An image recognition-based visual training method, device, equipment and medium

Abstract

The application discloses a visual training method and device based on image recognition, equipment and medium, belongs to the field of visual training, the method is: through fundus camera collection user's retina image, and the retina image is pretreated, and the macular region image is obtained; the macular region image is identified, and the spatial position coordinates of the fovea are obtained; the retina of the user is stimulated by a preset light source to achieve the purpose of visual training; wherein the preset light template is set on the position corresponding to the spatial position coordinates, so that the fovea is not stimulated by light; in the process of light stimulation, the eyeball movement of the user is tracked in real time, and the light template is moved synchronously based on the eyeball movement, so that the light template continuously blocks the fovea. Therefore, by implementing the application, the accuracy of visual training can be improved and closed-loop control is realized.

Description

Technical Field

[0001] This invention relates to the field of visual training, and more particularly to a visual training method, apparatus, device, and medium based on image recognition. Background Technology

[0002] Visual training (such as afterimage therapy and eccentric fixation training) is a key intervention for improving eccentric fixation amblyopia. Its core principle is to block the fovea (also known as the central fovea, which is a small depression in the center of the retina responsible for providing clear central vision and is the area with the sharpest vision) and precisely stimulate the area around the fovea to guide the user from eccentric fixation back to central fixation, thereby strengthening the function of the fovea and ultimately improving visual acuity and fixation stability.

[0003] However, current devices used for the aforementioned visual training have significant limitations, specifically in the following aspects: Firstly, most existing devices rely heavily on experience and human judgment for foveal localization and stimulus settings. For example, they use a Haidinger brush to guide the user's gaze, with the trainer determining the foveal position based on feedback, or use physical occlusions to avoid irradiation of the central area. These methods are susceptible to the trainer's experience and the user's cooperation (e.g., children or less cooperative users may have distractions leading to inaccurate feedback), easily resulting in large errors in foveal localization, and the operation process is cumbersome. Secondly, although current fundus cameras possess high-resolution imaging capabilities, capturing posterior segment structures such as the retina and macula to provide basic data support for foveal localization, most devices only perform static examinations. They lack both automated recognition and target analysis capabilities for fundus images and dynamic occlusion adjustment and feedback control functions. This prevents current technology from real-time correction of stimulus positions based on the user's eye movements during training, making it difficult to form a closed-loop control system. Summary of the Invention

[0004] This invention provides a visual training method, apparatus, device, and medium based on image recognition, which can improve the accuracy of visual training and achieve closed-loop control.

[0005] This invention provides a visual training method based on image recognition, comprising: Acquire retinal images of the user captured by a fundus camera, and preprocess the retinal images to obtain macular region images; Image recognition is performed on the image of the macular region to obtain the spatial coordinates of the fovea. A corresponding light source is set according to a preset light source wavelength, energy density, and light spot diameter, and the light source is controlled to emit light within a preset illumination time so that the light shines on the user's retina; wherein, a corresponding light template is obtained according to the light spot diameter, and the light template is set at the position corresponding to the spatial coordinates so that the fovea is not stimulated by light. The user's eye movement data is acquired in real time by an infrared eye tracker, and the illumination template is controlled to move synchronously based on the eye movement data so that the illumination template continuously blocks the fovea.

[0006] This invention acquires retinal images of the user using a fundus camera and preprocesses these images to ensure accurate coverage of the macula before visual training, providing a reliable data foundation for subsequent foveal localization and illumination stimulation. Image recognition of the macula allows for precise extraction of the spatial coordinates of the fovea, providing a positional basis for subsequent illumination template occlusion. Illumination stimulation of the user's retina using a preset light source, with the preset illumination template positioned at the corresponding spatial coordinates, ensures that the fovea is not stimulated while the surrounding retina is, effectively inducing negative afterimages and guiding the user from eccentric fixation back to central fixation, achieving the goal of visual training. By tracking the user's eye movements in real time during illumination stimulation and synchronously moving the illumination template based on these movements, the occlusion position of the illumination template can be dynamically corrected, ensuring the accuracy of visual training and achieving closed-loop control. Compared to existing technologies with low foveal localization accuracy and difficulty in meeting the visual training needs of less cooperative users, this application improves the accuracy of visual training and achieves closed-loop control.

[0007] Furthermore, before acquiring the user's retinal image from the fundus camera and preprocessing the retinal image to obtain the macular region image, the method further includes: The user's head position is fixed by a head support structure so that the user can look directly at the viewing window. A gaze target is projected within the viewing window so that the user gazes at the gaze target; wherein the direction of the user's gaze while maintaining the gaze on the gaze target is taken as the initial gaze direction.

[0008] The embodiments of the present invention guide the user's gaze through a head support structure and an observation window, which can help the user stabilize their gaze and provide a reference gaze direction for subsequent eye tracking.

[0009] Further, the step of acquiring the user's retinal image from the fundus camera and preprocessing the retinal image to obtain a macular region image includes: The retinal image is subjected to noise suppression to obtain a first retinal image; The first retinal image is contrast-enhanced to obtain a second retinal image; The macular region is cropped from the second retinal image to obtain a macular region image.

[0010] The embodiments of the present invention, by performing image preprocessing on retinal images, can ensure accurate coverage of the macula region before visual training, providing a reliable data basis for subsequent foveal localization and light stimulation.

[0011] Further, the step of performing image recognition on the macular region image to obtain the spatial coordinates of the fovea includes: Feature extraction and spatial regression are performed on the macular region image to obtain the pixel coordinates of the concave center; Based on the width of the observation window and the imaging resolution width of the fundus camera, the pixel coordinates are linearly converted into spatial position coordinates.

[0012] This invention, through image recognition and coordinate transformation of the macula region image, can accurately extract the spatial coordinates of the fovea, providing a positional basis for subsequent illumination template occlusion.

[0013] Further, the step of acquiring the user's eye movement data collected in real time by the infrared eye tracker and controlling the illumination template to move synchronously based on the eye movement data, so that the illumination template continuously occludes the fovea, includes: Based on real-time eye movement data collected by an infrared eye tracker, the offset of the user's real-time gaze direction compared to the initial gaze direction is calculated; Based on the offset, the light template is moved synchronously by controlling the deflector so that the light template continuously blocks the central concave area.

[0014] This invention, through real-time tracking of the user's eye movements during light stimulation and synchronous movement of the light template based on these eye movements, can dynamically correct the occlusion position of the light template, ensuring the accuracy of visual training and achieving closed-loop control.

[0015] Another embodiment of the present invention provides a vision training device based on image recognition, including: an image acquisition module, an image recognition module, an illumination stimulation module, and an eye tracking module; The image acquisition module is used to acquire retinal images of the user captured by the fundus camera, and to preprocess the retinal images to obtain macular region images; The image recognition module is used to perform image recognition on the macular region image to obtain the spatial coordinates of the fovea. The light stimulation module is used to set a corresponding light source according to a preset light source wavelength, energy density and light spot diameter, and control the light source to emit light within a preset illumination time so that the light shines on the user's retina; wherein, a corresponding light template is obtained according to the light spot diameter, and the light template is set at the position corresponding to the spatial coordinates so that the fovea is not stimulated by light. The eye-tracking module is used to acquire the user's eye movement data collected in real time by the infrared eye tracker, and control the illumination template to move synchronously based on the eye movement data so that the illumination template continuously blocks the fovea.

[0016] Another embodiment of the present invention provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the steps of a visual training method based on image recognition as described in the present invention.

[0017] Another embodiment of the present invention provides a computer-readable storage medium, comprising: a stored computer program, wherein when the computer program is executed, the device on which the computer-readable storage medium is located executes the steps of a visual training method based on image recognition as described in the present invention. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating an embodiment of the image recognition-based visual training method provided by the present invention. Figure 2 This is a schematic diagram of one embodiment of the image recognition-based visual training device provided by the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0021] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0022] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0024] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0025] See Figure 1 To address the problems of low central concave positioning accuracy and difficulty in meeting the visual training needs of users with low cooperation levels in existing technologies, an embodiment of the present invention provides a visual training method based on image recognition, including steps S101 to S104: Step S101: Acquire the user's retinal image using a fundus camera and preprocess the retinal image to obtain a macular region image.

[0026] Specifically, to stabilize the user's gaze and reduce micro-eye movements, before acquiring the user's retinal image via the fundus camera, the process includes: fixing the user's head position using a head support structure so that the user looks directly at the observation window; projecting a gaze target (such as a crosshair, dynamic animation, or product mascot image) into the observation window so that the user gazes at the gaze target; wherein, the direction of the user's gaze while maintaining focus on the gaze target is used as the initial gaze direction. Once the user's eyes are stable, the retinal image is then acquired via the fundus camera.

[0027] To highlight the foveal structure features, the retinal image needs to be preprocessed, including: noise suppression of the retinal image to obtain a first retinal image; contrast enhancement of the first retinal image to obtain a second retinal image; and cropping of the macular region of the second retinal image to obtain a macular region image.

[0028] Step S102: Perform image recognition on the macular region image to obtain the spatial coordinates of the central fovea.

[0029] Specifically, each eye has only one fovea. To accurately determine the location of the fovea in the fundus, a model with fovea localization capabilities (such as the fovea localization module provided by Fundus Image Toolbox) can be used to perform image recognition on the macular region image. This includes: extracting features and performing spatial regression on the macular region image to obtain the pixel coordinates of the fovea; and linearly converting the pixel coordinates into spatial position coordinates based on the width of the viewing window and the imaging resolution width of the fundus camera. Let the pixel coordinates of the fovea be (…). The width of the observation window is ( The imaging resolution width of the fundus camera is ( Then the spatial coordinates of the central concave point ( The following formula can be used for linear conversion: ; .

[0030] Step S103: The user's retina is stimulated by light from a preset light source to achieve the purpose of visual training; wherein, the preset light template is set at the position corresponding to the spatial coordinates so that the fovea is not stimulated by light.

[0031] Specifically, to meet differentiated visual training needs, before stimulating the user's retina with light through a preset light source, the process includes: acquiring preset illumination parameters from the trainer; wherein the illumination parameters include light source wavelength, energy density, light spot diameter, and illumination time; and obtaining a corresponding illumination template based on the light spot diameter. The illumination template is a real optical device, for example, an opaque blocking point set in the center of a circular transparent lens or optical path modulation plate to prevent light stimulation of the fovea; the size of the illumination template can be matched according to the light spot diameter to achieve precise occlusion of the fovea. In addition to illumination parameters, the trainer can also input the user's basic information (such as name, ID number, age, refractive error, and fixation characteristics) and bind it to the user's visual training data for subsequent tracking and management.

[0032] After setting the illumination parameters and illumination template, visual training can begin. Specifically, a corresponding light source is set according to the wavelength, energy density, and spot diameter of the light source. During the illumination period, the user's retina is stimulated by the light source. The preset illumination template is set at the position corresponding to the spatial coordinates to prevent the fovea from being stimulated by light. Through the occlusion of the illumination template, the light source forms a "central occlusion, peripheral illumination" light distribution pattern in the user's retina, effectively inducing the generation of a negative afterimage and guiding the user to gradually return from peripheral fixation to central fixation, thereby achieving the purpose of visual training.

[0033] Step S104: During the illumination stimulation process, the user's eye movements are tracked in real time, and the illumination template is moved synchronously based on the eye movements so that the illumination template continuously blocks the central fovea.

[0034] Specifically, in order to overcome the interference of eye movements on illumination accuracy caused by children and users with low cooperation, closed-loop control can be achieved through eye tracking during the illumination stimulation process. Specifically, based on the eye movement data (such as eye rotation and displacement data) collected in real time by the infrared eye tracker, the offset of the user's real-time gaze direction compared to the initial gaze direction is calculated (which can be expressed by angle or relative optical path coordinates); based on the offset, the illumination template is moved synchronously by controlling the deflector (such as a mechanical fine-tuning device) so that the illumination template continuously blocks the central fovea.

[0035] Optionally, when frequent gaze shifts or prolonged loss of focus are detected, illumination can be automatically paused, and an audio-visual cue can be issued to remind the user to refocus on the target. Simultaneously, compliance indicators (such as the percentage of effective fixation time and the number of gaze shifts) are recorded to provide quantitative data for evaluating the quality of visual training. Furthermore, eye movements can be recorded concurrently during visual training. After training, the eye movements, compliance indicators, and illumination parameters can be compiled into a data report and saved locally or uploaded to the cloud for subsequent evaluation and optimization by trainers.

[0036] This invention employs a fundus camera to acquire retinal images of the user and preprocesses these images to ensure accurate coverage of the macula before visual training, providing a reliable data foundation for subsequent foveal localization and illumination stimulation. Image recognition of the macula allows for precise extraction of the spatial coordinates of the fovea, providing a positional basis for subsequent illumination template occlusion. Illumination stimulation of the user's retina using a preset light source, with the preset illumination template positioned at the corresponding spatial coordinates, ensures that the fovea is not stimulated while the surrounding retina is, effectively inducing negative afterimages and guiding the user from eccentric fixation back to central fixation, thus achieving the goal of visual training. By tracking the user's eye movements in real-time during illumination stimulation and synchronously moving the illumination template based on these movements, the occlusion position of the illumination template can be dynamically corrected, ensuring the accuracy of visual training and achieving closed-loop control.

[0037] Optionally, in this embodiment of the invention, before acquiring the user's retinal image via a fundus camera and preprocessing the retinal image to obtain the macular region image, the method further includes: The user's head position is fixed by a head support structure so that the user can look directly at the viewing window. A gaze target is projected within the viewing window so that the user gazes at the gaze target; wherein the direction of the user's gaze while maintaining the gaze on the gaze target is taken as the initial gaze direction.

[0038] The embodiments of the present invention guide the user's gaze through a head support structure and an observation window, which can help the user stabilize their gaze and provide a reference gaze direction for subsequent eye tracking.

[0039] Optionally, in this embodiment of the invention, the step of acquiring a user's retinal image via a fundus camera and preprocessing the retinal image to obtain a macular region image includes: The retinal image is subjected to noise suppression to obtain a first retinal image; The first retinal image is contrast-enhanced to obtain a second retinal image; The macular region is cropped from the second retinal image to obtain a macular region image.

[0040] The embodiments of the present invention, by performing image preprocessing on retinal images, can ensure accurate coverage of the macula region before visual training, providing a reliable data basis for subsequent foveal localization and light stimulation.

[0041] Optionally, in this embodiment of the invention, the step of performing image recognition on the macular region image to obtain the spatial coordinates of the fovea includes: Feature extraction and spatial regression are performed on the macular region image to obtain the pixel coordinates of the concave center; Based on the width of the observation window and the imaging resolution width of the fundus camera, the pixel coordinates are linearly converted into spatial position coordinates.

[0042] This invention, through image recognition and coordinate transformation of the macula region image, can accurately extract the spatial coordinates of the fovea, providing a positional basis for subsequent illumination template occlusion.

[0043] Optionally, in this embodiment of the invention, before stimulating the user's retina with light through a preset light source to achieve the purpose of visual training, the method further includes: Obtain the irradiation parameters preset by the trainer; wherein, the irradiation parameters include the light source wavelength, energy density, light spot diameter, and irradiation time; The corresponding illumination template is obtained by matching the light spot diameter.

[0044] The embodiments of the present invention can meet the needs of differentiated visual training by presetting illumination parameters and illumination templates.

[0045] Optionally, in this embodiment of the invention, the step of stimulating the user's retina with light through a preset light source to achieve the purpose of visual training includes: The corresponding light source is set according to the light source wavelength, energy density, and spot diameter; During the irradiation period, the user's retina is stimulated by light from the light source; wherein a preset light template is set at the position corresponding to the spatial coordinates so that the fovea is not stimulated by light.

[0046] In this embodiment of the invention, a preset light source is used to stimulate the user's retina with light, and a preset light template is set at the position corresponding to the spatial coordinates. This ensures that the fovea is not stimulated by light, while the retina around the fovea is stimulated by light, thereby effectively inducing the generation of negative afterimages and guiding the user to gradually return from peripheral fixation to central fixation, thus achieving the purpose of visual training.

[0047] Optionally, in this embodiment of the invention, the step of tracking the user's eye movements in real time during the illumination stimulation process and synchronously moving the illumination template based on the eye movements so that the illumination template continuously blocks the fovea includes: Based on real-time eye movement data collected by an infrared eye tracker, the offset of the user's real-time gaze direction compared to the initial gaze direction is calculated; Based on the offset, the light template is moved synchronously by controlling the deflector so that the light template continuously blocks the central concave area.

[0048] This invention, through real-time tracking of the user's eye movements during light stimulation and synchronous movement of the light template based on these eye movements, can dynamically correct the occlusion position of the light template, ensuring the accuracy of visual training and achieving closed-loop control.

[0049] like Figure 2 As shown, based on the above method embodiments, corresponding apparatus embodiments are provided; An embodiment of the present invention provides a visual training device based on image recognition, including: an image acquisition module 201, an image recognition module 202, an illumination stimulation module 203, and an eye tracking module 204; The image acquisition module 201 is used to acquire the user's retinal image through a fundus camera and preprocess the retinal image to obtain a macular region image; The image recognition module 202 is used to perform image recognition on the macular region image to obtain the spatial coordinates of the central fovea. The light stimulation module 203 is used to stimulate the user's retina with light through a preset light source to achieve the purpose of visual training; wherein, the preset light template is set at the position corresponding to the spatial coordinates so that the fovea is not stimulated by light. The eye-tracking module 204 is used to track the user's eye movements in real time during the illumination stimulation process, and to move the illumination template synchronously based on the eye movements so that the illumination template continuously blocks the fovea.

[0050] Optionally, in this embodiment of the invention, a head support submodule and an observation window submodule are further included before the image acquisition module 201; The head support submodule is used to fix the user's head position through the head support structure so that the user can look directly at the viewing window; The observation window submodule is used to project a gaze target within the observation window so that the user gazes at the gaze target; wherein the direction of the user's gaze while maintaining the gaze on the gaze target is used as the initial gaze direction.

[0051] The embodiments of the present invention guide the user's gaze through a head support structure and an observation window, which can help the user stabilize their gaze and provide a reference gaze direction for subsequent eye tracking.

[0052] Optionally, in this embodiment of the invention, the image acquisition module 201 includes: a noise suppression submodule, a contrast enhancement submodule, and a region cropping submodule; The noise suppression submodule is used to suppress noise in the retinal image to obtain a first retinal image; The contrast enhancement submodule is used to enhance the contrast of the first retinal image to obtain a second retinal image; The region cropping submodule is used to crop the macular region of the second retinal image to obtain a macular region image.

[0053] The embodiments of the present invention, by performing image preprocessing on retinal images, can ensure accurate coverage of the macula region before visual training, providing a reliable data basis for subsequent foveal localization and light stimulation.

[0054] Optionally, in this embodiment of the invention, the image recognition module 202 includes: an image recognition submodule and a coordinate transformation submodule; The image recognition submodule is used to perform feature extraction and spatial regression on the macular region image to obtain the pixel coordinates of the concave center; The coordinate transformation submodule is used to linearly convert the pixel coordinates into spatial position coordinates based on the width of the observation window and the imaging resolution width of the fundus camera.

[0055] This invention, through image recognition and coordinate transformation of the macula region image, can accurately extract the spatial coordinates of the fovea, providing a positional basis for subsequent illumination template occlusion.

[0056] Optionally, in this embodiment of the invention, an illumination parameter submodule and an illumination template submodule are further included before the light stimulation module 203; The irradiation parameter submodule is used to acquire irradiation parameters preset by the trainer; wherein, the irradiation parameters include light source wavelength, energy density, light spot diameter, and irradiation time; The illumination template submodule is used to obtain a corresponding illumination template based on the diameter of the light spot.

[0057] The embodiments of the present invention can meet the needs of differentiated visual training by presetting illumination parameters and illumination templates.

[0058] Optionally, in this embodiment of the invention, the light stimulation module 203 includes: a light source setting submodule and a light stimulation submodule; The light source setting submodule is used to set the corresponding light source according to the light source wavelength, energy density and spot diameter; The light stimulation submodule is used to provide light stimulation to the user's retina through the light source during the irradiation period; wherein a preset light template is set at the position corresponding to the spatial coordinates so that the fovea is not stimulated by light.

[0059] In this embodiment of the invention, a preset light source is used to stimulate the user's retina with light, and a preset light template is set at the position corresponding to the spatial coordinates. This ensures that the fovea is not stimulated by light, while the retina around the fovea is stimulated by light, thereby effectively inducing the generation of negative afterimages and guiding the user to gradually return from peripheral fixation to central fixation, thus achieving the purpose of visual training.

[0060] Optionally, in this embodiment of the invention, the eye-tracking module 204 includes: an eye-tracking submodule and a control skew module; The eye-tracking submodule is used to calculate the offset of the user's real-time gaze direction from the initial gaze direction based on the eye movement data collected in real time by the infrared eye tracker. The control deflector module is used to control the deflector to move the illumination template synchronously based on the offset, so that the illumination template continuously blocks the central concave area.

[0061] This invention, through real-time tracking of the user's eye movements during light stimulation and synchronous movement of the light template based on these eye movements, can dynamically correct the occlusion position of the light template, ensuring the accuracy of visual training and achieving closed-loop control.

[0062] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can implement the image recognition-based visual training method provided by any of the above-described method embodiments of the present invention.

[0063] This invention employs an image acquisition module 201 to acquire a user's retinal image and preprocesses it to ensure accurate coverage of the macula before visual training, providing a reliable data foundation for subsequent foveal localization and illumination stimulation. An image recognition module 202 performs image recognition on the macula image, accurately extracting the spatial coordinates of the fovea, providing a positional basis for subsequent illumination template occlusion. An illumination stimulation module 203 provides illumination stimulation to the user's retina and sets a preset illumination template at the position corresponding to the spatial coordinates, ensuring the fovea is not stimulated while the surrounding retina is, effectively inducing negative afterimages and guiding the user from eccentric fixation back to central fixation, achieving the goal of visual training. An eye-tracking module 204 tracks the user's eye movements in real time during illumination stimulation and moves the illumination template synchronously based on these movements, dynamically correcting the illumination template occlusion position, ensuring the accuracy of visual training, and achieving closed-loop control.

[0064] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0065] Based on the above embodiment of a vision training method based on image recognition, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a vision training method based on image recognition according to any embodiment of the present invention.

[0066] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0067] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0068] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0069] Based on the above-described method embodiments, another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute a visual training method based on image recognition as described in any of the above-described method embodiments of the present invention.

[0070] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0071] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A visual training device based on image recognition, characterized in that, include: Image acquisition module, image recognition module, illumination stimulation module, and eye tracking module; The image acquisition module is used to acquire retinal images of the user captured by the fundus camera, and to preprocess the retinal images to obtain macular region images; The image recognition module is used to perform image recognition on the macular region image to obtain the spatial coordinates of the fovea. The light stimulation module is used to set a corresponding light source according to a preset light source wavelength, energy density and light spot diameter, and control the light source to emit light within a preset illumination time so that the light shines on the user's retina; wherein, a corresponding light template is obtained according to the light spot diameter, and the light template is set at the position corresponding to the spatial coordinates so that the fovea is not stimulated by light. The eye-tracking module is used to acquire the user's eye movement data collected in real time by the infrared eye tracker, and control the illumination template to move synchronously based on the eye movement data so that the illumination template continuously blocks the fovea.

2. A terminal device, characterized in that, The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a vision training method based on image recognition, the vision training method based on image recognition comprising: Acquire retinal images of the user captured by a fundus camera, and preprocess the retinal images to obtain macular region images; Image recognition is performed on the image of the macular region to obtain the spatial coordinates of the fovea. A corresponding light source is set according to a preset light source wavelength, energy density, and light spot diameter, and the light source is controlled to emit light within a preset illumination time so that the light shines on the user's retina; wherein, a corresponding light template is obtained according to the light spot diameter, and the light template is set at the position corresponding to the spatial coordinates so that the fovea is not stimulated by light. The user's eye movement data is acquired in real time by an infrared eye tracker, and the illumination template is controlled to move synchronously based on the eye movement data so that the illumination template continuously blocks the fovea.

3. A computer-readable storage medium, characterized in that, include: A stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform an image recognition-based visual training method, the image recognition-based visual training method comprising: Acquire retinal images of the user captured by a fundus camera, and preprocess the retinal images to obtain macular region images; Image recognition is performed on the image of the macular region to obtain the spatial coordinates of the fovea. A corresponding light source is set according to a preset light source wavelength, energy density, and light spot diameter, and the light source is controlled to emit light within a preset illumination time so that the light shines on the user's retina; wherein, a corresponding light template is obtained according to the light spot diameter, and the light template is set at the position corresponding to the spatial coordinates so that the fovea is not stimulated by light. The user's eye movement data is acquired in real time by an infrared eye tracker, and the illumination template is controlled to move synchronously based on the eye movement data so that the illumination template continuously blocks the fovea.

Images