Dysopia identification method and system

Abstract

The present application relates to a dysopia identification method and system. The method comprises: acquiring eyeball data information of a user and visual perception information of the user, and on the basis of the eyeball data information of the user, identifying cornea information of the user; on the basis of the eyeball data information of the user and by means of a gaze tracking algorithm, collecting a line-of-sight variation trajectory of the user, and on the basis of the line-of-sight variation trajectory of the user, determining eyeball focusing information of the user; on the basis of the visual perception information of the user and by means of a spectral perception policy, identifying a visual perception spectrum of the user, and on the basis of the visual perception spectrum of the user, identifying colour vision defect information of the user; and on the basis of the cornea information of the user and the eyeball focusing information of the user, performing calculation to obtain visual defect information of the user, and on the basis of the visual defect information of the user and the colour vision defect information of the user, determining dysopia information of the user. By means of the method, the accuracy of identifying visual defects of different users can be improved.

Description

Visual defect recognition method and system Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method and system for identifying visual defects. Background Art

[0002] In recent years, significant progress has been made in vision-related diseases and their treatment. Various technologies and devices have been developed to address visual impairments and enhance visual clarity for patients with myopia, hyperopia, astigmatism, and other vision-related diseases. Traditional methods of improving vision include the use of corrective lenses, such as glasses or contact lenses, which provide refractive correction to compensate for the eye's focusing errors. In addition, some vision therapies also include exercises and visual stimulation to improve eye coordination and focusing ability. However, this method is slow to take effect and requires the user's long-term assistance and cooperation, so how to improve the efficiency of vision correction is the focus of current research.

[0003] Current vision correction methods typically require multiple separate devices or specialized hardware for vision correction and eye tracking. This improves the efficiency of vision correction for users. However, the visual defect recognition methods used in these approaches are universal and do not consider the individual characteristics of users, resulting in low accuracy in identifying vision defects for different users.

[0004] Summary of the Invention

[0005] Based on this, it is necessary to provide a visual defect recognition method and system to address the above technical problems.

[0006] In a first aspect, the present application provides a method for identifying visual defects. The method comprises:

[0007] Acquiring user eyeball data information and the user's visual perception information, and identifying the user's cornea information based on the user's eyeball data information;

[0008] Based on the user's eye data information, using a gaze tracking algorithm, collecting the user's line of sight change trajectory, and determining the user's eye focus information based on the user's line of sight change trajectory;

[0009] Based on the visual perception information of the user, identifying the visual perception spectrum of the user through a spectral perception strategy, and identifying the color vision deficiency information of the user based on the visual perception spectrum of the user;

[0010] The user's vision defect information is calculated based on the user's cornea information and the user's eye focus information, and the user's visual defect information is determined based on the user's vision defect information and the user's color vision defect information.

[0011] Optionally, obtaining the user's eyeball data information and the user's visual perception information includes:

[0012] Collecting three-dimensional eye structure information of the user, and identifying eye sight information of the user based on the three-dimensional eye structure information of the user;

[0013] digitizing the user's three-dimensional structural information and the user's eye sight information to obtain the user's eye data information;

[0014] The user's perception information of each color in the spectrum and the user's identification information of each color in the spectrum are collected, and the perception information and the identification information are digitized to obtain the user's visual perception information.

[0015] Optionally, identifying the user's cornea information based on the user's eyeball data information includes:

[0016] Based on the three-dimensional eye structure information of the user, analyzing the three-dimensional boundary range of each eye structure in the three-dimensional eye structure information by an edge recognition algorithm;

[0017] In the three-dimensional boundary range of each eyeball structure, the three-dimensional boundary range of the cornea structure is screened, and the sub-three-dimensional structure information within the three-dimensional boundary range of the cornea structure is used as the cornea information of the user.

[0018] Optionally, collecting the user's gaze change trajectory based on the user's eyeball data information through a gaze tracking algorithm includes:

[0019] Obtain target change video information composed of target pictures played in a play order; the target pictures include position information of the target in the target pictures;

[0020] Based on the sample target change video information and the user's eye gaze information, a gaze tracking algorithm is used to collect the gaze focus position information of each time point when the user stays in each target object picture of the target change video information, and the gaze focus position information of each time point is connected according to the time sequence of each time point to obtain the user's gaze change trajectory.

[0021] Optionally, determining the user's eye focus information based on the user's gaze change trajectory includes:

[0022] Dividing the sight focus position information of the user at each time point in each target image of the target change video information according to each target image, to obtain the sight focus position information of the user in different target images;

[0023] For each target object image, based on the time points corresponding to the respective gaze focus position information of the user in the target object image and the gaze change trajectory of the user, the sub-sight change trajectory of the user in the target object image is filtered, and based on the respective gaze focus position information of the user in the target object image and the position information of the target object in the target object image, the respective gaze deviation change information of the user in the target object image is calculated;

[0024] Based on the sub-eyeline change trajectory of the user in the target object picture and the each line of sight deviation change information of the user in the target object picture, the sub-eyeball focusing information of the user in the target object picture is determined, and based on the sub-eyeball focusing information of the user in all target object pictures, the eyeball focusing information of the user is determined.

[0025] Optionally, identifying the user's visual perception spectrum by using a spectrum perception strategy based on the user's visual perception information includes:

[0026] Analyzing the user's perception information of each color based on the user's perception information of each color, and determining the user's recognition accuracy of each color based on the user's recognition information of each color;

[0027] For each color, based on the user's perception information of the color and the user's recognition accuracy of the color, the user's sensitivity to the color is calculated using a color sensitivity algorithm, and the user's sensitivity to each color is distributed and arranged according to the order of each color in the spectrum to obtain the user's visual perception spectrum.

[0028] Optionally, the calculating the user's vision impairment information based on the user's cornea information and the user's eye focusing information includes:

[0029] For each target object picture, identifying a target time point corresponding to a sight line deviation change information of the user that is lower than a deviation change threshold among each sight line deviation change information in the target object picture;

[0030] Calculating the precise focusing time of the user on the target object picture based on the time points corresponding to the respective sight line deviation change information of the user in the target object picture and the target time point of the user in the target object picture;

[0031] In the sub-sight line change trajectories of the user in the target object picture, according to the time sequence of the time points corresponding to the respective sight line deviation change information of the user in the target object picture, the target sight line change trajectories corresponding to all time points before the target time point in each time point of the target object picture are filtered, and based on the target sight line change trajectories, the user's sight focus range on the target object picture is identified;

[0032] The user's vision defect information is analyzed based on the user's precise focusing time in each target object picture, the user's cornea information, and the user's sight focusing range for each target object picture.

[0033] Optionally, analyzing the user's vision impairment information based on the user's precise focusing time in each target object image, the user's cornea information, and the user's sight focusing range for each target object image includes:

[0034] Obtaining the recognition difficulty of each target image, and normalizing the recognition difficulty of each target image to obtain a weight value of each target image;

[0035] For each target object image, based on the user's corneal information, the user's precise focusing time on the target object image, and the user's sight focusing range in the target object image, a vision defect judgment strategy is used to analyze the user's vision defect range for the target object in the target image and the user's zoom defect information for the target object in the target image;

[0036] Based on the weight values ​​of the target images, weighted processing is performed on the range of the user's vision defect in each target image to obtain the user's comprehensive vision defect range, and based on the weight values ​​of each target image, weighted processing is performed on the user's zoom defect information of the target object in each target image to obtain the user's comprehensive zoom defect information;

[0037] The user's comprehensive vision defect range and the user's comprehensive zoom defect information are used as the user's vision defect information.

[0038] Optionally, identifying the color vision deficiency information of the user based on the visual perception spectrum of the user includes:

[0039] Based on the user's visual perception, the color ranges corresponding to each normal color perception of the user and the color ranges corresponding to each abnormal color perception are identified, and in each color range of the abnormal color perception, the color range that meets the defect abnormality condition is screened as the user's color vision defect information.

[0040] In a first aspect, the present application provides a visual defect recognition system. The system comprises:

[0041] an acquisition module, configured to acquire eyeball data information of a user and visual perception information of the user, and identify corneal information of the user based on the eyeball data information of the user;

[0042] an analysis module, configured to collect a gaze change trajectory of the user based on the user's eyeball data information and a gaze tracking algorithm, and determine the user's eyeball focusing information based on the user's gaze change trajectory;

[0043] an identification module, configured to identify the user's visual perception spectrum based on the user's visual perception information and a spectral perception strategy, and to identify the user's color vision deficiency information based on the user's visual perception spectrum;

[0044] A determination module is used to calculate the user's vision defect information based on the user's corneal information and the user's eye focusing information, and to determine the user's visual defect information based on the user's vision defect information and the user's color vision defect information.

[0045] Optionally, the acquisition module is specifically configured to:

[0046] Collecting three-dimensional eye structure information of the user, and identifying eye sight information of the user based on the three-dimensional eye structure information of the user;

[0047] digitizing the user's three-dimensional structural information and the user's eye sight information to obtain the user's eye data information;

[0048] The user's perception information of each color in the spectrum and the user's identification information of each color in the spectrum are collected, and the perception information and the identification information are digitized to obtain the user's visual perception information.

[0049] Optionally, the acquisition module is specifically configured to:

[0050] Based on the three-dimensional eye structure information of the user, analyzing the three-dimensional boundary range of each eye structure in the three-dimensional eye structure information by an edge recognition algorithm;

[0051] In the three-dimensional boundary range of each eyeball structure, the three-dimensional boundary range of the cornea structure is screened, and the sub-three-dimensional structure information within the three-dimensional boundary range of the cornea structure is used as the cornea information of the user.

[0052] Optionally, the analysis module is specifically used to:

[0053] Obtain target change video information composed of target pictures played in a play order; the target pictures include position information of the target in the target pictures;

[0054] Based on the sample target change video information and the user's eye gaze information, a gaze tracking algorithm is used to collect the gaze focus position information of each time point when the user stays in each target object picture of the target change video information, and the gaze focus position information of each time point is connected according to the time sequence of each time point to obtain the user's gaze change trajectory.

[0055] Optionally, the analysis module is specifically used to:

[0056] Dividing the sight focus position information of the user at each time point in each target image of the target change video information according to each target image, to obtain the sight focus position information of the user in different target images;

[0057] For each target object image, based on the time points corresponding to the respective gaze focus position information of the user in the target object image and the gaze change trajectory of the user, the sub-sight change trajectory of the user in the target object image is filtered, and based on the respective gaze focus position information of the user in the target object image and the position information of the target object in the target object image, the respective gaze deviation change information of the user in the target object image is calculated;

[0058] Based on the sub-eyeline change trajectory of the user in the target object picture and the each line of sight deviation change information of the user in the target object picture, the sub-eyeball focusing information of the user in the target object picture is determined, and based on the sub-eyeball focusing information of the user in all target object pictures, the eyeball focusing information of the user is determined.

[0059] Optionally, the identification module is specifically configured to:

[0060] Analyzing the user's perception information of each color based on the user's perception information of each color, and determining the user's recognition accuracy of each color based on the user's recognition information of each color;

[0061] For each color, based on the user's perception information of the color and the user's recognition accuracy of the color, the user's sensitivity to the color is calculated using a color sensitivity algorithm, and the user's sensitivity to each color is distributed and arranged according to the order of each color in the spectrum to obtain the user's visual perception spectrum.

[0062] Optionally, the identification module is specifically configured to:

[0063] For each target object picture, identifying a target time point corresponding to a sight line deviation change information of the user that is lower than a deviation change threshold among each sight line deviation change information in the target object picture;

[0064] Calculating the precise focusing time of the user on the target image based on the time points corresponding to the respective sight line deviation change information of the user in the target image and the target time point of the user in the target image;

[0065] In the sub-sight line change trajectories of the user in the target object picture, according to the time sequence of the time points corresponding to the respective sight line deviation change information of the user in the target object picture, the target sight line change trajectories corresponding to all time points before the target time point in each time point of the target object picture are filtered, and based on the target sight line change trajectories, the user's sight focus range on the target object picture is identified;

[0066] The user's vision defect information is analyzed based on the user's precise focusing time in each target object picture, the user's cornea information, and the user's sight focusing range for each target object picture.

[0067] Optionally, the identification module is specifically configured to:

[0068] Obtaining the recognition difficulty of each target image, and normalizing the recognition difficulty of each target image to obtain a weight value of each target image;

[0069] For each target object image, based on the user's corneal information, the user's precise focusing time on the target object image, and the user's sight focusing range in the target object image, a vision defect judgment strategy is used to analyze the user's vision defect range for the target object in the target image and the user's zoom defect information for the target object in the target image;

[0070] Based on the weight values ​​of the target images, weighted processing is performed on the range of the user's vision defect in each target image to obtain the user's comprehensive vision defect range, and based on the weight values ​​of each target image, weighted processing is performed on the user's zoom defect information of the target object in each target image to obtain the user's comprehensive zoom defect information;

[0071] The user's comprehensive vision defect range and the user's comprehensive zoom defect information are used as the user's vision defect information.

[0072] Optionally, the determining module is specifically configured to:

[0073] Based on the user's visual perception, the color ranges corresponding to each normal color perception of the user and the color ranges corresponding to each abnormal color perception are identified, and in each color range of the abnormal color perception, the color range that meets the defect abnormality condition is screened as the user's color vision defect information.

[0074] The above-mentioned visual defect identification method and system method and system obtain the user's eyeball data information and the user's visual perception information, and identify the user's cornea information based on the user's eyeball data information; based on the user's eyeball data information, collect the user's line of sight change trajectory through a gaze tracking algorithm, and determine the user's eye focus information based on the user's line of sight change trajectory; based on the user's visual perception information, identify the user's visual perception spectrum through a spectral perception strategy, and identify the user's color vision defect information based on the user's visual perception spectrum; calculate the user's vision defect information based on the user's cornea information and the user's eye focus information, and determine the user's vision defect information based on the user's vision defect information and the user's color vision defect information. Through the user's eye data information and gaze tracking algorithm, the user's line of sight change trajectory and the user's eye focusing information corresponding to the line of sight change trajectory are identified, thereby analyzing the user's vision defect information. Then, through the user's visual perception information and the spectral perception strategy, the user's color vision defect information is analyzed to identify the user's vision defect information, avoiding the problem that universal methods cannot take into account the individual characteristics of users, thereby improving the accuracy of identifying vision defects of different users. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] FIG1 is a schematic diagram of a flow chart of a method for identifying visual defects in one embodiment;

[0076] FIG2 is a structural block diagram of a visual defect recognition system in one embodiment. DETAILED DESCRIPTION

[0077] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0078] The visual defect recognition method provided in the embodiment of the present application can be applied to a terminal, a server, or a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smart phones, and tablet computers. The server can be implemented as an independent server or a server cluster composed of multiple servers. The terminal uses the user's eye data information and the gaze tracking algorithm to identify the user's line of sight change trajectory and the user's eye focus information corresponding to the line of sight change trajectory, thereby analyzing the user's vision defect information. Then, through the user's visual perception information and the spectral perception strategy, the user's color vision defect information is analyzed to identify the user's visual defect information, thereby avoiding the problem that the universal method cannot take into account the individual characteristics of the user, thereby improving the recognition accuracy of vision defects of different users.

[0079] In one embodiment, as shown in FIG1 , a method for identifying visual defects is provided, which is described by taking the method applied to a terminal as an example, including the following steps:

[0080] Step S101: Acquire user's eyeball data information and user's visual perception information, and identify user's cornea information based on the user's eyeball data information.

[0081] In this embodiment, with user authorization, the terminal uses a 3D scanning device to scan the 3D structural information of the user's eyes. Based on this information, the terminal identifies the user's line of sight and uses this information as the user's eye data. The terminal then obtains the user's visual perception information in response to the user's uploaded information about their perception of various colors in the spectrum. The terminal uses the 3D structural information corresponding to the cornea within the user's 3D eye structural information as the user's corneal information.

[0082] Step S102 : Based on the user's eyeball data information, a gaze tracking algorithm is used to collect the user's line of sight change trajectory, and based on the user's line of sight change trajectory, the user's eyeball focusing information is determined.

[0083] In this embodiment, the terminal collects the user's sub-line of sight change trajectories for each target image based on target change video information composed of multiple target images and a gaze tracking algorithm. The sub-line of sight change trajectories are arranged in the order of playback to obtain the user's line of sight change trajectory. The terminal then analyzes the user's eye focus information based on this line of sight change trajectory, using the CamShift (Continuously Adaptive Mean Shift) visual tracking algorithm. The eye focus information is used to characterize the changes in the user's eye focus when tracking the target in the target image. The specific collection and determination processes will be described in detail later.

[0084] Step S103 : Based on the visual perception information of the user, the visual perception spectrum of the user is identified by using a spectral perception strategy, and based on the visual perception spectrum of the user, the color vision deficiency information of the user is identified.

[0085] In this embodiment, the terminal uses a spectral perception strategy to identify the sensitivity of each color in the user's visual perception information and sorts the sensitivity of each color according to the spectral order, thereby obtaining the user's visual perception spectrum. Based on the user's visual perception spectrum, the terminal then identifies the user's color deficiency information corresponding to the color with which the user has abnormal perception, thereby obtaining the user's color vision deficiency information. The specific identification process will be described in detail later.

[0086] Step S104 : calculating the user's vision defect information based on the user's cornea information and the user's eye focus information, and determining the user's visual defect information based on the user's vision defect information and the user's color vision defect information.

[0087] In this embodiment, the terminal calculates the user's vision impairment information based on the user's corneal information and the user's eye focus information. This vision impairment information includes the user's comprehensive vision impairment range and comprehensive zoom impairment information. The comprehensive vision impairment range corresponds to the area of ​​abnormal vision detection within the user's vision detection range. The terminal then uses this user's vision impairment information and the user's color vision deficiency information as the user's vision impairment information. The specific calculation and determination processes will be described in detail later.

[0088] Based on the above scheme, the user's eye data information and gaze tracking algorithm are used to identify the user's line of sight change trajectory and the user's eye focusing information corresponding to the line of sight change trajectory, thereby analyzing the user's vision defect information. Then, the user's visual perception information and spectral perception strategy are used to analyze the user's color vision defect information, thereby identifying the user's vision defect information. This avoids the problem that universal methods cannot take into account the individual characteristics of users, thereby improving the accuracy of identifying vision defects of different users.

[0089] Optionally, obtaining the user's eye data information and the user's visual perception information includes: collecting the user's eye three-dimensional structure information, and identifying the user's eye sight information based on the user's eye three-dimensional structure information; digitizing the user's three-dimensional structure information and the user's eye sight information to obtain the user's eye data information; collecting the user's perception information of each color in the spectrum, and the user's recognition information of each color in the spectrum, and digitizing the perception information and the recognition information to obtain the user's visual perception information.

[0090] In this embodiment, the terminal uses a 3D scanning device to collect 3D structural information of the user's eyeballs and, based on this information, identifies the user's eye sight information. The user's eye sight information is the vertical line between the focal point of the user's eyes after focusing and the user's facial orientation. The terminal then digitizes the user's 3D structural information and eye sight information to obtain the user's eye data information. The terminal also collects the user's perception information of each color in the spectrum and the user's identification information of each color in the spectrum, and digitizes this information to obtain the user's visual perception information.

[0091] Based on the above scheme, by digitizing the three-dimensional structure information of the eyeball, the eyeball sight information, the recognition information, and the perception information, the user's eyeball data information and the user's visual perception information are obtained, thereby eliminating the dimensional differences between different data and improving the uniformity of each data information.

[0092] Optionally, based on the user's eyeball data information, the user's corneal information is identified, including: based on the user's eyeball three-dimensional structure information, analyzing the three-dimensional boundary range of each eyeball structure in the eyeball three-dimensional structure information through an edge recognition algorithm; within the three-dimensional boundary range of each eyeball structure, screening the three-dimensional boundary range of the corneal structure, and using the sub-three-dimensional structure information within the three-dimensional boundary range of the corneal structure as the user's corneal information.

[0093] In this embodiment, the terminal uses an edge recognition algorithm to analyze the 3D boundary ranges of each eye structure within the user's 3D eye structure information. The terminal then selects the 3D boundary range corresponding to the user's cornea structure from within the 3D boundary ranges of each eye structure. Finally, the terminal uses the sub-3D structure information within the 3D boundary range of the cornea structure as the user's cornea information. The cornea information refers to the user's cornea information. The edge recognition algorithm is a wavelet edge detection algorithm corresponding to a wavelet-based image edge detection method.

[0094] Based on the above solution, the user's corneal information is determined by identifying the three-dimensional boundary range of each eyeball structure in the user's three-dimensional eyeball structure information, thereby improving the accuracy of determining the corneal information.

[0095] Optionally, based on the user's eye data information, the user's line of sight change trajectory is collected through a gaze tracking algorithm, including: obtaining target change video information composed of target object pictures played in a playback order; the target object picture includes the position information of the target object in the target object picture; based on the sample target change video information and the user's eye sight information, the line of sight focus position information of each time point when the user stays in each target object picture in the target change video information is collected through a gaze tracking algorithm, and each line of sight focus position information is connected according to the time sequence of each time point to obtain the user's line of sight change trajectory.

[0096] In this embodiment, the terminal obtains target change video information composed of target object images played in a playback order. The target objects in each target object image are different, and the size, range, and color of each target object are different. The difficulty of identifying each target object is different. The target object image includes the position information of the target object in the target object image. Then, based on the sample target change video information and the user's eye gaze information, the terminal uses a gaze tracking algorithm to collect the gaze focus position information of each time point when the user stays in each target object image in the target change video information, and connects the gaze focus position information according to the time sequence of each time point to obtain the user's gaze change trajectory.

[0097] Based on the above solution, the gaze tracking algorithm is used to identify the gaze focus position information of the user at each time point in each target object picture of the target change video information, thereby improving the accuracy of the determined gaze focus position information.

[0098] Optionally, based on the user's line of sight change trajectory, the user's eye focusing information is determined, including: dividing the line of sight focus position information of each time point when the user stays in each target object picture of the target change video information according to each target object picture, and obtaining the line of sight focus position information of the user in different target object pictures; for each target object picture, based on the time point corresponding to each line of sight focus position information of the user in the target object picture and the user's line of sight change trajectory, filtering the sub-line of sight change trajectory of the user in the target object picture, and calculating the line of sight deviation change information of the user in the target object picture based on the line of sight focus position information of the user in the target object picture and the position information of the target object in the target picture; determining the sub-eye focusing information of the user in the target object picture according to the sub-line of sight change trajectory of the user in the target object picture and the line of sight deviation change information of the user in the target picture, and determining the user's eye focusing information based on the sub-eye focusing information of the user in all target pictures.

[0099] In this embodiment, the terminal divides the user's gaze focus position information at each time point in each target image in the target change video information into different target images, thereby obtaining the user's gaze focus position information in different target images. The gaze focus position information in different target images corresponds to the same two-dimensional coordinate system as the position information of the target in the target image.

[0100] For each target object image, the terminal filters the user's sub-line of sight change trajectory in the target object image based on the time points corresponding to the user's line of sight focus position information in the target object image and the user's line of sight change trajectory. Then, based on the user's line of sight focus position information in the target object image and the position information of the target in the target object image, the terminal calculates the user's line of sight deviation change information in the target object image. The target object position information is the position information corresponding to the outline of the target object. The line of sight deviation change information is the straight-line distance information between the user's line of sight focus position information and the position information of the target in the target object image.

[0101] The terminal determines the user's eye focus information in the target image based on the user's sub-sight line movement trajectory in the target image and the deviation change information of each user's sight line in the target image. Finally, the terminal uses the user's eye focus information in all target images as the user's eye focus information.

[0102] Based on the above scheme, by dividing the gaze change trajectory into sub-gaze change trajectories in each target object picture, the accuracy of the user's gaze change trajectory analysis is improved, and by calculating the user's gaze deviation change information in the target object picture, it is used to represent the user's focus information in each target object picture, thereby improving the recognition of the user's focus information.

[0103] Optionally, based on the user's visual perception information, the user's visual perception spectrum is identified through a spectral perception strategy, including: based on the user's perception information of each color, analyzing the user's perception degree information of each color, and based on the user's identification information of each color, determining the user's identification accuracy of each color; for each color, based on the user's perception degree information of the color and the user's identification accuracy of the color, calculating the user's sensitivity to the color through a color sensitivity algorithm, and distributing and arranging the user's sensitivity to each color according to the order of each color in the spectrum to obtain the user's visual perception spectrum.

[0104] In this embodiment, the terminal determines the user's recognition accuracy for each color based on the user's recognition information for each color. The recognition information is the user's recognition of the color. For example, if the user recognizes red as red, green as cyan, and purple as black, the user's recognition accuracy for red is high, the recognition accuracy for green is medium, and the recognition accuracy for purple is low.

[0105] For each color, the terminal calculates the user's color sensitivity based on the user's color perception information and color recognition accuracy using a color sensitivity algorithm. The color sensitivity algorithm normalizes the user's color recognition accuracy to obtain a color recognition weight. Based on this color recognition weight, the terminal then weights the user's color perception information to determine the user's sensitivity to that color. The terminal then distributes the user's color sensitivity according to the order of each color on the spectrum to obtain the user's visual perception spectrum.

[0106] Based on the above solution, the user's sensitivity to color is determined through the user's color perception information and the user's color recognition accuracy, thereby improving the accuracy of the analysis of the user's sensitivity to various colors.

[0107] Optionally, the user's vision defect information is calculated based on the user's corneal information and the user's eye focusing information, including: for each target object picture, based on identifying the target time point corresponding to the line of sight deviation change information of the user in the target object picture that is lower than the deviation change threshold in the line of sight deviation change information; based on the time point corresponding to each line of sight deviation change information of the user in the target object picture and the target time point of the user in the target object picture, calculating the user's precise focusing time on the target object picture; in the sub-line of sight change trajectory of the user in the target object picture, according to the time sequence of the time points corresponding to each line of sight deviation change information of the user in the target object picture, filtering the target line of sight change trajectories corresponding to all time points before the target time point in each time point of the user in the target object picture, and identifying the user's line of sight focusing range on the target object picture based on the target line of sight change trajectory; analyzing the user's vision defect information based on the user's precise focusing time in each target object picture, the user's corneal information, and the user's line of sight focusing range on each target object picture.

[0108] In this embodiment, for each target image, the terminal selects the target time points corresponding to the user's sight line deviation change information in the target image, from the time points corresponding to the user's sight line deviation change information in the target image, that correspond to sight line deviation change information that is below a deviation change threshold preset in the terminal. The terminal then calculates the user's precise focus time on the target image based on the time points corresponding to the user's sight line deviation change information in the target image and the user's target time point in the target image. The precise focus time is the period between the user's first time point in the target image and the target time point.

[0109] In the sub-line of sight change trajectory of the user in the target object picture, the terminal filters the target line of sight change trajectory corresponding to all time points before the target time point in each time point of the user in the target object picture according to the time sequence of the time points corresponding to the various line of sight deviation change information of the user in the target object picture. Then, based on the target line of sight change trajectory, the terminal identifies the range contained in the target line of sight change trajectory of the user for the target object picture as the line of sight focusing range of the user for the target object picture. Finally, the terminal analyzes the user's vision defect information based on the user's precise focusing time in each target object picture, the user's corneal information, and the user's line of sight focusing range for each target object picture. The specific vision defect analysis process will be described in detail later.

[0110] Based on the above scheme, by finding the target time point, the user's precise focusing time on the target object image and the user's visual focusing range on the target object image are determined, thereby improving the accuracy of analyzing the user's vision defect information, reducing the program calculation amount, and improving the efficiency of analyzing the user's vision defect information.

[0111] Optionally, based on the user's precise focusing time on each target object picture, the user's corneal information, and the user's visual focusing range on each target object picture, the user's vision defect information is analyzed, including: obtaining the recognition difficulty of each target object picture, and normalizing the recognition difficulty of each target object picture to obtain a weight value for each target object picture; for each target object picture, based on the user's corneal information, the user's precise focusing time on the target object picture, and the user's visual focusing range on the target object in the target object picture, through a vision defect judgment strategy, analyzing the user's vision defect range for the target object in the target object picture and the user's zoom defect information on the target object in the target object picture; based on the weight value of each target object picture, weighting the user's vision defect range in each target object picture to obtain the user's comprehensive vision defect range, and based on the weight value of each target object picture, weighting the user's zoom defect information for the target object in each target object picture to obtain the user's comprehensive zoom defect information; and using the user's comprehensive vision defect range and the user's comprehensive zoom defect information as the user's vision defect information.

[0112] In this embodiment, the terminal obtains the recognition difficulty of each target image in response to the recognition difficulty information uploaded by the user. The terminal then normalizes the recognition difficulty of each target image to obtain a weight value for each target image. The weight value represents the recognition ease weight of the target image; the higher the weight, the lower the recognition difficulty.

[0113] For each target image, the user's vision defect range in the target image is analyzed based on the user's corneal information and the user's visual focusing range in the target image. The vision defect range is a two-dimensional position range used to characterize the position information range of the target image that the user incorrectly identifies in the target image. Then, based on the user's corneal information, the user's precise focusing time in the target image, and the user's visual focusing range in the target image, the terminal analyzes the user's zoom defect information on the target object in the target image. The zoom defect information is used to characterize the user's zoom clarity of the target object in the target image. The higher the zoom clarity, the smaller the zoom defect information, and the lower the zoom clarity, the larger the zoom defect information.

[0114] The terminal weights the user's vision impairment range in each target image based on the weight value of each target image to obtain the user's comprehensive vision impairment range. Furthermore, the terminal weights the user's zoom impairment information for each target image based on the weight value of each target image to obtain the user's comprehensive zoom impairment information. Finally, the terminal uses the user's comprehensive vision impairment range and the user's comprehensive zoom impairment information as the user's vision impairment information.

[0115] Based on the above scheme, the terminal analyzes the user's vision defect range in each target object picture and the user's zoom defect information on the target object in each target object picture through a vision defect judgment strategy, and then weightedly processes the vision defect range of each household in each target object picture and the user's zoom defect information on the target object in each target object picture according to the recognition difficulty of each target object picture to obtain the user's comprehensive vision defect range and the user's comprehensive zoom defect information, thereby improving the accuracy of the obtained user's vision defect information.

[0116] Optionally, based on the user's visual perception spectrum, the user's color vision defect information is identified, including: based on the user's visual perception, identifying the color range of each normal color perception corresponding to the user, and the color range of each abnormal color perception, and in the color range of each abnormal color perception, screening the color range that meets the defect abnormality condition as the user's color vision defect information.

[0117] In this embodiment, based on the user's visual perception, the terminal identifies color ranges corresponding to each user's normal color perception and color ranges corresponding to each abnormal color perception. Abnormal color ranges include color ranges whose color sensitivity exceeds a sensitivity threshold preset in the terminal, and color ranges whose color sensitivity falls below the sensitivity threshold preset in the terminal. The terminal then selects, from among the color ranges with abnormal color perception, color ranges whose sensitivity falls below the sensitivity threshold preset in the terminal as information about the user's color vision deficiency.

[0118] Based on the above solution, the user's color vision deficiency information is determined by sensitivity, thereby improving the accuracy of identifying the user's color vision deficiency information.

[0119] It should be understood that, although each step in the flowcharts involved in the above-mentioned embodiments is displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0120] Based on the same inventive concept, embodiments of the present application also provide a visual defect recognition system for implementing the aforementioned visual defect recognition method. The solution provided by this system is similar to the solution described in the aforementioned method. Therefore, the specific limitations in one or more visual defect recognition system embodiments provided below can be found in the limitations of the visual defect recognition method described above and will not be further elaborated here.

[0121] In one embodiment, as shown in FIG2 , a visual defect recognition system is provided, including: an acquisition module 210 , an analysis module 220 , a recognition module 230 , and a determination module 240 , wherein:

[0122] An acquisition module 210 is configured to acquire eyeball data information of a user and visual perception information of the user, and identify corneal information of the user based on the eyeball data information of the user;

[0123] An analysis module 220 is configured to collect a user's gaze change trajectory based on the user's eye data information and a gaze tracking algorithm, and determine the user's eye focus information based on the user's gaze change trajectory;

[0124] an identification module 230 for identifying the user's visual perception spectrum based on the user's visual perception information and using a spectral perception strategy, and identifying the user's color vision deficiency information based on the user's visual perception spectrum;

[0125] The determination module 240 is used to calculate the user's vision defect information based on the user's corneal information and the user's eye focusing information, and determine the user's visual defect information based on the user's vision defect information and the user's color vision defect information.

[0126] Optionally, the acquisition module 210 is specifically configured to:

[0127] Collecting three-dimensional eye structure information of the user, and identifying eye sight information of the user based on the three-dimensional eye structure information of the user;

[0128] digitizing the user's three-dimensional structural information and the user's eye sight information to obtain the user's eye data information;

[0129] The user's perception information of each color in the spectrum and the user's identification information of each color in the spectrum are collected, and the perception information and the identification information are digitized to obtain the user's visual perception information.

[0130] Optionally, the acquisition module 210 is specifically configured to:

[0131] Based on the three-dimensional eye structure information of the user, analyzing the three-dimensional boundary range of each eye structure in the three-dimensional eye structure information by an edge recognition algorithm;

[0132] In the three-dimensional boundary range of each eyeball structure, the three-dimensional boundary range of the cornea structure is screened, and the sub-three-dimensional structure information within the three-dimensional boundary range of the cornea structure is used as the cornea information of the user.

[0133] Optionally, the analysis module 220 is specifically configured to:

[0134] Obtain target change video information composed of target pictures played in a play order; the target pictures include position information of the target in the target pictures;

[0135] Based on the sample target change video information and the user's eye gaze information, a gaze tracking algorithm is used to collect the gaze focus position information of each time point when the user stays in each target object picture of the target change video information, and the gaze focus position information of each time point is connected according to the time sequence of each time point to obtain the user's gaze change trajectory.

[0136] Optionally, the analysis module 220 is specifically configured to:

[0137] Dividing the sight focus position information of the user at each time point in each target image of the target change video information according to each target image, to obtain the sight focus position information of the user in different target images;

[0138] For each target object image, based on the time points corresponding to the respective gaze focus position information of the user in the target object image and the gaze change trajectory of the user, the sub-sight change trajectory of the user in the target object image is filtered, and based on the respective gaze focus position information of the user in the target object image and the position information of the target object in the target object image, the respective gaze deviation change information of the user in the target object image is calculated;

[0139] Based on the sub-eyeline change trajectory of the user in the target object picture and the each line of sight deviation change information of the user in the target object picture, the sub-eyeball focusing information of the user in the target object picture is determined, and based on the sub-eyeball focusing information of the user in all target object pictures, the eyeball focusing information of the user is determined.

[0140] Optionally, the identification module 230 is specifically configured to:

[0141] Analyzing the user's perception information of each color based on the user's perception information of each color, and determining the user's recognition accuracy of each color based on the user's recognition information of each color;

[0142] For each color, based on the user's perception information of the color and the user's recognition accuracy of the color, the user's sensitivity to the color is calculated using a color sensitivity algorithm, and the user's sensitivity to each color is distributed and arranged according to the order of each color in the spectrum to obtain the user's visual perception spectrum.

[0143] Optionally, the identification module 230 is specifically configured to:

[0144] For each target object picture, identifying a target time point corresponding to a sight line deviation change information of the user that is lower than a deviation change threshold among each sight line deviation change information in the target object picture;

[0145] Calculating the precise focusing time of the user on the target object picture based on the time points corresponding to the respective sight line deviation change information of the user in the target object picture and the target time point of the user in the target object picture;

[0146] In the sub-sight line change trajectories of the user in the target object picture, according to the time sequence of the time points corresponding to the respective sight line deviation change information of the user in the target object picture, the target sight line change trajectories corresponding to all time points before the target time point in each time point of the target object picture are filtered, and based on the target sight line change trajectories, the user's sight focus range on the target object picture is identified;

[0147] The user's vision defect information is analyzed based on the user's precise focusing time in each target object picture, the user's cornea information, and the user's sight focusing range for each target object picture.

[0148] Optionally, the identification module 230 is specifically configured to:

[0149] Obtaining the recognition difficulty of each target image, and normalizing the recognition difficulty of each target image to obtain a weight value of each target image;

[0150] For each target object image, based on the user's corneal information, the user's precise focusing time on the target object image, and the user's sight focusing range in the target object image, a vision defect judgment strategy is used to analyze the user's vision defect range for the target object in the target image and the user's zoom defect information for the target object in the target image;

[0151] Based on the weight values ​​of the target images, weighted processing is performed on the range of the user's vision defect in each target image to obtain the user's comprehensive vision defect range, and based on the weight values ​​of each target image, weighted processing is performed on the user's zoom defect information of the target object in each target image to obtain the user's comprehensive zoom defect information;

[0152] The user's comprehensive vision defect range and the user's comprehensive zoom defect information are used as the user's vision defect information.

[0153] Optionally, the determining module 240 is specifically configured to:

[0154] Based on the user's visual perception, the color ranges corresponding to each normal color perception of the user and the color ranges corresponding to each abnormal color perception are identified, and in each color range of the abnormal color perception, the color range that meets the defect abnormality condition is screened as the user's color vision defect information.

[0155] Each module in the visual defect recognition device described above can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0156] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0157] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0158] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of each technical feature in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0159] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for identifying visual defects, characterized in that: The method comprises: Acquire eyeball data information of a user and visual perception information of the user, and identify corneal information of the user based on the eyeball data information of the user; Based on the eyeball data information of the user, using a gaze tracking algorithm, collecting the user's sight line movement trajectory, and determining the user's eyeball focusing information based on the user's sight line movement trajectory; Based on the visual perception information of the user, identifying the visual perception spectrum of the user through a spectral perception strategy, and identifying the color vision deficiency information of the user based on the visual perception spectrum of the user; Based on the user's cornea information and the user's eye focus information, the user's vision defect information is calculated, and based on the user's vision defect information and the user's color vision defect information, the user's visual defect information is determined.

2. The method according to claim 1, characterized in that The obtaining of the user's eyeball data information and the user's visual perception information includes: Collecting three-dimensional eye structure information of a user, and identifying eye sight information of the user based on the three-dimensional eye structure information of the user; Processing the three-dimensional structure information of the user and the eye sight information of the user into data to obtain the eye data information of the user; The user's perception information of each color in the spectrum and the user's identification information of each color in the spectrum are collected, and the perception information and the identification information are processed in a digital manner to obtain the user's visual perception information.

3. The method according to claim 2, characterized in that The identifying the cornea information of the user based on the eyeball data information of the user includes: Based on the three-dimensional structure information of the user's eyeball, analyzing the three-dimensional boundary range of each eyeball structure in the three-dimensional structure information of the eyeball by an edge recognition algorithm; In the three-dimensional boundary range of each eyeball structure, the three-dimensional boundary range of the corneal structure is screened, and the sub-three-dimensional structure information within the three-dimensional boundary range of the corneal structure is used as the corneal information of the user.

4. The method according to claim 2, characterized in that: The collecting the user's sight line change trajectory based on the user's eyeball data information through a gaze tracking algorithm includes: Obtain target change video information composed of target object pictures played in a play order; the target object picture includes position information of the target object in the target picture; Based on the sample target change video information and the user's eye gaze information, a gaze tracking algorithm is used to collect the gaze focus position information of each time point when the user stays in each target object picture of the target change video information, and the gaze focus position information of each time point is connected according to the time sequence of each time point to obtain the user's gaze change trajectory.

5. The method according to claim 4, characterized in that The determining the eye focus information of the user based on the eye line movement trajectory of the user includes: The sight focus position information of each time point at which the user stays in each target object picture of the target change video information is divided according to each target object picture to obtain each sight focus position information of the user in different target object pictures; For each target object picture, based on the time point corresponding to each line of sight focus position information of the user in the target object picture and the line of sight change trajectory of the user, the sub-line of sight change trajectory of the user in the target object picture is filtered, and based on each line of sight focus position information of the user in the target object picture and the position information of the target object in the target object picture, each line of sight deviation change information of the user in the target object picture is calculated; Based on the sub-eyeline change trajectory of the user in the target object picture and the eyeline deviation change information of the user in the target object picture, the sub-eye focusing information of the user in the target object picture is determined, and based on the sub-eye focusing information of the user in all target object pictures, the eye focusing information of the user is determined.

6. The method according to claim 2, characterized in that The identifying the visual perception spectrum of the user through a spectrum perception strategy based on the visual perception information of the user includes: Based on the user's perception information of each color, analyzing the user's perception degree information of each color, and based on the user's recognition information of each color, determining the user's recognition accuracy of each color; For each color, based on the user's perception information of the color and the user's recognition accuracy of the color, the user's sensitivity to the color is calculated through a color sensitivity algorithm, and the user's sensitivity to each color is sorted according to the order of each color in the spectrum. The user's visual perception spectrum is obtained by distributing and arranging the degrees.

7. The method according to claim 5, characterized in that The calculating the user's vision defect information based on the user's cornea information and the user's eye focus information includes: For each target object picture, based on identifying a target time point corresponding to a sight line deviation change information of the user that is lower than a deviation change threshold in each sight line deviation change information in the target object picture; Calculating the precise focusing time of the user on the target object picture based on the time points corresponding to each line of sight deviation change information of the user in the target object picture and the target time point of the user in the target object picture; In the sub-sight line change trajectory of the user in the target object picture, according to the time sequence of the time points corresponding to the sight line deviation change information of the user in the target object picture, the target sight line change trajectory corresponding to all time points before the target time point in each time point of the user in the target object picture is screened, and based on the target sight line change trajectory, the sight line focusing range of the user on the target object picture is identified; The user's vision defect information is analyzed based on the user's precise focusing time in each target object picture, the user's cornea information, and the user's sight focusing range for each target object picture.

8. The method according to claim 1, characterized in that: The analyzing the user's vision defect information based on the user's precise focusing time in each target object picture, the user's cornea information, and the user's sight focusing range for each target object picture includes: Obtaining the recognition difficulty of each target object image, and normalizing the recognition difficulty of each target object image to obtain a weight value of each target object image; For each target image, based on the user's corneal information, the user's precise focusing time on the target image, and the user's sight focusing range on the target image, a vision defect judgment strategy is used to analyze the user's vision defect range for the target object in the target image and the user's zoom defect information for the target object in the target image; Based on the weight values ​​of the target object pictures, weighted processing is performed on the vision defect range of the user in each target object picture to obtain the comprehensive vision defect range of the user, and based on the weight values ​​of the target object pictures, weighted processing is performed on the zoom defect information of the target object of each target object picture by the user to obtain the comprehensive zoom defect information of the user; The comprehensive vision defect range of the user and the comprehensive zoom defect information of the user are used as the vision defect information of the user.

9. The method according to claim 7, characterized in that: The identifying the color vision deficiency information of the user based on the visual perception spectrum of the user includes: Based on the visual perception of the user, the color ranges of normal color perception and abnormal color perception corresponding to the user are identified, and in each color range of abnormal color perception, the color range that meets the defect abnormality condition is screened as the color vision defect information of the user.

10. A visual defect recognition system, characterized in that: The system comprises: An acquisition module, used to acquire eyeball data information of a user and visual perception information of the user, and identify corneal information of the user based on the eyeball data information of the user; An analysis module, configured to collect the user's sight line change trajectory based on the user's eyeball data information and through a gaze tracking algorithm, and determine the user's eyeball focusing information based on the user's sight line change trajectory; an identification module, configured to identify the visual perception spectrum of the user through a spectrum perception strategy based on the visual perception information of the user, and to identify the color vision deficiency information of the user based on the visual perception spectrum of the user; A determination module is used to calculate the user's vision defect information based on the user's cornea information and the user's eye focusing information, and to determine the user's visual defect information based on the user's vision defect information and the user's color vision defect information.

Images