Paracenter fixation detection method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a para-center fixation detection method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring an eye fundus image of a to-be-detected person; determining macular center position information corresponding to the eye fundus image according to the eye fundus image of the to-be-detected person; according to the macula lutea center position information and the preset macula lutea fixation area, the para-center fixation type corresponding to the fundus image is determined, through the quantification technology and the visual calculation technology, analysis of the fundus image is rapidly completed, the examination time is shortened, the diagnosis efficiency is improved, whether a patient has para-center fixation or not can be more accurately judged, and the patient experience is improved. And errors caused by subjective judgment are reduced.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a paracentral gaze detection method, device, electronic device and storage medium. Background Art

[0002] As people's living standards improve, they pay more and more attention to their eyes. The diagnosis of eyes can be judged through doctors' subjective diagnosis and some routine ophthalmic examinations, such as vision tests, visual field tests, etc. In this way, misdiagnosis or detection deviations may occur. How to improve the diagnostic results of fundus images is an urgent problem that needs to be solved. Summary of the invention

[0003] Some embodiments of the present application aim to provide a paracentral fixation detection method, device, electronic device and storage medium. Through the technical solution of the embodiments of the present application, a fundus image of a person to be tested is obtained; based on the fundus image of the person to be tested, the macular center position information corresponding to the fundus image is determined; based on the macular center position information and a preset macular fixation area, the paracentral fixation type corresponding to the fundus image is determined, and through quantification technology and visual calculation technology, the analysis and diagnosis of the fundus image are quickly completed, the inspection time is shortened, the diagnostic efficiency is improved, and it can be more accurately determined whether the patient has paracentral fixation, reducing the error caused by subjective judgment.

[0004] In a first aspect, some embodiments of the present application provide a paracentral gaze detection method, comprising:

[0005] Acquire a fundus image of the person to be tested;

[0006] According to the fundus image of the person to be tested, determining the macular center position information corresponding to the fundus image;

[0007] A paracentral fixation type corresponding to the fundus image is determined according to the macular center position information and a preset macular fixation area.

[0008] Some embodiments of the present application identify the collected fundus images, determine the macula center position information in the fundus images, and then compare it with the preset macular fixation area to determine the paracentral fixation type of the fundus image. In this way, the analysis and diagnosis of the fundus images can be completed quickly, the examination time can be shortened, the diagnostic efficiency can be improved, and it can be determined more accurately whether the patient has paracentral fixation, reducing the errors caused by subjective judgment.

[0009] Optionally, the preset macular fixation area is obtained by:

[0010] obtaining sample fundus images of emmetropic persons;

[0011] According to a preset positioning algorithm, a preset macular fixation area in the sample fundus image is determined, wherein the preset positioning algorithm at least includes a pre-trained positioning model, or a positioning algorithm obtained based on machine learning or computer vision algorithm.

[0012] Some embodiments of the present application collect sample fundus images of emmetropic persons and use a preset positioning algorithm to determine a preset macular fixation area in the fundus image, i.e., a standard macular fixation area, which can be used for fundus judgment of any person to improve the accuracy of judgment.

[0013] Optionally, obtaining a sample fundus image of an emmetropic person includes:

[0014] acquiring a plurality of initial sample fundus images of a plurality of emmetropic persons;

[0015] The multiple initial sample fundus images are averaged to obtain the sample fundus images of the emmetropia personnel. Some embodiments of the present application acquire fundus images of multiple persons multiple times and then obtain the average value to acquire the sample fundus images of the emmetropia personnel, thereby improving the accuracy of sample acquisition.

[0016] Optionally, determining a paracentral fixation type corresponding to the fundus image according to the macular center position information and a preset macular fixation area includes:

[0017] Calculate the measurement distance and / or the field angle from the center of the macula to the center of the preset macula fixation area;

[0018] The paracentral fixation type corresponding to the fundus image is determined according to the measurement distance and / or the field of view angle and the size of the preset value.

[0019] In some embodiments of the present application, by calculating the measured distance and / or the field of view angle from the center of the macula to the center of a preset macular fixation area, the paracentral fixation type of the fundus image is determined according to the size of the distance and / or the size of the field of view angle, thereby enabling the fundus image to be quickly identified.

[0020] Optionally, the paracentral fixation types include at least macular-central fixation, paracentral fixation, paramacular fixation, peripheral fixation and wandering fixation.

[0021] In a second aspect, some embodiments of the present application provide a paracentral gaze detection device, comprising:

[0022] An acquisition module, used for acquiring fundus images of the person to be tested;

[0023] A determination module, used to determine the macular center position information corresponding to the fundus image of the person to be tested according to the fundus image of the person to be tested;

[0024] A classification module is used to determine the paracentral fixation type corresponding to the fundus image according to the macular center position information and a preset macular fixation area.

[0025] Some embodiments of the present application identify the collected fundus images, determine the macula center position information in the fundus images, and then compare it with the preset macular fixation area to determine the paracentral fixation type of the fundus image. In this way, the analysis and diagnosis of the fundus images can be completed quickly, the examination time can be shortened, the diagnostic efficiency can be improved, and it can be determined more accurately whether the patient has paracentral fixation, reducing the errors caused by subjective judgment.

[0026] Optionally, the device further comprises an establishing module, wherein the establishing module is configured to:

[0027] obtaining sample fundus images of emmetropic persons;

[0028] According to a preset positioning algorithm, a preset macular fixation area in the sample fundus image is determined, wherein the preset positioning algorithm at least includes a pre-trained positioning model, or a positioning algorithm obtained based on machine learning or computer vision algorithm.

[0029] Some embodiments of the present application collect sample fundus images of emmetropic persons and use a preset positioning algorithm to determine a preset macular fixation area in the fundus image, i.e., a standard macular fixation area, which can be used for fundus judgment of any person to improve the accuracy of judgment.

[0030] Optionally, the establishing module is used to:

[0031] acquiring a plurality of initial sample fundus images of a plurality of emmetropic persons;

[0032] The multiple initial sample fundus images are averaged to obtain the sample fundus images of the emmetropia personnel. Some embodiments of the present application acquire fundus images of multiple persons multiple times and then obtain the average value to acquire the sample fundus images of the emmetropia personnel, thereby improving the accuracy of sample acquisition.

[0033] Optionally, the classification module is used to:

[0034] Calculate the measurement distance and / or the field angle from the center of the macula to the center of the preset macula fixation area;

[0035] The paracentral fixation type corresponding to the fundus image is determined according to the measurement distance and / or the field of view angle and the size of the preset value.

[0036] In some embodiments of the present application, by calculating the measured distance and / or the field of view angle from the center of the macula to the center of the preset macular fixation area, the paracentral fixation type of the fundus image is determined according to the size of the distance and / or the size of the field of view angle, thereby enabling the fundus image to be quickly identified.

[0037] Optionally, the paracentral fixation types include at least macular-central fixation, paracentral fixation, paramacular fixation, peripheral fixation and wandering fixation.

[0038] In a third aspect, some embodiments of the present application provide an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, the para-central gaze detection method as described in any embodiment of the first aspect can be implemented.

[0039] In a fourth aspect, some embodiments of the present application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, can implement the para-central gaze detection method as described in any embodiment of the first aspect.

[0040] In a fifth aspect, some embodiments of the present application provide a computer program product, comprising a computer program, wherein the computer program, when executed by a processor, can implement the para-central gaze detection method as described in any embodiment of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of some embodiments of the present application, the drawings required for use in some embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 A schematic diagram of a flow chart of a paracentral gaze detection method provided in an embodiment of the present application;

[0043] Figure 2 A schematic diagram of the structure of a paracentral gaze detection device provided in an embodiment of the present application;

[0044] Figure 3 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The technical solutions in some embodiments of the present application will be described below in conjunction with the drawings in some embodiments of the present application.

[0046] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0047] As people's living standards improve, they pay more and more attention to their eyes. The diagnosis of eyes can be determined through the doctor's subjective diagnosis and some routine ophthalmic examinations, such as vision test, visual field test, etc. In this way, misdiagnosis or detection deviation may occur. How to improve the diagnostic results of fundus images is a problem that urgently needs to be solved. In view of this, some embodiments of the present application provide a paracentral fixation detection method, which includes obtaining a fundus image of a person to be tested; determining the macular center position information corresponding to the fundus image according to the fundus image of the person to be tested; determining the paracentral fixation type corresponding to the fundus image according to the macular center position information and a preset macular fixation area, by quickly completing the analysis and diagnosis of the fundus image, shortening the inspection time, and improving the diagnostic efficiency, it can more accurately determine whether the patient has paracentral fixation and reduce the error caused by subjective judgment.

[0048] like Figure 1 As shown, an embodiment of the present application provides a paracentral gaze detection method, the method comprising:

[0049] S101, obtaining a fundus image of a person to be tested;

[0050] Specifically, a fundus image of the person to be tested is obtained by a fundus camera, and the fundus camera transmits the collected fundus image to a terminal device, wherein the collected fundus image may be a 45° fundus image, or a 60°, 80°, 120° fundus image, or a wide-angle fundus image or a fundus image with other field angles, or even a fundus image of other modalities, and the fundus image may be shot with the optic disc as the center, or may be shot with the macula center as the center, or an image of other eye positions;

[0051] The fundus image includes a fundus color photograph obtained by a fundus camera, an optical coherence tomography (OCT) image, and a fluorescein fundus angiography (FFA) image, which is not specifically limited in the embodiments of the present application.

[0052] The fundus camera in the embodiment of the present application can be an ordinary camera or a camera that can identify amblyopia, that is, the amblyopia area is projected onto the camera. In other words, the generated standard macular fixation area logo can be superimposed and displayed on the camera, for example, it can be displayed by clicking or fixed.

[0053] S102, determining the macular center position information corresponding to the fundus image according to the fundus image of the person to be tested;

[0054] Specifically, after the terminal device obtains the fundus image of the person to be tested, the basic structure of the fundus image includes: blood vessels (arteries and veins), optic disc, optic cup, and macula. A preset positioning algorithm is used to locate and identify the macula in the fundus image to obtain the position of the macula in the fundus, and then determine the macula center position information based on the macula position.

[0055] Among them, the macula is located in the center of the retina and is the most sensitive area for vision. The cones responsible for vision and color vision are distributed in this area. Therefore, any lesions involving the macula will cause a significant decrease in central vision, dark and deformed vision, etc. The macula is located 0.35 cm temporally and slightly below the optic disc. It is in the optical center of the human eye and is the projection point of the visual axis. The macula is rich in lutein and is darker than the surrounding retina. There is a depression in the center of the macula, called the fovea, which is the area with the sharpest vision. The fovea is the area with the sharpest vision on the retina. Light converges here after entering the eyeball. It is closely related to the clarity, acuity, color vision and accuracy of the human eye.

[0056] In the embodiment of the present application, a preset positioning algorithm is used to locate and identify the macula in the fundus image of the person to be tested, wherein the preset positioning algorithm at least includes a pre-trained positioning model, or is based on a machine vision algorithm, and the pre-trained positioning model is obtained based on machine learning network training, and the machine learning model includes a convolutional neural network model, a recurrent neural network model and other network models, which are not specifically limited in the embodiment of the present application. The machine vision-based algorithm includes an image segmentation algorithm, a feature extraction algorithm and a target detection algorithm, and the specific algorithm can be set according to actual needs, which is not specifically limited in the embodiment of the present application.

[0057] S103: Determine a paracentral fixation type corresponding to the fundus image according to the macula center position information and a preset macula fixation area.

[0058] Specifically, a preset macular fixation area is pre-stored on the terminal device, and the preset macular fixation area is obtained by identifying the fundus image of the emmetropia person. The terminal device collects the fundus image of any person in real time, identifies the fundus image, obtains the macular center position information of the fundus image, compares the macular center position information with the preset macular fixation area, determines the relative position of the macular center position and the preset macular fixation area, and then obtains the paracentral fixation type of the fundus image.

[0059] Some embodiments of the present application identify the collected fundus images, determine the macula center position information in the fundus images, and then compare it with the preset macular fixation area to determine the paracentral fixation type of the fundus image. In this way, the analysis and diagnosis of the fundus images can be completed quickly, the examination time can be shortened, the diagnostic efficiency can be improved, and it can be determined more accurately whether the patient has paracentral fixation, reducing the errors caused by subjective judgment.

[0060] Another embodiment of the present application further supplements the paracentral gaze detection method provided in the above embodiment.

[0061] Optionally, the preset macular fixation area is obtained by:

[0062] obtaining sample fundus images of emmetropic persons;

[0063] Specifically, the terminal device can collect multiple sample fundus images of emmetropia personnel, and perform mean processing on the multiple sample fundus images to obtain sample fundus images. The emmetropia personnel can be one person or multiple persons, without specific limitation.

[0064] According to a preset positioning algorithm, a preset macular fixation area in the sample fundus image is determined, wherein the preset positioning algorithm at least includes a pre-trained positioning model, or a positioning algorithm obtained based on a machine vision algorithm.

[0065] Specifically, the terminal device processes the acquired sample fundus image, that is, extracts features from the sample fundus image to obtain a feature vector corresponding to the sample fundus image, inputs the feature vector into a preset trained positioning model or a positioning algorithm based on a machine vision algorithm, locates the macula in the sample fundus image, and obtains the macular fixation area, that is, the preset macular fixation area, which is also the standard macular fixation area.

[0066] In the embodiment of the present application, the fundus image of the emmetropia person is first identified to obtain a preset macular fixation area. The emmetropia calibration is to obtain a standard macular fixation area. For any person, only a paracentral test is required. After obtaining the fundus image of the emmetropia person, a machine learning model or computer vision can be used to locate the macula center position. The specific method is not limited in this application.

[0067] Some embodiments of the present application collect sample fundus images of emmetropic persons and use a preset positioning algorithm to determine a preset macular fixation area in the fundus image, i.e., a standard macular fixation area, which can be used for fundus judgment of any person to improve the accuracy of judgment.

[0068] Optionally, obtaining a sample fundus image of an emmetropic person includes:

[0069] acquiring a plurality of initial sample fundus images of a plurality of emmetropic persons;

[0070] A plurality of initial sample fundus images are averaged to obtain sample fundus images of emmetropes.

[0071] Some embodiments of the present application acquire fundus images of multiple persons for multiple times and then calculate the average value to obtain sample fundus images of emmetropia persons, thereby improving the accuracy of sample acquisition.

[0072] Optionally, determining a paracentral fixation type corresponding to the fundus image according to the macular center position information and a preset macular fixation area includes:

[0073] Calculate the measured distance and / or the field angle from the center of the macula to the center of the preset macular fixation area;

[0074] The paracentral fixation type corresponding to the fundus image is determined according to the measurement distance and / or the field of view angle and the size of the preset value.

[0075] Specifically, as an optional implementation, the terminal device can calculate the measured distance from the center position of the macula to the center of a preset macular fixation area based on the center position of the macula in the fundus image of the person to be tested, and judge the measured distance. If the para-central fixation type corresponding to the fundus image is judged based on the size of the measured distance, for example, if the measured distance is less than the first preset distance, the para-central fixation type of the fundus image is determined to be para-central fixation; if the measured distance is greater than the first preset distance and less than the second preset distance, the para-central fixation type of the fundus image is determined to be para-macular fixation; if the measured distance is greater than the second preset distance and less than the third preset distance, the para-central fixation type of the fundus image is determined to be peripheral fixation; if the measured distance is greater than the third preset distance, the para-central fixation type of the fundus image is determined to be wandering fixation, wherein the first preset distance, the second preset distance, and the third preset distance can be set according to the situation and are not limited in the embodiments of the present application.

[0076] As another optional implementation, the terminal device obtains the field of view angle corresponding to the fundus image of the person to be tested, compares the field of view angle with the preset field of view angle, and calculates the difference between the field of view angle and the preset field of view angle. If the difference is less than the first preset angle difference, the para-central fixation type of the fundus image is determined to be para-central fixation; if the difference is greater than the first preset angle difference and less than the second preset angle difference, the para-central fixation type of the fundus image is determined to be para-macular fixation; if the difference is greater than the second preset angle difference and less than the third preset angle difference, the para-central fixation type of the fundus image is determined to be peripheral fixation; if the difference is greater than the third preset angle difference, the para-central fixation type of the fundus image is determined to be wandering fixation; wherein, the first preset angle difference, the second preset angle difference, and the third preset angle difference can be set according to actual needs and are not specifically limited in the present application.

[0077] In summary, the embodiments of the present application calculate the measured distance and / or the field of view angle from the center of the macula to the center of the preset macular fixation area, and determine the paracentral fixation type corresponding to the fundus image according to the measured distance and / or the field of view angle and the size of the preset value. In the specific implementation process, you can choose to calculate only the test distance, or only the field of view angle, or both at the same time, which can be set as needed.

[0078] Specifically, the gaze properties of the amblyopic eye can be divided into the following three categories:

[0079] Central fixation: fixation is at the center of the fovea;

[0080] Paracentral fixation: the fixation point is offset from the fovea;

[0081] Wandering gaze: There is no fixed gaze point, that is, the gaze wanders.

[0082] Further subdivision, paracentral fixation can be divided into the following three types:

[0083] Parafoveal fixation: fixation point is near the fovea;

[0084] Paramacular fixation: fixation is in the macular area outside the fovea;

[0085] Peripheral fixation: fixation on retinal locations outside the macula.

[0086] The terminal device obtains fundus camera parameters, which include field of view angle. The distance corresponding to a 1° field of view angle on the fundus image is calculated based on the field of view angle of the fundus camera and recorded as the unit distance. A standard preset macular fixation area is generated based on the unit distance.

[0087] The standard preset macular areas include: a first area, i.e., a macular central fixation area with the macula as the center and a unit distance as a radius; a second area, i.e., a para-central fixation area with the first area as the center and twice the unit distance as a radius; a third area, i.e., a para-macular fixation area with the second area as the center and three times the unit distance as a radius. The shapes of the above-mentioned first, second and third areas are preferably regular shapes, such as circles, and those skilled in the art may also set them to other shapes.

[0088] When the terminal device detects the fundus image, if the gaze point falls on the center of the macula, it is central macular gaze, indicating that the patient's gaze point is stable and there is no amblyopia; if the gaze point falls outside the center of the macula and is within the first area, it is paracentral gaze, indicating that the patient has paracentral gaze, which is a manifestation of amblyopia; if the gaze point is within the second area, it is paramacular gaze, indicating that the patient has paramacular gaze, which is a manifestation of amblyopia and the severity of amblyopia is greater than that of paracentral gaze; if the gaze point is within the third area, it is peripheral gaze, indicating that the patient has peripheral gaze, which is a manifestation of amblyopia and the severity of amblyopia is greater than that of paramacular gaze, and the treatment is difficult; if the gaze point is outside the third area, it is wandering gaze, indicating that the patient has wandering gaze, which is a manifestation of amblyopia and the severity of amblyopia is greater than that of peripheral gaze, and the treatment is difficult.

[0089] That is to say, normal people use the center of the macula (fovea) of the fundus retina to focus on the target. Therefore, normal gaze is called central gaze. For various reasons, the eyes do not use the center of the macula to focus on the target, but use one or more parts outside the center of the macula to focus on the target, which is abnormal gaze.

[0090] In some embodiments of the present application, by calculating the measured distance and / or the field of view angle from the center of the macula to the center of a preset macular fixation area, the paracentral fixation type of the fundus image is determined according to the size of the distance and / or the size of the field of view angle, thereby enabling the fundus image to be quickly identified.

[0091] In the embodiment of the present application, the paracentral gaze can also be detected in reverse, and the fundus camera can be changed, that is, the eyes need to look at a point or a projection of an image when taking the fundus image.

[0092] The embodiments of the present application improve diagnostic accuracy. Through automated image analysis technology, it can more accurately determine whether the patient has paracentral fixation and reduce errors caused by subjective judgment. The automated method can quickly complete the analysis and diagnosis of fundus images, shorten the examination time, and improve diagnostic efficiency. It can reduce the number of examinations required by patients, reduce the burden on patients, and improve patients' medical experience. It can generate detailed diagnostic reports to provide doctors with a scientific basis, assist clinical decision-making, and improve treatment effects.

[0093] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any combination without conflict, and this application is not limited thereto.

[0094] Another embodiment of the present application provides a paracentral gaze detection device, which is used to execute the paracentral gaze detection method provided in the above embodiment.

[0095] like Figure 2 , which is a schematic diagram of the structure of a paracentral gaze detection device provided in an embodiment of the present application. The paracentral gaze detection device comprises an acquisition module 401, a determination module 402 and a classification module 403, wherein:

[0096] The acquisition module 401 is used to acquire the fundus image of the person to be tested;

[0097] The determination module 402 is used to determine the macular center position information corresponding to the fundus image according to the fundus image of the person to be tested;

[0098] The classification module 403 is used to determine the paracentral fixation type corresponding to the fundus image according to the macula center position information and the preset macula fixation area.

[0099] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0100] Some embodiments of the present application identify the collected fundus images, determine the macula center position information in the fundus images, and then compare it with the preset macular fixation area to determine the paracentral fixation type of the fundus image. In this way, the analysis and diagnosis of the fundus images can be completed quickly, the examination time can be shortened, the diagnostic efficiency can be improved, and it can be determined more accurately whether the patient has paracentral fixation, reducing the errors caused by subjective judgment.

[0101] Another embodiment of the present application further supplements the paracentral gaze detection device provided in the above embodiment.

[0102] Optionally, the device further comprises an establishing module, the establishing module being configured to:

[0103] obtaining sample fundus images of emmetropic persons;

[0104] According to a preset positioning algorithm, a preset macular fixation area in the sample fundus image is determined, wherein the preset positioning algorithm at least includes a pre-trained positioning model, or a positioning algorithm obtained based on machine learning or computer vision algorithm.

[0105] Some embodiments of the present application collect sample fundus images of emmetropic persons and use a preset positioning algorithm to determine a preset macular fixation area in the fundus image, i.e., a standard macular fixation area, which can be used for fundus judgment of any person to improve the accuracy of judgment.

[0106] Optionally, build modules for:

[0107] acquiring a plurality of initial sample fundus images of a plurality of emmetropic persons;

[0108] Performing mean processing on multiple initial sample fundus images to obtain sample fundus images of emmetropia personnel. Some embodiments of the present application acquire fundus images of multiple persons multiple times and then obtain the average value to acquire sample fundus images of emmetropia personnel, thereby improving the accuracy of sample acquisition.

[0109] Optionally, a classification module for:

[0110] Calculate the measured distance and / or the field angle from the center of the macula to the center of the preset macular fixation area;

[0111] The paracentral fixation type corresponding to the fundus image is determined according to the measurement distance and / or the field of view angle and the size of the preset value.

[0112] Some embodiments of the present application calculate the measured distance and / or field of view angle from the center of the macula to the center of a preset macular fixation area, and determine the paracentral fixation type of the fundus image based on the distance and / or field of view angle, thereby enabling rapid identification of the fundus image.

[0113] Optionally, the paracentral fixation types include at least macular-central fixation, paracentral fixation, paramacular fixation, peripheral fixation and wandering fixation.

[0114] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0115] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any combination without conflict, and this application is not limited thereto.

[0116] The embodiments of the present application further provide a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the operation of the method corresponding to any embodiment of the paracentral gaze detection method provided in the above embodiments can be implemented.

[0117] An embodiment of the present application further provides a computer program product, wherein the computer program product includes a computer program, wherein when the computer program is executed by a processor, the operation of the method corresponding to any embodiment of the paracentral gaze detection method provided in the above embodiments can be implemented.

[0118] like Figure 3 As shown, some embodiments of the present application provide an electronic device 500, which includes: a memory 510, a processor 520, and a computer program stored in the memory 510 and executable on the processor 520, wherein the processor 520 can implement a method of any embodiment included in the above-mentioned para-central gaze detection method when reading the program from the memory 510 through a bus 530 and executing the program.

[0119] Processor 520 can process digital signals and can include various computing structures, such as complex instruction set computer structure, reduced instruction set computer structure, or a structure that implements a combination of multiple instruction sets. In some examples, processor 520 can be a microprocessor.

[0120] The memory 510 may be used to store instructions executed by the processor 520 or data related to the execution of instructions. These instructions and / or data may include codes for implementing some or all functions of one or more modules described in the embodiments of the present application. The processor 520 of the disclosed embodiment may be used to execute instructions in the memory 510 to implement the method shown above. The memory 510 includes a dynamic random access memory, a static random access memory, a flash memory, an optical memory, or other memory known to those skilled in the art.

[0121] The above are only embodiments of the present application and are not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0122] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0123] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A paracentral gaze detection method, characterized in that: The method comprises: Acquire fundus images of the person to be tested; According to the fundus image of the person to be tested, determining the macular center position information corresponding to the fundus image; A paracentral fixation type corresponding to the fundus image is determined according to the macular center position information and a preset macular fixation area.

2. The paracentral gaze detection method according to claim 1, characterized in that: The preset macular fixation area is obtained by: obtaining sample fundus images of emmetropic persons; According to a preset positioning algorithm, a preset macular fixation area in the sample fundus image is determined, wherein the preset positioning algorithm at least includes a pre-trained positioning model, or a positioning algorithm obtained based on machine learning or computer vision algorithm.

3. The paracentral gaze detection method according to claim 2, characterized in that: The method of obtaining a sample fundus image of an emmetropic person includes: acquiring a plurality of initial sample fundus images of a plurality of emmetropic persons; The plurality of initial sample fundus images are averaged to obtain a sample fundus image of the emmetropic person.

4. The paracentral gaze detection method according to claim 1, characterized in that: The determining, according to the macular center position information and the preset macular fixation area, a paracentral fixation type corresponding to the fundus image comprises: Calculate the measurement distance and / or the field angle from the center of the macula to the center of the preset macula fixation area; The paracentral fixation type corresponding to the fundus image is determined according to the measurement distance and / or the field of view angle and the size of the preset value.

5. The paracentral gaze detection method according to claim 4, characterized in that: The paracentral fixation type includes at least one of macular central fixation, paracentral fixation, paramacular fixation, peripheral fixation and wandering fixation.

6. A paracentral gaze detection device, characterized in that: The device comprises: An acquisition module, used for acquiring fundus images of the person to be tested; A determination module, used to determine the macular center position information corresponding to the fundus image of the person to be tested according to the fundus image of the person to be tested; A classification module is used to determine the paracentral fixation type corresponding to the fundus image according to the macular center position information and a preset macular fixation area.

7. The paracentral gaze detection device according to claim 6, characterized in that: The device also includes a building module, the building module is used to: obtaining sample fundus images of emmetropic persons; According to a preset positioning algorithm, a preset macular fixation area in the sample fundus image is determined, wherein the preset positioning algorithm at least includes a pre-trained positioning model, or a positioning algorithm obtained based on machine learning or computer vision algorithm.

8. The paracentral gaze detection device according to claim 7, characterized in that: The establishment module is used to: acquiring a plurality of initial sample fundus images of a plurality of emmetropic persons; The plurality of initial sample fundus images are averaged to obtain a sample fundus image of the emmetropic person.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor can implement the paracentral gaze detection method described in any one of claims 1 to 5 when executing the program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the program is executed by a processor, the paracentral gaze detection method described in any one of claims 1 to 5 can be implemented.

Images