard model construction and historical matching analysis, and provide a data basis for the subsequent image analysis process. The image feature analysis of the tooth area in the reference grayscale image is performed through the standard model construction module to obtain the reference edge and reference corner point, and the standard model of each child's teeth is constructed through the reference edge curvature, the position distribution characteristics of the reference corner point, and the relationship between the reference corner point and the overall shape of the tooth, and the standard corner point and standard edge are determined; the construction of the standard model combines the reference grayscale images of multiple historical normal teeth of the same child, so that the standard model can accurately characterize each child. The tooth features that are adaptive to different children are used to avoid ignoring the impact of different individual tooth differences when analyzing according to a unified tooth template, thereby improving the accuracy of subsequent standard analysis; then, the comprehensive offset is determined by corner point analysis, and the suspected abnormal image is screened out, and the abnormal contrast edge is determined from the suspected abnormal image by edge analysis, that is, the abnormal tooth edge is analyzed using the two dimensions of corner point matching and edge matching, so that the normal pit and fissure area and the abnormal tooth area can be accurately analyzed, and the abnormal contrast edges of all suspected abnormal images are marked and transmitted to improve the transmission efficiency, and the abnormal contrast edges in the suspected abnormal image are marked to improve the accuracy of subsequent abnormal identification. In summary, the embodiment of the present invention constructs a standard model that is adaptive to different children, and combines the analysis of corner points and edges under the standard model to improve the accuracy of abnormal analysis, so that the abnormal tooth image area can be analyzed more accurately, the accuracy of image analysis of abnormal tooth areas is improved, and the accuracy of auxiliary assessment of dental health of children is improved. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0016] Figure 1 A structural diagram of an oral image communication system for morning checkups of children provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation, structure, features and effects of a children's morning check-up oral image communication system proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

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

[0019] The specific scheme of the oral image communication system for morning checkups of children provided by the present invention is described in detail below with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a structural diagram of a children's morning check-up oral image communication system provided by an embodiment of the present invention, including: an acquisition module 101, a standard model construction module 102, a corner point analysis module 103, an edge analysis module 104 and a communication module 105.

[0021] An acquisition module 101 is used to acquire a reference grayscale image of the child's historical normal teeth and an oral grayscale image during a morning checkup, and determine a tooth region in the reference grayscale image and the oral grayscale image; The standard model building module 102 is used to perform image feature analysis on the tooth areas in the reference grayscale image and the oral grayscale image, extract reference edges and reference corners in the reference grayscale image and contrast edges and contrast corners in the oral grayscale image at the same scale, and build a standard model of each child's tooth based on the reference edge curvature, the position distribution characteristics of the reference corners, and the relationship between the reference corners and the overall shape of the teeth. The standard model includes the standard corners and standard edges of each tooth. Corner point analysis module 103 is used to match the positions of the comparison corner points with the standard corner points in the standard model, determine the comprehensive offset of all comparison corner points, and screen the suspected abnormal image from the oral grayscale image according to the comprehensive offset; The edge analysis module 104 is used to determine the direction consistency of the contrast edge in each suspected abnormal image according to the gradient direction of the contrast edge in the suspected abnormal image and the matched standard edge; and determine the abnormal contrast edge of the suspected abnormal image according to the direction consistency; The communication module 105 is used to mark and transmit the abnormal contrast edges of all suspected abnormal images.

[0022] The embodiment of the present invention aims to screen the oral images of children in the morning checkup based on prior analysis, so as to determine abnormal tooth images, so as to improve the accuracy of auxiliary assessment of children's individual dental health. Among them, dental abnormalities mainly include misaligned and lost teeth, dental calculus and tooth decay. They all affect the shape, color and structure of teeth. Therefore, specific abnormality analysis is mainly performed based on tooth color and shape.

[0023] It should be noted that, in the embodiment of the present invention, the acquisition module 101 mainly realizes the data acquisition function and provides a data basis for the analysis of the oral images of children in the morning examination. In the embodiment of the present invention, a reference grayscale image of historical normal teeth is obtained, and the reference grayscale image is used to construct an adaptive tooth template for different children. The oral grayscale image during the morning examination is the oral image obtained by shooting during the morning examination, and the oral image is grayed to obtain the oral grayscale image.

[0024] Since the oral cavity includes the tooth area, the gum area and other corresponding areas, such as the tongue area, in order to accurately analyze the teeth, it is necessary to extract the tooth area. In an embodiment of the present invention, semantic segmentation is performed on the reference grayscale image and the oral grayscale image respectively to determine the tooth area.

[0025] Among them, semantic segmentation is a technology well known to those skilled in the art. The tooth area can be accurately divided by semantic segmentation. Of course, in other embodiments of the present invention, other methods can also be used to determine the tooth area, such as grayscale value segmentation. The tooth area generally appears white or light yellow, which is significantly different from the red color of other areas in grayscale. Therefore, the tooth area can be determined by grayscale division.

[0026] In the embodiment of the present invention, since the tooth shapes of different children vary greatly, it is impossible to use a unified tooth template to analyze all children. It is necessary to set adaptive templates for different children, that is, it is necessary to construct a standard model of each child's teeth.

[0027] It should be noted that the frequency of morning check-ups for children varies in different situations, ranging from once a month to once a year. In order to effectively analyze the overall situation and avoid misidentification, scale normalization is required so that the collected images are on the same scale.

[0028] In an embodiment of the present invention, the reference grayscale image and the oral grayscale image are normalized based on a geometric calibration method; the geometric calibration method is a method well known to relevant technical personnel in the field, and the geometric calibration method is used to normalize the image so that the tooth areas in different images are aligned to a uniform scale, and the tooth information in the tooth areas in different images is analyzed and trained.

[0029] In an embodiment of the present invention, Canny edge detection is performed on the reference grayscale image to obtain reference edges, which constitute a reference edge image, and then corner point detection is performed to obtain reference corner points; Canny edge detection is performed on the oral grayscale image to obtain contrast edges, which constitute a contrast edge image, and corner point detection is performed on the contrast edge image to obtain contrast corner points.

[0030] Edge detection and corner detection can detect and analyze each image, so as to extract edge features and corner features. Since they belong to the same child, the tooth area of ​​the oral grayscale image obtained by the morning examination is similar to the tooth area of ​​the reference grayscale image, and the inconsistent area is the abnormal area.

[0031] Since there are multiple reference grayscale images of the same child, the tooth regions corresponding to each image may be different to a certain extent. Therefore, the embodiment of the present invention integrates the tooth regions of all reference grayscale images of the same child to obtain a standard model of each child's teeth.

[0032] Furthermore, in some embodiments of the present invention, a standard model of each child's tooth is constructed based on the reference edge curvature, the position distribution characteristics of the reference corner points, and the relationship of the reference corner points to the overall shape of the tooth, including: determining the curvature of the reference edge of the same child's tooth in all reference grayscale images, the position distribution of the reference corner points on the reference edge, and the distribution pattern of the reference corner points on the tooth contour as construction information; inputting the construction information into a preset tooth image model, performing model training on the preset tooth image model, and obtaining a standard model, wherein the standard model is a standardized image model corresponding to the child's tooth area.

[0033] Among them, the construction information is the position information of the tooth edge, corner point, etc. In the embodiment of the present invention, the construction information mainly includes the curvature of the reference edge in the reference grayscale image, the position distribution of the reference corner point on the reference edge, and the distribution law of the reference corner point on the tooth contour. It should be noted that this part of the construction information can be used as big data information, set as training data, and input into the big data model to be trained to perform model training to obtain a standard model. Among them, the big data model can be specifically, for example, a machine learning model, which performs machine learning through the tooth area features under normal conditions, that is, the reference edge and the reference corner point, thereby realizing the training process.

[0034] In the embodiment of the present invention, a standard model is obtained through training, and then a standard difference analysis needs to be performed on each oral grayscale image.

[0035] Furthermore, in some embodiments of the present invention, the positions of the comparison corner points are matched with the standard corner points in the standard model to determine the comprehensive offset of all the comparison corner points, including: mapping the position of each comparison corner point in the oral grayscale image to the standard model at the same scale, and performing model matching based on the positions of the comparison corner points and the standard corner points, matching the comparison corner points and the standard corner points that are closest in position as a pair of matching points; taking the mean of the Euclidean distances of all pairs of matching points as the first offset index; calculating the difference in the number of comparison corner points among all comparison corner points and the matching points, and normalizing the maximum and minimum values ​​as the second offset index; taking the product of the first offset index and the second offset index, and normalizing the maximum and minimum values ​​as the comprehensive offset of all comparison corner points.

[0036] It is understandable that abnormal phenomena such as misaligned and fallen teeth, tartar and tooth decay will cause changes in the morphology of teeth, resulting in changes in the position, number and edge curvature of the corner points in the tooth area. For example, the tartar area will cause the teeth to be covered with tartar, and the covered area will cover the normal tooth edges, resulting in a large number of edges and corner points in the image. The position, number, curvature and length of the corner points at the corresponding positions of these edge corner points in the standard tooth model will all change. Therefore, by comparing the edge curvature, length and position and number of corner points in the tooth area with the standard model, if the changing characteristics of the edge curvature or the length distribution deviate from the standard model, it can be determined whether the area is a potential abnormal area.

[0037] Among them, in the overall matching process, this solution performs anomaly analysis through two matching analysis processes, corner point matching and edge matching. First, the comprehensive offset is determined by corner point matching. The comprehensive offset in the embodiment of the present invention is the offset index corresponding to the corner point matching. The comprehensive offset is analyzed by the distance of the matched corner points and the proportion of the number of matched corner points.

[0038] In an embodiment of the present invention, the first offset index is index information corresponding to the corner point distance. The larger the Euclidean distance of the matching point, the farther the matched comparison corner point position is from the standard corner point position, that is, the more likely it is that the corner point offset is caused by some abnormal reasons. At this time, the larger the value of the first offset index is.

[0039] In the embodiment of the present invention, the difference in the number of comparison corner points between all comparison corner points and the comparison corner points in the matching points indicates the number of comparison corner points that have not been matched. The larger the value is, the larger the number of unmatched comparison corner points is, that is, the more likely it is that an abnormal phenomenon will occur overall, and the larger the value of the second offset index is.

[0040] Therefore, the first offset index and the second offset index are combined to calculate the comprehensive offset. Since the larger the values ​​of the first offset index and the second offset index are, the more abnormal they can be, the product value of the first offset index and the second offset index is directly normalized to the maximum and minimum values ​​as the comprehensive offset of all comparison corner points.

[0041] Of course, in some other embodiments of the present invention, the sum of the first offset index and the second offset index may be directly calculated and normalized to be the comprehensive offset.

[0042] It is understandable that the larger the value of the comprehensive offset, the worse the matching effect between the contrast corner points in the oral grayscale image and the standard model, that is, the more likely it is to produce abnormal phenomena, such as tooth dislocation, tartar, and tooth decay. Therefore, the comprehensive offset can be combined for further screening.

[0043] Furthermore, in some embodiments of the present invention, suspected abnormal images are screened from oral grayscale images according to the comprehensive offset, including: taking the oral grayscale images to which the comparison corner points having a comprehensive offset greater than a preset offset threshold belong as suspected abnormal images.

[0044] The preset offset threshold is a threshold value of the comprehensive offset. In the embodiment of the present invention, the preset offset threshold can be set to 0.5. That is to say, when the comprehensive offset is greater than 0.5, the corresponding oral grayscale image is screened as a suspected abnormal image.

[0045] The suspected abnormal image in the embodiment of the present invention means that there are corresponding abnormal effects in the image, but the accuracy of the abnormal analysis effect obtained based only on corner point detection is not ideal. Therefore, additional edge analysis is required to effectively deal with complex tooth changes.

[0046] Among them, for edge analysis, the gradient direction is mainly analyzed, because the gums themselves will change with the use of teeth, especially in children, whose gum edges and tooth edges in the mouth grow rapidly. The accuracy of direct analysis based on the position deviation of the edge is low and the reliability is insufficient. In addition, under normal growth conditions of the tooth area in the mouth, the overall edge morphology changes little, and due to phenomena such as tooth decay and tartar, the boundary edge between the teeth and gums will have a greater effect, resulting in obvious deformation of the edge, that is, each edge has a similar gradient direction under normal conditions, and will produce a larger gradient direction change under abnormal conditions. Therefore, in the embodiment of the present invention, the tooth edge is analyzed for abnormality through the gradient direction.

[0047] Furthermore, in some embodiments of the present invention, the directional consistency of the contrast edges in each suspected abnormal image is determined based on the gradient directions of the contrast edges in the suspected abnormal image and the matched standard edges, including: when at least two contrast corner points contained in a contrast edge match the corresponding standard corner points in the standard edge, the contrast edge and the standard edge are regarded as matched edges; based on the gradient directions of the contrast edge and each pixel point in the standard edge, the contrast gradient direction of the contrast edge and the standard gradient direction of the standard edge are determined; the angle value of the angle between the contrast gradient direction of the contrast edge and the standard gradient direction of the matched standard edge is determined as the edge matching angle difference; and the inverse of the edge matching angle difference is normalized to the maximum and minimum values ​​as the directional consistency.

[0048] Among them, edge matching can be analyzed in combination with the characteristics of corner point matching, that is, when at least two contrast corner points contained in a contrast edge match the corresponding standard corner points in the standard edge, the contrast edge and the standard edge are regarded as matching edges. Since dental plaque, tooth decay, etc. can cause edge changes, direct matching has a poor effect. Corner point matching can accurately perform matching analysis, and its matching accuracy is higher.

[0049] Then, a gradient direction analysis is performed. It can be understood that under normal growth conditions, the gradient direction changes slightly, while under abnormal conditions, the gradient direction changes significantly. The standard gradient direction represents the overall gradient direction of the standard edge, while the contrast gradient direction represents the overall gradient direction of the contrast edge. Therefore, in the embodiment of the present invention, it is necessary to perform a difference analysis on the matching standard gradient direction and contrast gradient direction.

[0050] Furthermore, in some embodiments of the present invention, the contrast gradient direction of the contrast edge and the standard gradient direction of the standard edge are determined according to the gradient direction of each pixel in the contrast edge and the standard edge, including: determining the gradient direction of each pixel in the contrast edge, and taking the sum of the gradient directions of all the pixels as the contrast gradient direction of the contrast edge; similarly, taking the sum of the gradient directions of all the pixels in the standard edge as the standard gradient direction of the standard edge.

[0051] Since the number of pixels in the contrast edge and the standard edge may be greatly different, the effect of directly matching one by one based on the pixels is poor. Therefore, the present invention integrates the sum vector of the gradient directions of all pixels in the standard edge (the vector length of each pixel is 1 by default), and uses the direction of the corresponding sum vector as the standard gradient direction, and integrates the sum vector of the gradient directions of all pixels in the contrast edge, and uses the direction of the corresponding sum vector as the contrast gradient direction.

[0052] In an embodiment of the present invention, the difference analysis of two directions is specifically performed through the angle value of the two directions, wherein the angle is specifically an angle less than or equal to 180 degrees. That is to say, the larger the angle between the two directions, the larger the difference between the two directions. Therefore, in an embodiment of the present invention, the edge matching angle difference is directly determined, and the opposite number of the edge matching angle difference is normalized to the maximum and minimum values ​​as the direction consistency.

[0053] Among them, directional consistency is a characteristic indicator that represents directional consistency. That is, the larger the value of directional consistency is, the more consistent the overall gradient direction between the matching standard edge and the comparison edge is.

[0054] The smaller the value of directional consistency is, the greater the difference in overall gradient direction between the comparison edge and the matching standard edge is, that is, the comparison edge has a directional change, which may be caused by holes caused by tooth decay or edge changes caused by dental tartar. Therefore, the smaller the value of directional consistency is, the greater the abnormal feature is.

[0055] In the embodiment of the present invention, a contrast edge whose direction consistency is less than a preset consistency threshold is regarded as an abnormal contrast edge.

[0056] The preset consistency threshold is a threshold value of directional consistency. The preset consistency threshold in the embodiment of the present invention may be specifically, for example, 0.5, that is, a contrast edge with a directional consistency less than 0.5 is regarded as an abnormal contrast edge.

[0057] The abnormal contrast edge indicates that the suspected abnormal image has poor corner point matching effect. The worse the contrast edge matching effect is, the more likely it is that the suspected abnormal image during the morning inspection needs further processing, such as subsequent manual analysis, or classified storage.

[0058] In an embodiment of the present invention, abnormal contrast edges of all suspected abnormal images are marked and transmitted, including: taking a preset neighborhood area of ​​the abnormal contrast edge in the suspected abnormal image as an area to be analyzed; and performing lossless image compression transmission on the area to be analyzed.

[0059] Among them, the preset neighborhood area can specifically perform morphological expansion on the abnormal contrast edge, and the expansion scale can be 10, that is, the area within 10 pixels on both sides of the abnormal contrast edge is used as the area to be analyzed, and the area to be analyzed is subjected to lossless image compression transmission.

[0060] In the embodiment of the present invention, the image area other than the area to be analyzed may not be transmitted, or may be transmitted with lossy compression to improve the transmission efficiency. If there is a subsequent manual analysis step, it is convenient to focus on analyzing the abnormal area to be analyzed, improve the subsequent processing efficiency, and improve the overall accuracy of the auxiliary assessment of children's individual dental health.

[0061] In the embodiment of the present invention, by obtaining the reference grayscale image of historical normal teeth and the grayscale image of the oral cavity during the morning checkup, it is convenient to perform subsequent standard model construction and historical matching analysis, and provide a data basis for the subsequent image analysis process. The image feature analysis of the tooth area in the reference grayscale image is performed through the standard model construction module to obtain the reference edge and reference corner point, and the standard model of each child's teeth is constructed through the reference edge curvature, the position distribution characteristics of the reference corner point, and the relationship between the reference corner point and the overall shape of the tooth, and the standard corner point and standard edge are determined; the construction of the standard model combines the reference grayscale images of multiple historical normal teeth of the same child, so that the standard model can accurately characterize each child. The tooth features that are adaptive to different children are used to avoid ignoring the impact of different individual tooth differences when analyzing according to a unified tooth template, thereby improving the accuracy of subsequent standard analysis; then, the comprehensive offset is determined by corner point analysis, and the suspected abnormal image is screened out, and the abnormal contrast edge is determined from the suspected abnormal image by edge analysis, that is, the abnormal tooth edge is analyzed using the two dimensions of corner point matching and edge matching, so that the normal pit and fissure area and the abnormal tooth area can be accurately analyzed, and the abnormal contrast edges of all suspected abnormal images are marked and transmitted to improve the transmission efficiency, and the abnormal contrast edges in the suspected abnormal image are marked to improve the accuracy of subsequent abnormal identification. In summary, the embodiment of the present invention constructs a standard model that is adaptive to different children, and combines the analysis of corner points and edges under the standard model to improve the accuracy of abnormal analysis, so that the abnormal tooth image area can be analyzed more accurately, the accuracy of image analysis of abnormal tooth areas is improved, and the accuracy of auxiliary assessment of dental health of children is improved.

[0062] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying 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.

[0063] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A children's morning check-up oral image communication system, characterized in that: The system includes: An acquisition module, used to acquire a reference grayscale image of the child's historical normal teeth and an oral grayscale image during a morning checkup, and determine a tooth region in the reference grayscale image and the oral grayscale image; A standard model construction module is used to perform image feature analysis on the tooth areas in the reference grayscale image and the oral grayscale image, extract reference edges and reference corners in the reference grayscale image and contrast edges and contrast corners in the oral grayscale image at the same scale, and construct a standard model of each child's tooth based on the reference edge curvature, the position distribution characteristics of the reference corners, and the relationship between the reference corners and the overall morphology of the teeth, wherein the standard model includes the standard corners and standard edges of each tooth; A corner point analysis module is used to match the positions of the comparison corner points with the standard corner points in the standard model, and determine the comprehensive offset of all the comparison corner points; and to screen the suspected abnormal image from the oral grayscale image according to the comprehensive offset; An edge analysis module, used to determine the directional consistency of the contrast edge in each suspected abnormal image according to the gradient direction of the contrast edge in the suspected abnormal image and the matched standard edge; and determine the abnormal contrast edge of the suspected abnormal image according to the directional consistency; The communication module is used to mark and transmit the abnormal contrast edges of all suspected abnormal images.

2. A children's morning check-up oral image communication system as claimed in claim 1, characterized in that: The step of determining the tooth region in the reference grayscale image and the oral grayscale image comprises: Semantic segmentation is performed on the reference grayscale image and the oral grayscale image respectively to determine the tooth area.

3. The oral image communication system for children's morning checkup according to claim 1, characterized in that: Performing image feature analysis on the tooth regions in the reference grayscale image and the oral grayscale image respectively, extracting reference edges and reference corners in the reference grayscale image and contrast edges and contrast corners in the oral grayscale image at the same scale, including: The reference grayscale image and the oral grayscale image are normalized based on a geometric calibration method so that the tooth regions in the reference grayscale image and the oral grayscale image are aligned to a uniform scale; Performing Canny edge detection on the reference grayscale image to obtain reference edges, the reference edges constitute a reference edge image, and then performing corner point detection to obtain reference corner points; Performing Canny edge detection on the oral grayscale image to obtain contrast edges, the contrast edges constitute a contrast edge image, and performing corner point detection on the contrast edge image to obtain contrast corner points.

4. The oral image communication system for children's morning checkup according to claim 1, characterized in that: Based on the reference edge curvature, the position distribution characteristics of the reference corner points, and the relationship between the reference corner points and the overall shape of the teeth, a standard model of each child's teeth is constructed, including: Determine the curvature of the reference edge of the same child's tooth in all reference grayscale images, the position distribution of the reference corner points on the reference edge, and the distribution law of the reference corner points on the tooth contour as construction information; The construction information is input into a preset tooth image model, and model training is performed on the preset tooth image model to obtain a standard model, wherein the standard model is a standardized image model corresponding to a child's tooth area.

5. The oral image communication system for children's morning checkup according to claim 1, characterized in that: The step of matching the positions of the comparison corner points with the standard corner points in the standard model to determine the comprehensive offsets of all the comparison corner points includes: The position of each contrast corner point in the oral grayscale image is mapped to the standard model at the same scale, and the model is matched according to the position of the contrast corner point and the position of the standard corner point, and the contrast corner point with the closest position is matched with the standard corner point as a pair of matching points; The mean of the Euclidean distances of all pairs of matching points is used as the first offset indicator; Calculate the difference in the number of all contrast corner points and the contrast corner points in the matching points, and normalize the maximum and minimum values ​​as the second offset index; The product of the first offset index and the second offset index is normalized to the maximum and minimum values ​​to be used as the comprehensive offset of all the compared corner points.

6. The oral image communication system for children's morning checkup according to claim 1, characterized in that: The suspected abnormal image is obtained by screening the oral grayscale image according to the comprehensive offset, including: The oral grayscale image to which the comparison corner point having the comprehensive offset greater than the preset offset threshold belongs is taken as a suspected abnormal image.

7. A children's morning checkup oral image communication system as claimed in claim 5, characterized in that: According to the gradient direction of the contrast edge in the suspected abnormal image and the matched standard edge, the direction consistency of the contrast edge in each suspected abnormal image is determined, including: When at least two comparison corner points included in a comparison edge match corresponding standard corner points in the standard edge, the comparison edge and the standard edge are regarded as matched edges; Determine the contrast gradient direction of the contrast edge and the standard gradient direction of the standard edge according to the gradient direction of each pixel in the contrast edge and the standard edge; Determine the angle value of the contrast gradient direction of the contrast edge and the standard gradient direction of the matched standard edge as the edge matching angle difference; The opposite number of the edge matching angle difference is normalized to the maximum and minimum values ​​to be used as the direction consistency.

8. The oral image communication system for children's morning checkup as claimed in claim 7, characterized in that: According to the gradient direction of each pixel in the contrast edge and the standard edge, the contrast gradient direction of the contrast edge and the standard gradient direction of the standard edge are determined, including: Determine the gradient direction of each pixel in the contrast edge, and take the sum of the gradient directions of all pixels as the contrast gradient direction of the contrast edge; similarly, take the sum of the gradient directions of all pixels in the standard edge as the standard gradient direction of the standard edge.

9. The oral image communication system for children's morning checkup according to claim 1, characterized in that: Determining the abnormal contrast edge of the suspected abnormal image according to the directional consistency includes: The contrast edge whose direction consistency is less than a preset consistency threshold is regarded as an abnormal contrast edge.

10. The oral image communication system for children's morning checkup according to claim 1, characterized in that: The abnormal contrast edges of all suspected abnormal images are marked and transmitted, including: Taking a preset neighborhood area of ​​the abnormal contrast edge in the suspected abnormal image as an area to be analyzed; The region to be analyzed is subjected to lossless image compression and transmission.

Images