Traditional Chinese medicine three-dimensional teaching display system

Abstract

The invention discloses a traditional Chinese medicine three-dimensional teaching display system, and belongs to the technical field of traditional Chinese medicine teaching. Comprising a three-dimensional model establishing unit used for establishing a traditional Chinese medicine three-dimensional model, a cutting presetting unit used for generating a candidate normal set, a data obtaining unit used for obtaining image data of a section of the traditional Chinese medicine three-dimensional model, and a section analysis unit used for generating a section display value score. The optimal section analysis unit is used for generating an optimal section of the traditional Chinese medicine three-dimensional model; the display unit is used for performing section display on the traditional Chinese medicine three-dimensional model according to the optimal section of the traditional Chinese medicine three-dimensional model; the three-dimensional model building unit is used for building the medicinal material model, the candidate cutting scheme is generated in combination with user interaction, the section value is intelligently evaluated, finally, the optimal teaching display section is automatically selected, the operation complexity is reduced, the operation accuracy is improved, the teaching intuition is improved, and therefore the quality of teaching display of traditional Chinese medicinal materials is improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of traditional Chinese medicine teaching, and particularly relates to a three-dimensional teaching display system for traditional Chinese medicine medicinal materials. BACKGROUND

[0002] Traditional Chinese medicine is a treasure of the Chinese nation, and its inheritance and teaching methods need to be deeply integrated with modern technology. The morphology of medicinal materials, especially its internal structural characteristics, is an important basis for identifying the authenticity of medicinal materials and understanding the efficacy. Traditional teaching relies mainly on two-dimensional pictures, textual descriptions or physical specimens, and it is difficult to intuitively and stereoscopically display the three-dimensional morphology and internal structure of medicinal materials.

[0003] At present, the existing three-dimensional model display technology has been applied in some fields. For example, some systems allow users to observe the overall three-dimensional model by manually rotating and zooming, or to view the internal model by presetting a cutting plane. These existing technologies have the following main problems: first, the cutting method is usually limited to fixed coordinate axis directions, lacking flexibility and pertinence; second, in the interactive cutting process, the existing systems cannot intelligently identify user intentions, and require users to make complex parameter adjustments; most importantly, the existing technology lacks a scientific evaluation mechanism for the value of cross-section display, resulting in the inability to automatically select the cross-section that best reflects the key characteristics of medicinal materials for display.

[0004] In the context of traditional Chinese medicine teaching, the specific cross-section of medicinal materials often contains important identification characteristics, such as vascular bundle arrangement and secretory tissue distribution. The existing technology cannot automatically select the cross-section with the most teaching value according to the characteristics of medicinal materials, and teachers and students need to repeatedly try different cutting angles, which not only wastes time but also makes it difficult to ensure teaching effectiveness. SUMMARY

[0005] In view of the deficiencies of the prior art, the present application provides a three-dimensional teaching display system for traditional Chinese medicine medicinal materials, which solves the above problems.

[0006] To achieve the above purpose, the present application is implemented by the following technical solutions: a three-dimensional teaching display system for traditional Chinese medicine medicinal materials, specifically comprising: a three-dimensional model establishment unit for establishing a three-dimensional model of traditional Chinese medicine medicinal materials; a cutting presetting unit for obtaining a stroke point sequence of a cutting intention drawn by a user on the surface of the model, and generating a candidate normal set; a data acquisition unit for cutting the three-dimensional model of traditional Chinese medicine medicinal materials according to the candidate normal set, and acquiring image data of the cross-section of the three-dimensional model of traditional Chinese medicine medicinal materials; wherein the image data includes a cross-section grayscale image, a cross-section contour perimeter and a cross-section contour area; a cross-section analysis unit for establishing a cross-section display value evaluation model according to the image data of the cross-section, and generating a cross-section display value score; The optimal cross-section analysis unit is used to generate the optimal cross-section of the three-dimensional model of Chinese medicine materials based on the cross-section display value score of all cross-sections. The display unit is used to display the cross-section of the three-dimensional model of Chinese medicinal materials based on the optimal cross-section of the model.

[0007] Based on the above technical solutions, the present invention also provides the following optional technical solutions: Further technical solution: The cutting preset unit specifically includes: The stroke spatial direction generation module is used to generate the average direction vector of the entire stroke based on the sequence of stroke points intended for cutting. The main direction analysis module is used to generate a normalized main direction unit vector of the stroke based on the average direction vector of the stroke as a whole. The candidate normal set generation module is used to generate a candidate normal set based on the normalized unit vector of the stroke principal direction.

[0008] Further technical solution: The method for generating the average direction vector of the entire stroke specifically includes: Through the formula:

[0009] Generate the average direction vector of the entire stroke ; In the formula, This represents the three-dimensional coordinates of the (i+1)th stroke point. This represents the three-dimensional coordinates of the i-th stroke point, and n represents the number of points contained in the stroke point sequence of the cutting intention. Let be the Euclidean norm of the vector.

[0010] Further technical solution: The method for generating the normalized stroke principal direction unit vector specifically includes: Through the formula:

[0011] Generate normalized unit vectors of the principal directions of the strokes. ; In the formula, It represents the average direction vector of the entire stroke. Let be the Euclidean norm of the vector.

[0012] Further technical solution: The specific method for generating the candidate normal set includes: Through the formula:

[0013] Generate candidate normal set ; In the formula, represents the normalized stroke main direction unit vector, represents the global reference direction unit vector, represents the vector perpendicular to the stroke main direction and the global reference direction, is the cross product operator of the vector, represents the opposite direction of represents the opposite direction of represents the global reference direction unit vector opposite direction.

[0014] Further technical solutions: the cross-section analysis unit specifically comprises: Texture analysis module, for generating cross-section texture information entropy value according to cross-section gray image; Geometric analysis module, for generating cross-section geometric complexity characteristic value according to cross-section contour perimeter and cross-section contour area; Comprehensive analysis module, for establishing cross-section display value evaluation model according to cross-section texture information entropy value and cross-section geometric complexity characteristic value, and generating cross-section display value score.

[0015] Further technical solutions: the generation mode of the cross-section texture information entropy value specifically comprises: Through the formula:

[0016] Generate cross-section texture information entropy value ; In the formula, L represents the total number of gray levels of the gray image, represents the probability of gray level j appearing in the cross-section image; The generation mode of the probability of gray level j appearing in the cross-section image is specifically: Through the formula:

[0017] Generate the probability of gray level j appearing in the cross-section image ; In the formula, represents the number of pixels with gray value j in the gray image, represents the total number of pixels of the gray image.

[0018] Further technical solutions: the generation mode of the cross-section geometric complexity characteristic value specifically comprises: Through the formula:

[0019] Generating cross-section geometry complexity characteristic value ; In the formula, C represents the cross-section contour perimeter, A represents the cross-section contour area, and k is a constant.

[0020] Further technical solutions: The expression of the cross-section display value evaluation model is specifically:

[0021] In the expression, represents the cross-section display value score, represents the cross-section texture information entropy value, represents the cross-section geometry complexity characteristic value, represents the cross-section color distribution characteristic value, , , are weight coefficients, and ; Among them, the generation method of the cross-section color distribution characteristic value specifically includes: Through the formula:

[0022] Generating cross-section color distribution characteristic value ; In the formula, represents the standard deviation of all pixel values of the cross-section image red R channel, represents the standard deviation of all pixel values of the cross-section image green G channel, represents the standard deviation of all pixel values of the cross-section image blue B channel, represents the arithmetic mean of all pixel values of the cross-section image red R channel, represents the arithmetic mean of all pixel values of the cross-section image green G channel, represents the arithmetic mean of all pixel values of the cross-section image blue B channel, and g is a constant.

[0023] Further technical solutions: The generation method of the optimal cross-section specifically includes: Through the formula:

[0024] Generating optimal cross-section ; In the formula, represents the cross-section display value score of the cross-section , represents the fth cross-section.

[0025] The application provides a three-dimensional teaching display system for traditional Chinese medicine medicinal materials, which has the following beneficial effects compared with the prior art: The application constructs a medicinal material model through a three-dimensional model establishing unit, generates a candidate cutting scheme in combination with user interaction, intelligently evaluates the value of a section based on texture, geometry and color characteristics, and finally automatically selects an optimal teaching display section, thereby reducing operation complexity, improving operation accuracy and teaching intuitiveness, and improving the quality of traditional Chinese medicine medicinal material teaching display. BRIEF DESCRIPTION OF DRAWINGS

[0026] Figure 1 A structure diagram of a three-dimensional teaching display system for traditional Chinese medicine medicinal materials is provided.

[0027] Figure 2 A flowchart of a three-dimensional teaching display method for traditional Chinese medicine medicinal materials is provided. DETAILED DESCRIPTION

[0028] In order to make the objectives, technical solutions and advantages of the application clearer, further detailed descriptions are made to the application in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the application and do not limit the application.

[0029] The specific implementation of the application is described in detail in combination with specific examples.

[0030] Please refer to Figure 1 A three-dimensional teaching display system for traditional Chinese medicine medicinal materials is provided for an embodiment of the application, which specifically comprises: A three-dimensional model establishing unit 10 is configured to establish a three-dimensional model of traditional Chinese medicine medicinal materials; A cutting presetting unit 20 is configured to obtain a stroke point sequence of a cutting intention drawn on the surface of the model by a user, and generate a candidate normal set; A data acquisition unit 30 is configured to cut the three-dimensional model of traditional Chinese medicine medicinal materials according to the candidate normal set, and acquire image data of a section of the three-dimensional model of traditional Chinese medicine medicinal materials; wherein the image data comprises a section grayscale image, a section contour perimeter and a section contour area; A section analysis unit 40 is configured to establish a section display value evaluation model according to the image data of the section, and generate a section display value score; An optimal section analysis unit 50 is configured to generate an optimal section of the three-dimensional model of traditional Chinese medicine medicinal materials according to the section display value scores of all sections; A display unit 60 is configured to perform section display on the three-dimensional model of traditional Chinese medicine medicinal materials according to the optimal section of the three-dimensional model of traditional Chinese medicine medicinal materials; The three-dimensional model establishing unit 10 refers to constructing a digital model of medicinal materials through three-dimensional scanning or modeling software. The digital model contains the internal structure of traditional Chinese medicine medicinal materials and provides basic three-dimensional data for subsequent cutting analysis. The cutting presetting unit 20 refers to generating candidate normals by capturing the stroke trajectory drawn by the user on the model surface. A touch pen input device can be used to collect stroke point sequences and convert the user's intuitive intention into mathematical vectors. The data acquisition unit 30 refers to cutting the model along the candidate normal direction and extracting cross-sectional image data. A ray casting algorithm can be used to realize three-dimensional model cutting and obtain grayscale images and contour parameters. The cross-section analysis unit 40 refers to evaluating the teaching value of the cross-section by calculating the texture entropy value and the geometric complexity. Image processing algorithms can be used to extract grayscale distribution features. The optimal cross-section analysis unit 50 refers to automatically selecting the highest score cross-section according to the scoring. A sorting algorithm can be used to traverse all candidate cross-section scores. The display unit 60 refers to visualizing and rendering the selected cross-section. OpenGL or WebGL technology can be used to realize the synchronous display of three-dimensional models and cross-sections.

[0031] Specifically, after the three-dimensional model establishing unit generates a three-dimensional grid model of medicinal materials, the user draws a cutting intention trajectory on the model surface using a touch pen. The cutting presetting unit converts the stroke point sequence into an average direction vector and generates a candidate normal set containing the main direction and its orthogonal direction. The data acquisition unit cuts the model along each candidate normal, extracts the cross-sectional grayscale image, and calculates the contour perimeter and area. The cross-section analysis unit calculates the texture information entropy and geometric complexity characteristic value, and obtains the display value score by weighted summation. The optimal cross-section analysis unit selects the cross-section corresponding to the highest score, which is highlighted and dynamically displayed by the display unit.

[0032] Compared with the prior art, the traditional method requires the user to manually adjust the rotation angle to find the cross-section. However, the present scheme automatically generates candidate directions by analyzing the stroke trajectory, reducing the number of operation steps. The prior art uses fixed XYZ axis cutting, which cannot adapt to different medicinal material structure characteristics. However, the present scheme generates personalized candidate directions according to user intentions, improving direction adaptability. Conventional systems rely on manual experience to judge the value of the cross-section, while the present scheme automatically optimizes through a quantitative evaluation model, avoiding subjective judgment errors. Through the above technical solutions, the present application realizes the quick conversion of user intentions into mathematical vectors, reduces the operation complexity, improves the accuracy of cross-section selection through multi-dimensional feature fusion evaluation, and shortens the teaching preparation time through an automated process. For example, when explaining the horizontal cross-section of angelica, the user can draw a horizontal stroke to automatically generate a high-quality cross-section containing the distribution characteristics of the vessel bundle, without repeatedly adjusting the cutting angle.

[0033] Preferably, the application further proposes that the cutting preset unit 20 specifically comprises: A stroke space direction generation module is configured to generate an average direction vector of the whole stroke according to the stroke point sequence of the cutting intention. A main direction analysis module is configured to generate a normalized stroke main direction unit vector according to the average direction vector of the whole stroke. A candidate normal set generation module is configured to generate a candidate normal set according to the normalized stroke main direction unit vector. The stroke point sequence of the cutting intention refers to a set of point coordinates continuously drawn by the user on the surface of the three-dimensional model, which can be realized by a stylus input or a mouse trajectory capture, and is used to reflect the cutting direction trend expected by the user. The average direction vector refers to a vector calculated by the mean value of the direction vectors between adjacent stroke points, which can be realized by normalizing the difference between consecutive points and then averaging, and is used to eliminate local jitter interference and extract the overall direction feature of the stroke. The normalized stroke main direction unit vector refers to a unit vector obtained by standardizing the length of the average direction vector, which can be realized by dividing the vector by its module, and is used to eliminate the influence of stroke length difference on direction judgment. The candidate normal set refers to a normal direction set composed of the main direction and its derived directions, which can be generated by vector cross product and reverse direction expansion, and is used to provide cutting surface direction options that conform to the spatial geometric rules.

[0034] Specifically, the user expresses the cutting intention by drawing a stroke trajectory on the model surface, and the system records the stroke point sequence and calculates the direction vectors between adjacent points. By accumulating and averaging these direction vectors, the average direction vector reflecting the overall trend drawn by the user is obtained. The vector is normalized to obtain the main direction unit vector with clear direction semantics. Combined with the main direction and the preset global reference direction, the vector cross product operation is used to generate orthogonal directions, and the positive and negative directions are expanded to form a set containing six candidate normals. In this way, the user does not need to manually adjust complex parameters, but only needs to draw naturally to trigger the system to generate cutting direction options that conform to the spatial geometric constraints. Compared with the prior art, the traditional method relies on fixed coordinate axis direction or requires the user to manually input normal parameters in the three-dimensional coordinate system, which has the problems of complicated operation and unreasonable direction selection. The present scheme automatically deduces the cutting direction by analyzing the user's drawing trajectory, which not only retains the intuitive operation, but also ensures that the candidate direction conforms to the orthogonal relationship in three-dimensional space through mathematical constraints, avoiding the confusion caused by completely free definition.

[0035] By the technical solution, the application effectively solves the problem that the traditional cutting direction selection depends on fixed axial or complex parameter adjustment, so that the generation process of the cutting direction conforms to the human operation intuition, and meanwhile, a candidate direction set conforming to the spatial geometric rule is provided, the number of repeated adjustments of the user is reduced, and the interactive efficiency and direction rationality of the teaching display system are improved.

[0036] Preferably, the application further provides a generation method of the average direction vector of the whole stroke, which specifically comprises: The average direction vector of the whole stroke is generated by the following formula:

[0037] The average direction vector of the whole stroke is generated by the following formula: In the formula, xi+1 represents the three-dimensional coordinates of the i+1th stroke point, xi represents the three-dimensional coordinates of the ith stroke point, n represents the number of points contained in the stroke point sequence of the cutting intention, and ||·|| represents the Euclidean norm of the vector. The Euclidean norm of the vector is a calculation method of the geometric length of the vector in the three-dimensional space, and can be specifically implemented by square sum and square root operation, and is used to convert the adjacent point vector into a unit direction to eliminate the influence of the drawing speed on the direction calculation. The stroke point sequence refers to a set of spatial coordinate points continuously drawn by the user on the surface of the three-dimensional model, and can be specifically implemented by a touch pen trajectory capture or gesture recognition technology, and is used to record the input path of the cutting intention of the user. The average direction vector is an arithmetic mean of unit vectors between adjacent stroke points, and can be specifically implemented by vector superposition and normalization calculation, and is used to eliminate the direction deviation caused by hand-drawing shaking. The Euclidean norm of the vector is a calculation method of the geometric length of the vector in the three-dimensional space, and can be specifically implemented by square sum and square root operation, and is used to convert the adjacent point vector into a unit direction to eliminate the influence of the drawing speed on the direction calculation. Specifically, the scheme calculates the local direction vector through the coordinate difference value of the adjacent stroke points, and performs unitization processing to eliminate the stroke length difference. The unit vectors of all adjacent points are arithmetically averaged to obtain the overall direction trend, wherein each local direction vector is given the same weight to avoid the excessive influence of a specific section on the overall direction. The Euclidean norm ensures that the direction vector calculation conforms to the geometric characteristics of the three-dimensional space, so that the finally generated average direction vector

[0038] can accurately reflect the cutting intention of the user in the three-dimensional space. The calculation process converts the discrete stroke input into continuous spatial direction parameters, providing a mathematical basis for subsequent cutting surface generation.

[0039] ​​​​Compared with the prior art, the traditional method usually directly uses the direction of the line connecting the starting point and the ending point of a stroke as the cutting direction, and cannot effectively process curved strokes or inputs with drawing jitter. The scheme can accurately capture the actual spatial trend drawn by the user, for example, when the user draws a wavy cutting line, the overall cutting direction can still be extracted. Compared with fixed axial cutting or manual parameter adjustment, the method realizes the automatic analysis of user intention through mathematical modeling, avoiding the operation burden of repeatedly adjusting the cutting direction manually.

[0040] Through the above technical scheme, the present application realizes accurate analysis of the hand-drawn cutting direction of the user, effectively solves the problem of cutting surface deviation caused by stroke direction misjudgment. The scheme can automatically eliminate local jitter interference in hand-drawn input, accurately extract the cutting direction of the user's real intention, so that the cutting display of the three-dimensional model is highly consistent with the user's expectation. In the traditional Chinese medicine teaching scene, the technology ensures the accuracy of the internal structure cutting direction of medicinal materials.

[0041] Preferably, the present application further proposes that the generation mode of the normalized stroke main direction unit vector specifically comprises: Through the formula:

[0042] The normalized stroke main direction unit vector is generated ; In the formula, represents the average direction vector of the whole stroke, is the Euclidean norm of the vector; wherein the normalization refers to a mathematical processing process of converting the vector length into a unit length, which can be realized by the operation of dividing the vector by its module length. This operation can eliminate the influence of different stroke speeds or lengths on direction calculation; The stroke main direction unit vector refers to a reference vector that only retains direction information after standardization processing. It can be realized by the unitization calculation of the direction vector in the three-dimensional coordinate system. The vector serves as a reference direction for the generation of the candidate normal set, providing a spatial reference for the cutting plane direction selection.

[0043] Specifically, the stroke point sequence input by the user is calculated in space direction to form an average direction vector, which is converted into a unit vector through a modulus length normalization operation. The unit vector serves as the main direction reference, and its direction information is completely retained and not affected by the length of the stroke drawing trajectory. For example, when the user draws a cutting stroke in an arbitrary direction on the surface of a three-dimensional model, the system automatically converts the stroke trajectory into a reference direction with a unified length standard, avoiding direction calculation deviations caused by differences in stroke drawing speed. Through mathematical vector normalization processing, the subsequently generated candidate normal set has spatial consistency, ensuring the stability of the tangent direction in different operation scenarios.

[0044] Compared with the prior art, the traditional method relies on fixed axis or manual parameter adjustment to determine the cutting direction, and cannot accurately capture the spatial characteristics of the user's drawing intention. The present scheme converts the user's freely drawn spatial trajectory into a direction reference with mathematical specifications through vector normalization processing, which not only retains the spatial directionality of the user's operation intention, but also avoids the operational redundancy of manually adjusting the direction parameters. For example, in the prior art, the cutting direction needs to be selected by the axis of the coordinate system drop-down menu, while the present scheme automatically generates an accurate normal direction that meets the user's intention through the stroke trajectory. Through the above technical scheme, the present application realizes accurate mathematical mapping of the user's drawing trajectory to the cutting direction, effectively solving the operation error caused by the mismatch between the cutting direction and the user's intention. For example, in the internal duct structure display scene of medicinal materials, the cutting stroke drawn by the user at a specific angle can be accurately converted into the corresponding dissection plane direction, avoiding the operational burden of adjusting the cutting angle multiple times to position the target section in the traditional method. This technical means enables the system to automatically identify the spatial pointing characteristics of the user's intention, significantly improving the accuracy and operational efficiency of the cutting plane generation.

[0045] Preferably, the present application further proposes that the generation method of the candidate normal set specifically comprises: Through the formula:

[0046] generate a candidate normal set ; In the formula, represents the normalized stroke main direction unit vector, represents the global reference direction unit vector, represents a vector perpendicular to both the stroke main direction and the global reference direction, is the cross product operator of the vector, represents the opposite direction of represents the opposite direction of represents the opposite direction of represents the opposite direction of represents a global reference direction unit vector in the opposite direction; wherein the normalized stroke main direction unit vector refers to a vector after unitizing the overall direction of the user-drawn cutting stroke, which can be realized by normalization after average calculation of stroke point sequence coordinate difference, and is used to reflect the main direction of the user's cutting intention on the surface of the three-dimensional model; the global reference direction unit vector refers to a pre-defined fixed direction vector, which can be realized by using an axial unit vector in a three-dimensional coordinate system, and is used to provide a spatial reference direction independent of the user-drawing direction; the cross product operation refers to generating a new direction perpendicular to the original vector through the orthogonal relationship between vectors, which can be realized by vector multiplication calculation, and is used to expand a third dimension direction perpendicular to both the user-drawing direction and the global reference direction; the opposite direction refers to reversing the direction of the original vector, which can be realized by using the sign inversion operation of the vector, such as the opposite of , which is used to cover the possibility of space sectioning symmetrical to the original direction. Specifically, the generation process of the candidate normal set first generates a main direction unit vector based on the average direction of the user-drawing stroke, then generates an orthogonal direction through cross product operation in combination with the global reference direction, and finally combines the positive and negative directions to form six candidate normals. For example, when the user draws a diagonal cutting stroke on the surface of the medicinal material three-dimensional model, the main direction unit vector will point to the oblique direction of the stroke trajectory, the global reference direction can be set to the vertical direction, the cross product operation will generate the horizontal transverse direction, and the positive and negative direction combination will cover the positive and negative sides of the oblique direction, the positive and negative sides of the horizontal transverse direction, and the positive and negative sides of the vertical direction. Therefore, the candidate normal set is symmetrically distributed in multiple dimensions in space, ensuring that cutting planes of different angles can be included in the evaluation range, and avoiding missing the cross section of the internal structure of the medicinal material with high display value due to single direction.

[0047] Compared with the prior art, the traditional method usually generates a sectioning plane only by using a fixed axial direction or a single user input direction, such as sectioning only along the X, Y, Z axes or the user-drawing direction. However, the present scheme generates a candidate set containing orthogonal directions and symmetrical reversals through vector operation and direction expansion of the main direction and the global reference direction, so that the sectioning direction forms a complementary coverage in three-dimensional space, significantly improving the exploration ability of the complex internal structure of the medicinal material. By the technical solution, the application effectively solves the problem that the single candidate normal generation mode cannot comprehensively evaluate the optimal section, and ensures that the section planes of different spatial angles are included in the candidate range through multi-dimensional direction combination, thereby improving the accuracy and reliability of the optimal section selection, and providing sufficient direction basis for subsequent section display value evaluation.

[0048] Preferably, the application further proposes that the section analysis unit specifically comprises: a texture analysis module, configured to generate a section texture information entropy value according to a section gray-scale image; a geometry analysis module, configured to generate a section geometric complexity characteristic value according to a section contour perimeter and a section contour area; a comprehensive analysis module, configured to establish a section display value evaluation model according to the section texture information entropy value and the section geometric complexity characteristic value, and generate a section display value score; The section texture information entropy value refers to an information entropy value calculated by statistically calculating the probability of different gray-scale level pixel distribution in the gray-scale image, and can be specifically implemented by using a negative logarithm weighted sum formula of the gray-scale level occurrence probability, and is used for quantifying the complexity of the section texture. The section geometric complexity characteristic value refers to a characteristic value calculated by a mathematical relationship formula of the perimeter and the area, and can be specifically implemented by using a proportion formula of the square of the perimeter and the area, and is used for describing the shape feature of the section contour. The section display value evaluation model refers to a mathematical model of linearly weighting and fusing the texture and the geometric feature, and can be specifically implemented by using a weighted sum formula of a preset weight coefficient, and is used for comprehensively evaluating the teaching display value of the section.

[0049] Specifically, the texture analysis module first calculates the proportion of the number of each gray-scale level pixel in the total pixels in the gray-scale image, calculates the occurrence probability of each gray-scale level, and then accumulates the product of the probability of each gray-scale level and the corresponding logarithmic value according to the information entropy formula, to obtain the entropy value reflecting the texture complexity. The geometry analysis module measures the perimeter and the area of the section contour, substitutes into the geometric complexity calculation formula, to obtain the characteristic value representing the irregularity degree of the shape. The comprehensive analysis module inputs the entropy value and the complexity characteristic value into the evaluation model, linearly combines through the preset weight coefficient, to generate a comprehensive score. The score mechanism can simultaneously consider the texture details and the shape feature, and screen out the teaching section with rich information and typical structure.

[0050] Compared with the prior art, the traditional method relies on manual experience to select the section plane or only uses a single geometric parameter for evaluation, cannot quantify the texture information, and has single evaluation dimension. The present application solves the problems of strong subjectivity of manual judgment and unclear evaluation standard by fusing the texture entropy value and the geometric complexity characteristic, and constructs a multi-dimensional evaluation system, thereby realizing the objectivity and automation of section screening.

[0051] Through the technical solution, the application can automatically identify high-quality teaching sections with high texture information and typical geometric features, avoiding repeated manual adjustment of the sectioning direction, and improving the efficiency and accuracy of three-dimensional teaching display of Chinese medicinal materials.

[0052] Preferably, the application further provides a generation method of the section texture information entropy value, which specifically includes: Through the formula:

[0053] generate the section texture information entropy value ; In the formula, L represents the total number of gray levels of the gray image, represents the probability of the gray level j in the section image; The generation method of the probability of the gray level j in the section image specifically includes: Through the formula:

[0054] generate the probability of the gray level j in the section image ; In the formula, represents the number of pixels with the gray value j in the gray image, represents the total number of pixels in the gray image; wherein the total number of gray levels L refers to the number range of different gray values in the image, which can be implemented by 256 gray values, and the parameter directly affects the accuracy of texture evaluation; gray level probability refers to the proportion of the number of pixels with each gray value to the total number of pixels, which can be realized by traversing the image pixels and counting, so as to convert the image texture features into statistical distribution data that can be calculated; section texture information entropy value The calculation formula refers to a mathematical model for calculating the information amount based on the probability distribution, which is realized by logarithmic weighted summation, and the model converts the uniformity of the gray distribution into an entropy value index to represent the texture complexity.

[0055] Specifically, the method first traverses all pixels in the cross-sectional gray image, counts the frequency of each gray level, and divides the frequency by the total number of pixels to obtain the probability distribution of each gray level. Then the probability distribution is substituted into the information entropy formula to calculate the cumulative sum of the product of the probability of all gray levels and the logarithmic value. When the gray distribution is more dispersed, the entropy value calculation result is larger, indicating that the cross-sectional texture contains more detailed information; on the contrary, the smaller the entropy value, the more concentrated the gray distribution, reflecting the single texture. This process converts the subjective texture complexity judgment into a comparable numerical index through mathematical modeling, providing an objective basis for the system to automatically select the optimal cross-section.

[0056] Compared with the prior art, the traditional method relies on manual experience observation or fixed direction sectioning, lacks quantitative evaluation mechanism for texture complexity, resulting in low efficiency and strong subjectivity in cross-section selection. The present scheme constructs an objective evaluation model based on probability distribution through statistical analysis and information entropy calculation, which can automatically identify the cross-section with the most significant texture feature, avoiding the manual trial-and-error operation steps.

[0057] Through the above technical scheme, the present application solves the problem of missing cross-sectional texture evaluation standard in the three-dimensional teaching system, and realizes the quantitative analysis of the internal texture characteristics of medicinal materials. The method generates a comparable entropy value index through gray scale statistics and information entropy calculation, which provides a core parameter for the system to automatically select the most valuable cross-section for teaching, and improves the accuracy of medicinal material structure display and teaching efficiency.

[0058] Preferably, the present application further proposes that the generation mode of the cross-sectional geometric complexity characteristic value specifically includes: Through the formula:

[0059] Generate cross-sectional geometric complexity characteristic value ; In the formula, C represents the cross-sectional contour perimeter, A represents the cross-sectional contour area, and k is a constant, which is 4; The cross-sectional contour perimeter C refers to the total length of the closed contour curve of the cross-sectional edge, which can be realized by calculating the cumulative value of the distance between adjacent pixels after extracting the contour pixel points by using the image edge detection algorithm. This parameter is used to represent the extensibility and irregularity of the contour; The cross-sectional contour area A refers to the number of pixels in the area enclosed by the closed contour curve. It can be realized by multiplying the total number of pixels in the closed area by the unit pixel area by using the image filling algorithm. This parameter is used to reflect the size of the cross-section; The constant k takes the value of 4, which means that the ideal circle is taken as a reference shape of the normalization factor, and the specific value can be derived by substituting the relationship between the circumference and the area of the circle into the formula. When the cross section is circular, the characteristic value is equal to 1. This setting makes the complexity of any shape be converted into the degree of deviation from the standard circle. Specifically, this scheme converts the complexity of the contour shape into a quantifiable indicator by establishing a proportional relationship model between the square of the circumference and the area. The square operation of the circumference parameter strengthens the contribution of edge irregularity to the result, and the area parameter as the denominator balances the influence of size difference. When the cross-sectional shape deviates from the circle, the characteristic value will increase as the growth rate of the circumference exceeds the expansion rate of the area. For example, for a circular and star-shaped cross section with the same area, the star-shaped cross section will have a higher characteristic value due to the significant increase in circumference, and thus be identified as a more complex structure. By setting k to 4, the circular characteristic value is constant at 1, forming a normalization reference, so that the complexity evaluation of any shape has a unified standard.

[0060] Compared with the prior art, the traditional method relies on manual experience to judge the complexity of the cross section, lacks quantitative evaluation standard, and leads to low screening efficiency and large subjective deviation. The fixed direction sectioning or random attempt method in the prior art cannot accurately capture the key structural features of the internal medicine. The present scheme converts the geometric shape into a quantitative numerical indicator through mathematical modeling, eliminates the uncertainty of manual judgment, and realizes the standardization and automation of complexity evaluation. Through the above technical scheme, the present application provides an objective and quantitative basis for evaluating the complexity of the cross-sectional structure of medicinal materials, so that the system can automatically identify cross sections with high complexity characteristics. The characteristic value is used as a key input parameter for display value scoring, effectively selecting complex cross sections that can reflect the internal texture boundaries, cavity distribution or vessel orientation of medicinal materials, and improving the recognizability and teaching pertinence of structural features in three-dimensional teaching display.

[0061] Preferably, the present application further provides an expression of the cross-sectional display value evaluation model, which is specifically:

[0062] In the expression, represents the cross-sectional display value score, represents the cross-sectional texture information entropy value, represents the cross-sectional geometric complexity characteristic value, represents the cross-sectional color distribution characteristic value, , , are weight coefficients, and ; The generation method of the cross-sectional color distribution characteristic value specifically includes: Through the formula:

[0063] cross-section color distribution feature value ; In the formula, represents the standard deviation of all pixel values of the red R channel of the cross-section image, represents the standard deviation of all pixel values of the green G channel of the cross-section image, represents the standard deviation of all pixel values of the blue B channel of the cross-section image, represents the arithmetic mean of all pixel values of the red R channel of the cross-section image, represents the arithmetic mean of all pixel values of the green G channel of the cross-section image, represents the arithmetic mean of all pixel values of the blue B channel of the cross-section image, and g is a constant and takes a value of 3; wherein the cross-section texture information entropy value is a quantitative index reflecting the internal texture difference through the statistical characteristics of the pixel distribution of the gray-scale image, and can be specifically realized by calculating the Shannon entropy of the probability of occurrence of each gray level, and is used to capture the distribution characteristics of the microstructure such as fibers and vessels in the cross-section of medicinal materials; cross-section geometric complexity feature value is a parameter for measuring the complexity of the contour shape through the ratio of the perimeter to the area, and can be specifically realized by using the normalized circularity calculation formula, and is used to distinguish between smooth contours and complex structures with fractal characteristics; cross-section color distribution feature value is an index for representing the significance of color change through the statistical parameters of the RGB channel, and can be specifically realized by using the sum of the squares of the ratio of the standard deviation to the mean of the channel, and is used to identify the visual features such as color stratification and spots in the cross-section; weighting coefficients , , are adjustment parameters for balancing the influence of different feature dimensions on the score, and can be specifically determined by using empirical values or machine learning optimization methods, for example , , can be respectively set to 0.4, 0.3, and 0.3, and the normalization of the evaluation results is ensured by constraining the total sum of the weights to be 1.

[0064] Specifically, the technical scheme extracts features through three parallel computing modules. The texture analysis module performs histogram statistics on the cross-sectional gray image, calculates the probability of each gray level, and then substitutes it into the Shannon entropy formula to obtain the entropy value reflecting the internal organizational density. The geometric analysis module measures the perimeter and area of the cross-sectional profile, and generates a feature value representing the shape complexity by normalizing the ratio of the square of the perimeter to the area. The color analysis module separates the RGB channels and calculates the mean and standard deviation of each channel, and reflects the dispersion degree of color distribution through the square of the ratio of the standard deviation to the mean. The three feature values are weighted and summed after being weighted by a weight coefficient to generate a comprehensive score for cross-sectional value ranking, and finally the cross-section with the highest score is selected as the optimal display surface.

[0065] Compared with the prior art, the traditional method usually only relies on a single geometric parameter or manually selects the cross-section according to experience, for example, only according to the maximum area or the most regular contour, which is easy to ignore the texture details and color features. The present scheme establishes a multi-dimensional evaluation system to linearly fuse the texture entropy value, geometric complexity and color distribution feature, which not only retains the advantages of single feature, but also balances the features through weight adjustment. For example, when evaluating the cross-section of medicinal materials with obvious annual ring structure, a higher geometric complexity feature value can effectively highlight the ring texture, and the color distribution feature value can capture the color difference of different growth layers, and the synergistic effect of the two can improve the evaluation accuracy.

[0066] Through the above technical scheme, the present application can automatically identify the cross-section of medicinal materials which has rich texture details, complex geometric shape and significant color contrast, solve the feature omission problem caused by single evaluation dimension of traditional methods, avoid the randomness of manual screening, and improve the standardization degree of teaching display.

[0067] Preferably, the present application further proposes that the generation mode of the optimal cross-section specifically comprises: Through the formula:

[0068] Generate the optimal cross-section ; In the formula, represents the cross-sectional display value score of the cross-section , and represents the fth cross-section. Among them, the cross-sectional display value score is an index for quantitatively evaluating the display value of each candidate cross-section through mathematical modeling, which can be realized by adopting a weighted calculation model of comprehensive texture information entropy value, geometric complexity feature value and color distribution feature value. The scoring model provides an objective quantitative basis for cross-section selection. The argmax function refers to a calculation method for finding a solution corresponding to the maximum value of a target function from a limited candidate set. Specifically, an algorithm can be used to traverse and compare the score values of all candidate sections and record the index of the maximum value. This function ensures quick determination of the global optimal solution in a discrete solution space.

[0069] Specifically, the system first calculates the texture features, geometric features, and color distribution features of all candidate sections in parallel, and generates a comprehensive score value for each section through a predefined weighted scoring formula. After the scoring calculation is completed, the system traverses all the score results and marks the section with the highest score value as the optimal display object. This process converts complex teaching requirements into executable numerical comparison operations through mathematical optimization algorithms, enabling efficient decision-making under limited computing resources. The weight coefficients in the scoring model can be dynamically adjusted according to different types of medicinal materials, for example, the geometric complexity weight can be increased for rhizome-type medicinal materials to highlight the internal vascular bundle structure. Compared with the prior art, the traditional method relies on manual experience to select a section or only supports fixed direction cutting, which cannot guarantee that the section contains key structural information. The present solution solves the randomness problem of display effect caused by the lack of evaluation criteria in the prior art by establishing a multi-dimensional evaluation model and an automated optimization mechanism, which selects the dissection section with the highest information density without human intervention. Through the above technical solution, the present application realizes intelligent selection of the section of the medicinal material three-dimensional model, effectively improving the information transmission efficiency of teaching display. The system can automatically identify and highlight the anatomical features of medicinal materials that have identification significance, such as preferentially selecting sections with dense oil chamber distribution and clear vessel arrangement when displaying the cross section of angelica, allowing learners to intuitively observe the core structural features of medicinal materials.

[0070] Please refer to Figure 2 The present application also proposes a three-dimensional teaching display method for Chinese medicinal materials, which is applied to the three-dimensional teaching display system for Chinese medicinal materials described above, and specifically includes the following steps: Step S10: Establish a three-dimensional model of Chinese medicinal materials; Step S20: Obtain the stroke point sequence of the user's cutting intention drawn on the model surface, and generate a candidate normal set; Step S30: Cut the three-dimensional model of Chinese medicinal materials according to the candidate normal set, and obtain image data of the section of the three-dimensional model of Chinese medicinal materials; wherein the image data includes a section grayscale image, a section contour perimeter, and a section contour area; Step S40: Establish a section display value evaluation model according to the image data of the section, and generate a section display value score; Step S50: Generate the optimal section of the three-dimensional model of Chinese medicinal materials according to the section display value score of all sections; Step S60: According to the optimal section of the traditional Chinese medicine material three-dimensional model, the section display of the traditional Chinese medicine material three-dimensional model is performed.

[0071] Preferably, the step S20 further includes: According to the stroke point sequence of the cutting intention, an average direction vector of the stroke as a whole is generated; According to the average direction vector of the stroke as a whole, a normalized stroke main direction unit vector is generated; According to the normalized stroke main direction unit vector, a candidate normal set is generated.

[0072] Preferably, the step S40 further includes: According to the section gray image, a section texture information entropy value is generated; According to the section contour perimeter and the section contour area, a section geometric complexity characteristic value is generated; According to the section texture information entropy value and the section geometric complexity characteristic value, a section display value evaluation model is established, and a section display value score is generated.

[0073] Although the embodiments of the present application have been shown and described, it is to be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A three-dimensional teaching display system for traditional Chinese medicine materials, characterized in that, The system specifically comprises: A three-dimensional model establishing unit for establishing a three-dimensional model of a traditional Chinese medicine medicinal material; A cutting presetting unit for obtaining a stroke point sequence of a cutting intention drawn by a user on a model surface, and generating a candidate normal set; A data acquisition unit for cutting the three-dimensional model of the traditional Chinese medicine medicinal material according to the candidate normal set, and acquiring image data of a cross section of the three-dimensional model of the traditional Chinese medicine medicinal material; wherein the image data comprises a cross section grayscale image, a cross section contour perimeter, and a cross section contour area; A cross section analysis unit for establishing a cross section display value evaluation model according to the image data of the cross section, and generating a cross section display value score; An optimal cross section analysis unit for generating an optimal cross section of the three-dimensional model of the traditional Chinese medicine medicinal material according to the cross section display value scores of all cross sections; A display unit for performing cross section display on the three-dimensional model of the traditional Chinese medicine medicinal material according to the optimal cross section of the three-dimensional model of the traditional Chinese medicine medicinal material.

2. The traditional Chinese medicine material three-dimensional teaching display system according to claim 1, characterized in that, The cutting presetting unit specifically comprises: A stroke space direction generation module for generating an average direction vector of a stroke as a whole according to the stroke point sequence of the cutting intention; A main direction analysis module for generating a normalized stroke main direction unit vector according to the average direction vector of the stroke as a whole; A candidate normal set generation module for generating the candidate normal set according to the normalized stroke main direction unit vector.

3. The traditional Chinese medicine material three-dimensional teaching display system according to claim 2, characterized in that, The generation manner of the average direction vector of the stroke as a whole specifically comprises: through a formula: generating an average direction vector for the whole of the stroke ; In the formula, represents the three-dimensional coordinates of the i+1th stroke point, represents the three-dimensional coordinates of the i th stroke point, and n represents the number of points contained in the stroke point sequence of the cutting intention, is the Euclidean norm of the vector.

4. The traditional Chinese medicine material three-dimensional teaching display system according to claim 2, characterized in that, The generation manner of the normalized stroke main direction unit vector specifically comprises: through a formula: generating normalized stroke main direction unit vectors ; In the formula, represents the average direction vector of the whole stroke, is the Euclidean norm of the vector.

5. The Chinese medicine material three-dimensional teaching display system according to claim 2, characterized in that, The generation manner of the candidate normal set specifically comprises: through a formula: generating a set of candidate normals ; In the formula, represents the normalized stroke main direction unit vector, represents the global reference direction unit vector, represents the vector perpendicular to both the stroke main direction and the global reference direction, is the cross product operator of vectors, represents the opposite direction of represents the opposite direction of represents the opposite direction of the global reference direction unit vector .

6. The Chinese medicine material three-dimensional teaching display system according to claim 1, characterized in that, The cross section analysis unit specifically comprises: A texture analysis module for generating a cross section texture information entropy value according to the cross section grayscale image; A geometry analysis module for generating a cross section geometry complexity characteristic value according to the cross section contour perimeter and the cross section contour area; An integrated analysis module for establishing a cross section display value evaluation model according to the cross section texture information entropy value and the cross section geometry complexity characteristic value, and generating a cross section display value score.

7. The Chinese medicine material three-dimensional teaching display system according to claim 6, characterized in that, The generation manner of the cross section texture information entropy value specifically comprises: through a formula: generating cross-sectional texture information entropy values ; In the equation, L represents the total number of gray levels of the gray scale image, represents the probability of the gray level j appearing in the cross-sectional image. The generation manner of the probability of the gray level j appearing in the cross section image specifically is: through a formula: Probability of occurrence of gray level j in cross-sectional images ; In the formula, represents the number of pixels with a gray value of j in the gray-scale image, represents the total number of pixels in the gray-scale image.

8. The traditional Chinese medicine material three-dimensional teaching display system according to claim 6, characterized in that, The generation manner of the cross section geometry complexity characteristic value specifically comprises: through a formula: Generating cross-sectional geometry complexity characteristic values ; In the formula, C represents the cross section contour perimeter, A represents the cross section contour area, and k is a constant.

9. The traditional Chinese medicine material three-dimensional teaching display system according to claim 6, characterized in that, The expression of the cross section display value evaluation model specifically is: In the expression, represents the cross-section display value score, represents the cross-section texture information entropy value, represents the cross-section geometric complexity characteristic value, represents the cross-section color distribution characteristic value, , , are weight coefficients, and ; wherein the generation manner of the cross section color distribution characteristic value specifically comprises: through a formula: generating cross-sectional color distribution feature values ; In the formula, denotes the standard deviation of all pixel values of the red color R channel of the cross-sectional image, denotes the standard deviation of all pixel values of the green color G channel of the cross-sectional image, denotes the standard deviation of all pixel values of the blue color B channel of the cross-sectional image, denotes the arithmetic mean of all pixel values of the red color R channel of the cross-sectional image, denotes the arithmetic mean of all pixel values of the green color G channel of the cross-sectional image, denotes the arithmetic mean of all pixel values of the blue color B channel of the cross-sectional image, g being a constant.

10. The traditional Chinese medicine material three-dimensional teaching display system according to claim 1, characterized in that, The generation manner of the optimal cross section specifically comprises: through a formula: generating an optimal cross section ; In the formula, represents the cross-section of the cross-section presentation value score, represents the f-th cross-section.

Images