Three-dimensional model construction method based on ophthalmology detection

Abstract

The invention relates to the field of eye detection, and discloses a three-dimensional model construction method based on ophthalmology detection, which comprises the following steps: firstly, collecting human eye state information, and preprocessing the human eye state information to obtain preliminary eye state information; performing data analysis on the initial eye state information, and determining initial parameters of an eye three-dimensional model; performing parameter optimization to obtain screening parameters of the eye three-dimensional model; establishing an eye three-dimensional model, collecting eye key points in the eye three-dimensional model, and binding eye screening point data for the eye key points; performing normalization processing on the eye key points, and performing screening operation through big data comparison to obtain final eye state information; geometric structure reconstruction is carried out to obtain a reconstructed eye three-dimensional model; the problems that in the prior art, eye detection is not accurate, the diagnosis result is prone to being affected, and an existing eye model is greatly different from the actual eye size, position and shape of a patient are solved.

Description

Technical Field

[0001] The present invention relates to the field of eye detection, and in particular to a method for constructing a three-dimensional model based on ophthalmic detection. Background Art

[0002] With the development of technology, the medical level has gradually improved. For ophthalmology, medical technology has also become more and more developed. However, since the eyes are relatively vulnerable organs of the human body, great care is required during both ophthalmic detection and eye treatment.

[0003] Current ophthalmic detection technologies basically use lasers for eye monitoring and scanning. However, in existing eye monitoring technologies, the detection effect is not good. Since the eye is not a flat surface, the images obtained by laser scanning are affected by overlapping, resulting in a very poor effect and easily affecting the detection and diagnosis results. Therefore, a method for constructing a three-dimensional model based on ophthalmic detection is highly necessary. Summary of the Invention

[0004] The present invention aims to provide a method for constructing a three-dimensional model based on ophthalmic detection to solve the problems of inaccurate eye detection in the prior art, which easily affects the diagnosis results, and the large differences in size, position, and shape between the existing eye models and the actual eyes of patients.

[0005] To achieve the above object, the present invention provides the following method: A method for constructing a three-dimensional model based on ophthalmic detection provided by the present invention is as follows: S1: Collect the eye state information of the human body through an eye detection device, and preprocess the eye state information of the human body to obtain preliminary eye state information; S2: Analyze the preliminary eye state information based on historical ophthalmic detection data to establish the initial parameters of the eye three-dimensional model; S3: Optimize the initial parameters of the eye three-dimensional model to obtain the screening parameters of the eye three-dimensional model; S4: Establish an eye three-dimensional model according to the screening parameters of the eye three-dimensional model, collect the eye key points in the eye three-dimensional model, and bind the eye screening point data to the eye key points; S5: Normalize the eye key points, perform screening operations through big data comparison, and obtain the final eye state information; S6: Use the final eye state information after the screening operation to perform geometric correction processing and geometric structure reconstruction to obtain the reconstructed eye three-dimensional model.

[0006] Preferably, the collecting of human eye status information through eye detection equipment includes: detecting basic human eye information through ophthalmic ultrasound diagnostic equipment, OTC, ophthalmic AI screening software, and ophthalmic surgical microscope, as well as human eye refractive power, visual field, ophthalmoscope, slit lamp and intraocular pressure measurement.

[0007] Preferably, the step of preprocessing the human eye state information to obtain preliminary eye state information includes: screening the collected human eye state information for invalid data and calculating the average data value of the human eye state information; if the human eye state information is higher / lower than 70% of the average data value of the human eye state information, screening out the human eye state information to obtain valid human eye state information; converting the valid human eye state information into a unified format, storing the valid human eye state information in a unified database to obtain preliminary eye state information.

[0008] Preferably, the step of performing data analysis on the preliminary eye state information according to historical ophthalmic test data to establish the initial parameters of the three-dimensional eye model includes: summarizing and analyzing the basic information of the human eye and the historical ophthalmic test data, by dividing the eye from inside to outside into three parts of the eye body, namely the core body, the outer eye body, and the inner eye body; performing data splitting on the preliminary eye state information according to the three parts of the eye body, and calculating the average initial parameters of each of the three parts of the eye body by combining the historical ophthalmic test data; performing data fitting on the average parameters of the three parts of the eye body, and combining multiple groups of data on the average initial parameters at the junction of the three parts of the eye body to obtain the initial parameter interval of the eye junction; performing data encapsulation on the average initial parameters of each of the three parts of the eye body and the initial parameter interval of the eye junction to obtain the initial parameters of the three-dimensional eye model.

[0009] Preferably, the initial parameters of the three-dimensional eye model are optimized to obtain the formula for screening parameters of the three-dimensional eye model: P=St=(1-a)S(t-1)+M Among them, P is the screening parameter of the eye 3D model, S is the initial parameter of the eye 3D model, a is the mixing parameter, a∈(0,1), t is the tth cycle in the model training cycle, and M is the parameter update amount of the model training.

[0010] Preferably, after optimizing the initial parameters of the three-dimensional eye model to obtain the screening parameters of the three-dimensional eye model, it further includes verifying the accuracy of the screening parameters of the three-dimensional eye model: the server obtains the current time point and the previous verification time point; the server determines whether the verification time value is reached according to the current time point and the previous verification time point; if so, the server sends a verification start instruction to the target subsystem; the server determines whether the screening parameters of the three-dimensional eye model are received within a preset time; if so, the server verifies and compares the screening parameters of the three-dimensional eye model with the historical ophthalmic detection data stored in the server, and the verification comparison is a comparison of the screening parameters of the three-dimensional eye model with a data set of the same attributes in the historical ophthalmic detection data; the server performs corresponding verification operations according to the comparison result of the verification comparison, and the comparison result is the result of whether the verification data set is abnormal.

[0011] Preferably, the step of the server verifying and comparing the screening parameters of the three-dimensional eye model with the historical ophthalmic detection data stored in the server includes: the server performs a set retrieval in the historical ophthalmic detection data stored in the server according to the screening parameters of the three-dimensional eye model, and the set retrieval is a retrieval of a data set of the same type as the screening parameters of the three-dimensional eye model; the server extracts a first comparison data set according to the retrieval result of the set retrieval; the server verifies and compares the screening parameters of the three-dimensional eye model with the first comparison data set; the server verifying and comparing the screening parameters of the three-dimensional eye model with the first comparison data set includes: the server calculates a first verification value of the screening parameters of the three-dimensional eye model, and the first verification value is the ratio of the screening parameters of the three-dimensional eye model to the first comparison data set; the server calculates a second verification value of the first comparison data set, and the value of the second verification value is 0 or 1; the server determines whether there is a value of 0 among the first verification value and the second verification value; if not, the server determines whether the first verification value and the second verification value are consistent; if the server determines that the first verification value and the second verification value are consistent, the server determines that the screening parameters of the three-dimensional eye model are not abnormal.

[0012] Preferably, the steps of establishing an eye three-dimensional model according to the eye three-dimensional model screening parameters, collecting eye key points in the eye three-dimensional model, and binding eye screening point data to the eye key points include: establishing an eye three-dimensional model according to the eye three-dimensional model screening parameters; collecting eye key points in the eye three-dimensional model, where the eye key points are the center points of the core body, the outer eye body, and the inner eye body, the central intersection points of each part, and the central point of the core area of eye detection; binding the eye three-dimensional model screening parameters for eye detection to the eye key points, and connecting all the eye key points adjacent to each other to form an eye three-dimensional structure network.

[0013] Preferably, the steps of normalizing the eye key points, performing screening operations through big data comparison, and obtaining the final eye state information include: normalizing the eye three-dimensional structure network, converting the data of the eye three-dimensional structure network, converting the format of each eye three-dimensional structure network into a unique data string, and obtaining an eye three-dimensional structure string; performing screening operations on the eye three-dimensional structure string through big data, and comparing multiple eye three-dimensional structure strings; screening based on the difference degree of the adjacent point positions of each eye key point in the eye three-dimensional structure string, obtaining the eye three-dimensional structure string with the lowest difference degree, and obtaining the final eye state information.

[0014] Preferably, the steps of performing geometric correction processing on the final eye state information after the screening operation, performing geometric structure reconstruction, and obtaining a reconstructed eye three-dimensional model include: screening the overlapping eye key points in the final eye state information according to the repetition rate of the eye key points; performing geometric reconstruction of the eye three-dimensional model according to the positions of the eye key points with the most overlapping times at the same position for the overlapping eye key points; and establishing the reconstructed eye three-dimensional model according to the eye key points obtained by geometric reconstruction.

[0015] The beneficial effects of the present invention are reflected in that: by collecting the eye state information of the human body, the present invention successively performs steps such as preprocessing, data analysis, and screening parameters to correct the parameters of the eye three-dimensional model, making the data of the eye three-dimensional model more accurate, preventing errors in eye detection results and incorrect detection data. Then, after establishing the eye three-dimensional model, it successively performs screening of eye key points and normalization processing, enabling the eye three-dimensional model to be specifically adjusted for different detected humans, and being able to adapt to the establishment of eye three-dimensional models for patients of different ages and different physical conditions. Finally, geometric correction processing is performed to reconstruct the eye three-dimensional model, making the establishment process of the eye three-dimensional model faster each time, being able to fine-tune using the historical eye three-dimensional model, making the reconstructed eye three-dimensional model more widely applicable and the use process more convenient. Brief Description of the Drawings

[0016] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts do not necessarily draw according to the actual scale.

[0017] Figure 1 is a schematic flowchart of a three-dimensional model construction method based on ophthalmic detection provided by an embodiment of the present invention; Figure 2 is a flowchart of the model construction steps of the three-dimensional eye model provided by an embodiment of the present invention. Specific embodiments

[0018] The following is to enable those skilled in the art to better understand the solution of the present invention. The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present invention.

[0019] The terms "first", "second", etc. in the specification and claims of the present invention and the above drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or terminal comprising a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or terminals.

[0020] Referring to "embodiment" in this article means that the specific features, structures or characteristics described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0021] Currently, the basic ophthalmic detection technologies all use the laser method for eye monitoring and scanning. However, in the existing eye monitoring technologies, the detection effect is not good. Since the eye is not a flat surface, the images scanned by the laser are affected by the overlapping, resulting in a very poor effect, which is likely to affect the detection result and the diagnosis result. Therefore, a three-dimensional model construction method based on ophthalmic detection is very necessary.

[0022] The present invention aims to provide a three-dimensional model construction method based on ophthalmic detection to solve the problems of inaccurate eye detection in the prior art, which easily affects the diagnosis results, and the large differences between the existing eye model and the actual patient's eye size, position and shape.

[0023] The specific embodiment of the present invention provides a method for constructing a three-dimensional model based on ophthalmological detection, the method is as follows Figure 1 , Figure 2 As shown, the following steps are included: S1: Collect human eye status information through an eye detection device, and pre-process the human eye status information to obtain preliminary eye status information.

[0024] In an embodiment of the present invention, collecting human eye status information through eye detection equipment includes: detecting basic human eye information, as well as human eye refractive power, visual field, ophthalmoscope, slit lamp and intraocular pressure measurement through ophthalmic ultrasound diagnostic instrument, OTC, ophthalmic AI screening software, and ophthalmic surgical microscope; filtering invalid data of the collected human eye status information, and calculating the average data value of the human eye status information; if the human eye status information is higher / lower than 70% of the average data value of the human eye status information, the human eye status information is filtered out to obtain valid human eye status information; converting the valid human eye status information into a unified format, storing the valid human eye status information in a unified database, and obtaining preliminary eye status information.

[0025] S2: Perform data analysis on preliminary eye status information based on historical ophthalmic examination data to establish initial parameters of the three-dimensional eye model.

[0026] In an embodiment of the present invention, basic information of human eyes and historical ophthalmic test data are summarized and analyzed, and the eyes are divided into three parts from inside to outside, namely the core body, the outer eye body, and the inner eye body; preliminary eye state information is data-split according to the three parts of the eye body, and the average initial parameters of each of the three parts of the eye body are calculated in conjunction with the historical ophthalmic test data; the average parameters of the three parts of the eye body are data-fitted, and the average initial parameters at the junction of the three parts of the eye body are combined with multiple groups of data to obtain the initial parameter interval of the eye junction; the average initial parameters of each of the three parts of the eye body and the initial parameter interval of the eye junction are data-encapsulated to obtain the initial parameters of the three-dimensional eye model.

[0027] S3: Optimize the initial parameters of the three-dimensional eye model to obtain screening parameters of the three-dimensional eye model.

[0028] In the embodiment of the present invention, the initial parameters of the three-dimensional eye model are optimized, and the formula for obtaining the screening parameters of the three-dimensional eye model is: P = St = (1 - a)S(t - 1) + M Among them, P is the screening parameter of the eye three-dimensional model, S is the initial parameter of the eye three-dimensional model, a is the mixing parameter, a ∈ (0, 1), t is the t-th cycle in the model training period, and M is the parameter update amount of model training; after optimizing the initial parameters of the eye three-dimensional model to obtain the screening parameters of the eye three-dimensional model, it also includes verifying the accuracy of the screening parameters of the eye three-dimensional model: The server obtains the current time point and the previous verification time point; the server determines whether the verification time value is reached according to the current time point and the previous verification time point; if so, the server sends a verification start instruction to the target subsystem; the server determines whether the screening parameters of the eye three-dimensional model are received within the preset time; if so, the server verifies and compares the screening parameters of the eye three-dimensional model with the historical ophthalmic detection data stored in the server, and the verification comparison is the comparison of the data sets with the same attributes between the screening parameters of the eye three-dimensional model and the historical ophthalmic detection data; the server performs corresponding verification operations according to the comparison result of the verification comparison, and the comparison result is the result of whether the verification data set is abnormal; the server performs a set retrieval in the historical ophthalmic detection data stored in the server according to the screening parameters of the eye three-dimensional model, and the set retrieval is the retrieval of the data set of the same type as the screening parameters of the eye three-dimensional model; the server extracts the first comparison data set according to the retrieval result of the set retrieval; the server verifies and compares the screening parameters of the eye three-dimensional model with the first comparison data set; the server verifies and compares the screening parameters of the eye three-dimensional model with the first comparison data set, including: the server calculates the first verification value of the screening parameters of the eye three-dimensional model, and the first verification value is the ratio of the screening parameters of the eye three-dimensional model to the first comparison data set; the server calculates the second verification value of the first comparison data set, and the value of the second verification value is 0 or 1; the server determines whether there is a value of 0 among the first verification value and the second verification value; if not, the server determines whether the first verification value and the second verification value are consistent; if the server determines that the first verification value and the second verification value are consistent, the server determines that the screening parameters of the eye three-dimensional model are not abnormal.

[0029] S4: Establish an eye three-dimensional model according to the screening parameters of the eye three-dimensional model, collect the eye key points in the eye three-dimensional model, and bind the eye screening point data to the eye key points.

[0030] In the embodiment of the present invention, an eye three-dimensional model is established according to the screening parameters of the eye three-dimensional model; the eye key points in the eye three-dimensional model are collected, and the eye key points are the center points of the core body, the outer eye body, the inner eye body, the central intersection points of each part, and the central point of the core area of the eye detection; the screening parameters of the eye three-dimensional model for eye detection are bound to the eye key points, and all the eye key points are connected adjacent to each other to form an eye three-dimensional structure network.

[0031] S5: Normalize the key points of the eye, and through big data comparison, perform screening operations to obtain the final eye state information.

[0032] In the embodiment of the present invention, the three-dimensional eye structure network is normalized, the data of the three-dimensional eye structure network is transformed, and each three-dimensional eye structure network is formatted into a unique data string to obtain the three-dimensional eye structure string; the three-dimensional eye structure string is screened and calculated through big data, and multiple three-dimensional eye structure strings are compared; screening is performed based on the difference degree of the adjacent point positions of each key point of the eye in the three-dimensional eye structure string, and the three-dimensional eye structure string with the lowest difference degree is obtained to obtain the final eye state information.

[0033] S6: Use the final eye state information after screening operations to perform geometric correction processing and geometric structure reconstruction to obtain the reconstructed three-dimensional eye model.

[0034] In the embodiment of the present invention, the overlapping key points of the eye are screened according to the repetition rate of the key points of the eye in the final eye state information; according to the overlapping key points of the eye, the three-dimensional eye model is geometrically reconstructed according to the position of the key point of the eye with the most overlapping times at the same position; the reconstructed three-dimensional eye model is established according to the key points of the eye reconstructed geometrically.

[0035] The beneficial effects of the present invention are reflected in: by collecting the eye state information of the human body, the present invention successively performs steps such as preprocessing, data analysis, and screening parameters to correct the parameters of the three-dimensional eye model, making the data of the three-dimensional eye model more accurate, preventing errors in the eye detection results and incorrect detection data. Then, after establishing the three-dimensional eye model, the key points of the eye are screened and normalized successively, so that the three-dimensional eye model can be specifically adjusted for different detected humans, and can adapt to the establishment of three-dimensional eye models for patients of different ages and different physical conditions. Finally, geometric correction processing is performed to reconstruct the three-dimensional eye model, making the establishment process of the three-dimensional eye model faster each time, being able to use the historical three-dimensional eye model for fine-tuning, making the reconstructed three-dimensional eye model more widely applicable and more convenient to use.

[0036] The above are only embodiments of the present invention, and common specific technical solutions or characteristics and the like in the solution are not described in detail here; it should be noted that for those skilled in the art, without departing from the solution of the present invention, several deformations and improvements can still be made, and these should also be regarded as the protection scope of the present invention, and these will not affect the effects of the present invention and the practicality of the patent. The protection scope required by this application should be subject to the content of its claims, and the specific implementation manners and the like recorded in the specification can be used to explain the content of the claims.

Claims

1. A three-dimensional model construction method based on ophthalmological detection, characterized in that: The method comprises: S1: collecting human eye state information through an eye detection device, and preprocessing the human eye state information to obtain preliminary eye state information; S2: performing data analysis on the preliminary eye status information according to historical ophthalmological test data to establish initial parameters of the three-dimensional eye model; S3: Optimizing the initial parameters of the three-dimensional eye model to obtain screening parameters of the three-dimensional eye model; S4: establishing a three-dimensional eye model according to the three-dimensional eye model screening parameters, collecting eye key points in the three-dimensional eye model, and binding eye screening point data to the eye key points; S5: normalizing the eye key points, performing screening operations through big data comparison, and obtaining final eye state information; S6: Performing geometric correction processing using the final eye state information after the screening operation, and reconstructing the geometric structure to obtain a reconstructed three-dimensional eye model.

2. The method for constructing a three-dimensional model based on ophthalmic detection according to claim 1, characterized in that: The collecting of human eye status information through eye detection equipment includes: detecting basic information of the human eye through ophthalmic ultrasound diagnostic equipment, OTC, ophthalmic AI screening software, and ophthalmic surgical microscope, as well as the refractive power, visual field, ophthalmoscope, slit lamp and intraocular pressure measurement of the human eye.

3. A three-dimensional model construction method based on ophthalmic detection according to claim 2, characterized in that: The step of preprocessing the human eye state information to obtain preliminary eye state information includes: Screening invalid data from the collected human eye state information and calculating an average data value of the human eye state information; If the human eye state information is higher / lower than 70% of the average data value of the human eye state information, the human eye state information is filtered out to obtain valid human eye state information; The effective information on the human eye state is converted into a unified format, and the effective information on the human eye state is stored in a unified database to obtain preliminary eye state information.

4. A three-dimensional model construction method based on ophthalmic detection according to claim 3, characterized in that: The step of performing data analysis on the preliminary eye state information according to historical ophthalmological test data to establish initial parameters of the eye three-dimensional model includes: The basic information of human eyes and historical ophthalmological test data are summarized and analyzed, and the eyes are divided into three parts from inside to outside, namely the core body, the outer eye body, and the inner eye body; Splitting the preliminary eye status information according to the three parts of the eye body, and calculating the average initial parameters of each of the three parts of the eye body in conjunction with the historical ophthalmological test data; The average parameters of the three parts of the eye body are fitted, and the average initial parameters of the junction of the three parts of the eye body are combined with multiple groups of data to obtain the initial parameter interval of the eye junction; The average initial parameters of each of the three parts of the eye body and the initial parameter interval of the eye boundary are data packaged to obtain the initial parameters of the three-dimensional eye model.

5. A method for constructing a three-dimensional model based on ophthalmic detection according to claim 4, characterized in that: The parameter optimization of the initial parameters of the eye three-dimensional model is performed to obtain the formula for the screening parameters of the eye three-dimensional model: P=St=(1-a)S(t-1)+M Among them, P is the screening parameter of the eye 3D model, S is the initial parameter of the eye 3D model, a is the mixing parameter, a∈(0,1), t is the tth cycle in the model training cycle, and M is the parameter update amount of model training.

6. The method for constructing a three-dimensional model based on ophthalmic testing according to claim 1, characterized in that: After optimizing the initial parameters of the eye three-dimensional model to obtain the eye three-dimensional model screening parameters, the method further includes verifying the accuracy of the eye three-dimensional model screening parameters: The server obtains the current time point and the last verification time point; The server determines whether the verification time value is reached according to the current time point and the last verification time point; If yes, the server sends a verification start instruction to the target subsystem; The server determines whether the eye three-dimensional model screening parameters are received within a preset time; If yes, the server verifies and compares the eye three-dimensional model screening parameters with the historical ophthalmic test data stored in the server, wherein the verification and comparison is a comparison of the eye three-dimensional model screening parameters with a data set of the same attributes of the historical ophthalmic test data; The server performs a corresponding verification operation according to a comparison result of the verification comparison, wherein the comparison result is a result of whether the verification data set is abnormal.

7. A method for constructing a three-dimensional model based on ophthalmological detection according to claim 6, characterized in that: The step of the server verifying and comparing the eye three-dimensional model screening parameters with the historical ophthalmic test data stored in the server includes: The server performs a set search in the historical ophthalmic test data stored in the server according to the eye three-dimensional model screening parameter, wherein the set search is a search for a data set of the same type as the eye three-dimensional model screening parameter; The server extracts a first comparison data set according to the search result of the set search; The server verifies and compares the eye three-dimensional model screening parameters with the first comparison data set; The server verifies and compares the eye three-dimensional model screening parameters with the first comparison data set, including: The server calculates a first verification value of the eye three-dimensional model screening parameter, where the first verification value is a ratio of the eye three-dimensional model screening parameter to the first comparison data set; The server calculates a second check value of the first comparison data set, where the second check value is 0 or 1; The server determines whether there is a value of 0 between the first check value and the second check value; If not, the server determines whether the first check value is consistent with the second check value; If the server determines that the first verification value is consistent with the second verification value, the server determines that there is no abnormality in the eye three-dimensional model screening parameters.

8. The method for constructing a three-dimensional model based on ophthalmological detection according to claim 4, characterized in that: The step of establishing a three-dimensional eye model according to the three-dimensional eye model screening parameters, collecting eye key points in the three-dimensional eye model, and binding eye screening point data to the eye key points comprises: Establishing a three-dimensional eye model according to the three-dimensional eye model screening parameters; Collecting eye key points in the three-dimensional eye model, wherein the eye key points are the center points of the core body, the outer eye body, the inner eye body, the center intersection points of each part, and the center point of the core area of ​​eye detection; The eye detection three-dimensional model screening parameters are bound to the eye key points, and all the eye key points are adjacently connected to form a three-dimensional eye structure network.

9. A method for constructing a three-dimensional model based on ophthalmological detection according to claim 8, characterized in that: The step of normalizing the eye key points, performing screening operations through big data comparison, and obtaining final eye state information includes: Normalizing the three-dimensional eye structure network, converting the three-dimensional eye structure network into data, and converting the format of each three-dimensional eye structure network into a unique data string to obtain a three-dimensional eye structure string; Performing screening operation on the three-dimensional eye structure character string through big data, and comparing multiple three-dimensional eye structure character strings; The eye three-dimensional structure character string is screened based on the degree of distinction of the positions of adjacent points of each eye key point, to obtain the eye three-dimensional structure character string with the lowest degree of distinction, and to obtain the final eye state information.

10. A method for constructing a three-dimensional model based on ophthalmological detection according to claim 9, characterized in that: The step of performing geometric correction processing and geometric structure reconstruction using the final eye state information after the screening operation to obtain a reconstructed eye three-dimensional model includes: Filtering the overlapping eye key points according to the eye key point repetition rate for the final eye state information; According to the overlapping eye key points, geometrically reconstructing the eye three-dimensional model according to the positions of the eye key points with the largest number of overlaps at the same position; The reconstructed three-dimensional eye model is established according to the geometrically reconstructed eye key points.

Images