Eye device, display correction method and AR / VR equipment

Abstract

The invention discloses an eye device, a display correction method and AR / VR equipment. The eye device comprises an imaging module, a display module, an optical signal acquisition module, an adjustment module and an acquisition module, the imaging module is arranged on the side, close to the to-be-detected eye, of the display module, and the optical signal acquisition module is arranged on the side, away from the to-be-detected eye, of the imaging module; the imaging module is used for imaging the display image output by the display module on the retina area of the eye to be detected; the imaging module is also used for transmitting reflected light of the retina area to the optical signal acquisition module; the optical signal acquisition module is used for acquiring a fundus image of the to-be-detected eye according to the reflected light; the acquisition module is used for acquiring optical adjustment parameters according to the fundus image, and the adjustment module is used for adjusting display parameters of the display module and imaging parameters of the imaging module according to the optical adjustment parameters so as to correct the display image, so that the actual visual experience of a retinopathy user is improved, and the visual demand of the user is met.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of detection technology, and in particular to an eye device, a display correction method and an AR / VR device. Background Art

[0002] Due to the influence of some diseases, the retina may also induce some lesions, which may cause great changes in the shape and size of objects when viewing, such as objects becoming smaller, larger, and distorted.

[0003] Currently, some lesions can be alleviated or cured through medications, surgery, etc., but abnormal vision before effective treatment will still cause great distress to patients. Summary of the invention

[0004] The present invention provides an eye device, a display correction method and AR / VR equipment to improve the actual visual experience of users with retinal diseases and meet the visual needs of users.

[0005] In a first aspect, an embodiment of the present invention provides an eye device, comprising: an imaging module, a display module, an optical signal acquisition module, an adjustment module, and an acquisition module;

[0006] The imaging module is arranged on a side of the display module close to the eye to be tested, and the optical signal acquisition module is arranged on a side of the imaging module away from the eye to be tested;

[0007] The imaging module is used to image the display image output by the display module on the retinal area of ​​the eye to be tested; the imaging module is also used to transmit the reflected light of the retinal area to the optical signal acquisition module;

[0008] The optical signal acquisition module is used to obtain the fundus image of the eye to be tested according to the reflected light;

[0009] The acquisition module is connected to the optical signal acquisition module, and the acquisition module is used to acquire optical adjustment parameters according to the fundus image;

[0010] The adjustment module is connected to the display module, the imaging module and the acquisition module respectively; the adjustment module is used to adjust the display parameters of the display module and the imaging parameters of the imaging module according to the optical adjustment parameters to correct the displayed image.

[0011] Optionally, the acquisition module includes an adaptation unit, a deep learning unit and an output unit;

[0012] The adapting unit is used for obtaining a data pair of the fundus image and the optical adjustment parameter according to different fundus images and the optical adjustment parameter for correcting the display image corresponding to each fundus image;

[0013] The deep learning unit is used to train the model of the fundus image and the optical adjustment parameter based on a deep learning method;

[0014] The output unit is used to output the optical adjustment parameter according to the fundus image and the model of the optical adjustment parameter.

[0015] Optionally, the deep learning method adopts a natural language processing algorithm.

[0016] Optionally, the eye device further includes a data processing module;

[0017] The data processing module is connected to the optical signal acquisition module; the data processing module is used to compare the fundus image with the image database to determine the degree of the pathological changes in the eye to be tested.

[0018] Optionally, the display parameters include brightness parameters and color parameters; and the imaging parameters include imaging distance and imaging position.

[0019] Optionally, the imaging module adopts a microlens array.

[0020] In a second aspect, an embodiment of the present invention provides a display correction method, which is performed by an eye device according to any embodiment of the present invention, wherein the eye device comprises: an imaging module, a display module, an optical signal acquisition module, an adjustment module, and an acquisition module;

[0021] The correction method comprises:

[0022] The imaging module images the display image output by the display module on the retinal area of ​​the eye to be tested; and transmits the reflected light of the retinal area to the optical signal acquisition module;

[0023] The optical signal acquisition module obtains the fundus image of the eye to be tested according to the reflected light;

[0024] The acquisition module acquires optical adjustment parameters according to the fundus image;

[0025] The adjustment module adjusts the display parameters of the display module and the imaging parameters of the imaging module according to the optical adjustment parameters to correct the displayed image.

[0026] Optionally, the acquisition module includes an adaptation unit, a deep learning unit and an output unit;

[0027] The correction method comprises:

[0028] The adapting unit obtains a data pair of the fundus image and the optical adjustment parameter according to the different fundus images and the optical adjustment parameter for correcting the display image corresponding to each fundus image;

[0029] The deep learning unit trains a model of the fundus image and the optical adjustment parameter based on a deep learning method;

[0030] The output unit outputs the optical adjustment parameter according to the fundus image and the model of the optical adjustment parameter.

[0031] Optionally, the eye device further comprises: a data processing module;

[0032] The correction method comprises:

[0033] The data processing module compares the fundus image with the image database to determine the degree of the pathological changes in the eye to be tested.

[0034] In a third aspect, an embodiment of the present invention provides an AR / VR device, comprising the eye device described in any embodiment of the present invention.

[0035] The technical solution provided by the embodiment of the present invention utilizes an imaging module to image the display image output by the display module on the retinal area of ​​the eye to be tested, and also transmits the reflected light of the retinal area to the optical signal acquisition module; the optical signal acquisition module obtains the fundus image of the eye to be tested according to the reflected light; the acquisition module obtains the optical adjustment parameters according to the fundus image; the adjustment module adjusts the display parameters of the display module and the imaging parameters of the imaging module according to the optical adjustment parameters or manually to correct the display image, thereby improving the actual visual experience of users with retinal diseases and meeting the users' visual needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram of the structure of an eye device provided by an embodiment of the present invention;

[0037] Figure 2 A schematic diagram of the structure of another eye device provided by an embodiment of the present invention;

[0038] Figure 3 A schematic diagram of the structure of another eye device provided by an embodiment of the present invention

[0039] Figure 4 A schematic flow chart of a display correction method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] Figure 1 A schematic diagram of the structure of an eye device provided by an embodiment of the present invention, see Figure 1 , including: an imaging module 110, a display module 120, an optical signal acquisition module 130, an adjustment module 140 and an acquisition module 150;

[0042] The imaging module 110 is disposed on a side of the display module 120 close to the eye to be tested, and the optical signal acquisition module 130 is disposed on a side of the imaging module 110 away from the eye to be tested;

[0043] The imaging module 110 is used to image the display image output by the display module 120 on the retinal area of ​​the eye to be tested; the imaging module 110 is also used to transmit the reflected light of the retinal area to the optical signal acquisition module 130;

[0044] The optical signal acquisition module 130 is used to obtain a fundus image of the eye to be tested according to the reflected light;

[0045] The acquisition module 150 is connected to the optical signal acquisition module 130, and the acquisition module 150 is used to acquire optical adjustment parameters according to the fundus image;

[0046] The adjustment module 140 is connected to the display module 120 , the imaging module 110 and the acquisition module 150 respectively; the adjustment module 140 is used to adjust the display parameters of the display module 120 and the imaging parameters of the imaging module 110 according to the optical adjustment parameters to correct the displayed image.

[0047] Specifically, the imaging module 110 can use an optical device to image the display image, and the display image can fall on the retinal area of ​​the eye to be tested. Exemplarily, the imaging module 110 may include a microlens array, which may be an array of micron-level lenses, having the focusing and imaging functions of traditional lenses, and having the characteristics of small unit size and high integration. The imaging module 110 is arranged between the display module 120 and the eye to be tested, and the imaging module 110 can transmit the display image to the retinal area of ​​the eye to be tested, and the reflected light of the retinal area can be transmitted to the optical signal acquisition module 130 through the imaging module 110. Among them, the display image can be a generated virtual image, or it can be an image of the external environment collected by the lens device. Exemplarily, the bidirectional imaging process of the imaging module 110 can be realized by changing the imaging direction and / or imaging focus. For example, the imaging module 110 can include a driving unit, and the driving unit can be used to control the imaging direction of the microlens array. When the display image is transmitted to the retinal area of ​​the eye to be tested, the imaging direction of the microlens array can be from the display device to the eye to be tested. When the reflected light from the retinal area is transmitted to the optical signal collection module 130, the driving unit can control the microlens array to flip so that the imaging direction of the microlens array can be from the eye to be tested to the optical signal collection module 130. Through the high-speed refresh of the driving unit, the imaging direction can be changed at a certain frequency. Alternatively, by changing the focus of the microlens array, the arrangement of the focus in the focal plane can display any pattern.

[0048] Some lesions of the retina, such as macular degeneration or lesions of the retina and choroid near the macula, can cause the visual cells to be crowded together or overlapped, which results in different imaging effects felt by users with different fundus lesions being different. Therefore, the display parameters of the display module 120 and the imaging parameters of the imaging module 110 can be manually adjusted by the adjustment module 140 to compensate for the visual deformation so that the user can feel normal visual imaging. Exemplarily, the display parameters may include brightness parameters and color parameters, and the imaging parameters may include imaging distance and imaging position.

[0049] The optical signal acquisition module 130 can use the reflected light from the retinal area to image the retina of the eye to be tested and obtain a fundus image. By collecting a large number of fundus images of different eyes to be tested and the optical adjustment parameters of the corresponding fundus images, a data pair of the fundus image and the optical adjustment parameter can be established, and a known deep learning method can be used for training, such as using a natural language processing algorithm (Natural Language Processing, NLP), such as a Transformer framework for training, to obtain a model of the mapping relationship between the fundus image and the optical adjustment parameter. Therefore, the acquisition module 150 can input the fundus image of the optical signal acquisition module 130 according to the model of the fundus image and the optical adjustment parameter, and obtain the corresponding optical adjustment parameter.

[0050] After the user obtains the fundus image through detection, the adjustment module 140 can adjust the display parameters of the display module 120 and the imaging parameters of the imaging module 110 according to the optical adjustment parameters to correct the displayed image so that the user can experience normal visual imaging.

[0051] The technical solution provided by the embodiment of the present invention utilizes the imaging module 110 to image the display image output by the display module 120 on the retinal area of ​​the eye to be tested, and also transmits the reflected light of the retinal area to the optical signal acquisition module 130; the optical signal acquisition module 130 obtains the fundus image of the eye to be tested according to the reflected light; the acquisition module 150 obtains the optical adjustment parameters according to the fundus image; the adjustment module 140 adjusts the display parameters of the display module 120 and the imaging parameters of the imaging module 110 according to the optical adjustment parameters or manually to correct the display image, thereby improving the actual visual experience of users with retinal diseases and meeting the visual needs of users.

[0052] Figure 2 A schematic diagram of the structure of another eye device provided by an embodiment of the present invention, see Figure 2 , Optionally, the acquisition module 150 includes an adaptation unit 151, a deep learning unit 152 and an output unit 153;

[0053] The adapting unit 151 is used to obtain a data pair of fundus images and optical adjustment parameters according to different fundus images and the optical adjustment parameters of the corrected display image corresponding to each fundus image;

[0054] The deep learning unit 152 is used to train a model of fundus images and optical adjustment parameters based on a deep learning method;

[0055] The output unit 153 is used to output the optical adjustment parameters according to the fundus image and the model of the optical adjustment parameters.

[0056] Specifically, fundus images of different users are collected through an eye device to obtain a sufficient number of fundus images, and the optical adjustment parameters of the displayed image corrected by the user through the adjustment module 140 are also collected. The adaptation unit 151 adapts the corrected optical adjustment parameters corresponding to each fundus image to obtain a data pair of the fundus image and the optical adjustment parameters, that is, the fundus image and the optical adjustment parameters have a certain mapping relationship. The deep learning unit 152 can obtain a model of the fundus image and the optical adjustment parameters based on the deep learning method and using the obtained data pair as training data. Among them, the deep learning method can be trained using an existing natural language processing algorithm (Natural Language Processing, NLP), such as a Transformer framework. Therefore, after the user's fundus image is collected, the output unit 153 can output the corresponding optical adjustment parameters based on the obtained fundus image.

[0057] The adjustment module 140 can automatically adjust the display parameters of the display module 120 and the imaging parameters of the imaging module 110 according to the optical adjustment parameters to correct the displayed image so that the user can experience the corrected visual imaging.

[0058] Figure 3 A schematic diagram of the structure of another eye device provided by an embodiment of the present invention, see Figure 3 , the eye device also includes a data processing module 160;

[0059] The data processing module 160 is connected to the optical signal acquisition module 130 ; the data processing module 160 is used to compare the fundus image with the image database to determine the degree of the lesion of the eye to be tested.

[0060] Specifically, the image database used by the data processing module 160 can be obtained using an existing medical image training model for retinal lesions. The image database may include images corresponding to different lesions. For example, for diabetic retinopathy, there may be yellow-white exudation, blood spots, etc. in the fundus, and osteocyte-like pigment deposition in retinal pigment degeneration. The data processing module 160 compares and matches the features of the fundus image with the features in the image database, thereby determining whether there is a corresponding lesion and the extent of the corresponding lesion based on the degree of matching. For example, if the similarity between the fundus image and the image features of a certain type of lesion in the image database reaches 90%, it can be said that the risk of the eye to be tested being at a high risk of the corresponding lesion is high. If the similarity is only 20%, it can be said that the risk of the eye to be tested being at a low risk of the corresponding lesion is low. The eye device provided in the embodiment of the present invention can help users understand eye health in a timely manner, avoid delaying the user's diagnosis or treatment opportunities, and improve the convenience of use.

[0061] Furthermore, the judgment of the degree of lesions of the eye to be measured by the data processing module 160 can be linked to the optical adjustment parameters of the display image corrected by the adjustment module 140. For example, the judgment result of the degree of lesions of the eye to be measured is classified by the data processing module 160, that is, the normal fundus head portrait, the first lesion fundus image, the second lesion fundus image, etc. are obtained according to the classification of the fundus image. For the classification of each fundus image, the optical adjustment parameters of the display image can be obtained accordingly. In other words, when the adjustment module 140 compensates for the visual deformation, the display image can be adjusted according to the type of lesion of the fundus image, or the display image can be adjusted according to the current specific fundus image based on the model of the fundus image and the optical adjustment parameters. The corresponding adjustment sequence can also be set, for example, the display image is adjusted according to the classification of the fundus image first, and then the optical adjustment parameters are determined according to the specific fundus image, and the display image is adjusted to achieve the purpose of fine adjustment.

[0062] Figure 4 A flow chart of a display correction method is provided for an embodiment of the present invention. This embodiment can be applied to the display correction of fundus lesions and is performed by an eye device of any embodiment of the present invention. The eye device includes: an imaging module, a display module, an optical signal acquisition module, an adjustment module and an acquisition module. The device can be implemented in hardware and / or software. The method specifically includes the following steps:

[0063] S110, the imaging module images the display image output by the display module on the retinal area of ​​the eye to be tested; and transmits the reflected light of the retinal area to the optical signal acquisition module;

[0064] Specifically, the imaging module 110 can use an optical device to image the display image, and the display image can fall on the retinal area of ​​the eye to be tested. Exemplarily, the imaging module 110 may include a microlens array, which may be an array of micron-level lenses, having the focusing and imaging functions of traditional lenses, and having the characteristics of small unit size and high integration. The imaging module 110 is arranged between the display module 120 and the eye to be tested, and the imaging module 110 can transmit the display image to the retinal area of ​​the eye to be tested, and the reflected light of the retinal area can be transmitted to the optical signal acquisition module 130 through the imaging module 110. Among them, the display image can be a generated virtual image, or it can be an image of the external environment collected by the lens device. Exemplarily, the bidirectional imaging process of the imaging module 110 can be realized by changing the imaging direction and / or imaging focus. For example, the imaging module 110 can include a driving unit, and the driving unit can be used to control the imaging direction of the microlens array. When the display image is transmitted to the retinal area of ​​the eye to be tested, the imaging direction of the microlens array can be from the display device to the eye to be tested. When the reflected light from the retinal area is transmitted to the optical signal collection module 130, the driving unit can control the microlens array to flip so that the imaging direction of the microlens array can be from the eye to be tested to the optical signal collection module 130. Through the high-speed refresh of the driving unit, the imaging direction can be changed at a certain frequency. Alternatively, by changing the focus of the microlens array, the arrangement of the focus in the focal plane can display any pattern.

[0065] S120, the optical signal acquisition module obtains a fundus image of the eye to be tested according to the reflected light;

[0066] S130, an acquisition module acquires optical adjustment parameters according to the fundus image;

[0067] Specifically, by collecting a large number of fundus images of different eye parts to be tested and the optical adjustment parameters of the corresponding fundus images, a data pair of fundus images and optical adjustment parameters can be established, and trained using known deep learning methods, for example, using a natural language processing algorithm (Natural Language Processing, NLP), such as the Transformer framework for training, to obtain a model of the mapping relationship between fundus images and optical adjustment parameters. Therefore, the acquisition module 150 can input the fundus image of the optical signal acquisition module 130 according to the model of fundus images and optical adjustment parameters, and obtain the corresponding optical adjustment parameters.

[0068] S140: The adjustment module adjusts the display parameters of the display module and the imaging parameters of the imaging module according to the optical adjustment parameters to correct the displayed image.

[0069] Specifically, some retinal lesions, such as macular lesions or retinal and choroidal lesions near the macula, can cause the visual cells to be crowded together or overlapped, etc., which results in different imaging effects actually felt by users with different fundus lesions being different. Therefore, the display parameters of the display module 120 and the imaging parameters of the imaging module 110 can be manually adjusted through the adjustment module 140 to compensate for the visual deformation so that the user can feel normal visual imaging. Exemplarily, the display parameters may include brightness parameters and color parameters, etc., and the imaging parameters include imaging distance and imaging position, etc. After the user obtains the fundus image through detection, the adjustment module 140 can automatically adjust the display parameters of the display module 120 and the imaging parameters of the imaging module 110 according to the optical adjustment parameters to correct the displayed image so that the user can feel normal visual imaging.

[0070] Optionally, the acquisition module includes an adaptation unit, a deep learning unit, and an output unit;

[0071] Correction methods include:

[0072] The adapting unit obtains a data pair of the fundus image and the optical adjustment parameter according to different fundus images and the optical adjustment parameter of the corrected display image corresponding to each fundus image;

[0073] The deep learning unit trains models of fundus images and optical adjustment parameters based on deep learning methods;

[0074] The output unit outputs the optical adjustment parameter according to the fundus image and the model of the optical adjustment parameter.

[0075] Specifically, different users are collected through the eye device to compensate for visual deformation to obtain a sufficient number of fundus images, and the optical adjustment parameters of the user's correction of the display image through the adjustment module 140 are also collected. The adaptation unit 151 adapts the corrected optical adjustment parameters corresponding to each fundus image to obtain a data pair of the fundus image and the optical adjustment parameters, that is, the fundus image and the optical adjustment parameters have a certain mapping relationship. The deep learning unit 152 is based on a deep learning method and uses the obtained data pair as training data to obtain a model of the fundus image and the optical adjustment parameters. Among them, the deep learning method can be trained using an existing natural language processing algorithm (Natural Language Processing, NLP), such as a Transformer framework. Therefore, after the user's fundus image is collected, the output unit 153 can output the corresponding optical adjustment parameters based on the obtained fundus image.

[0076] The adjustment module 140 can automatically adjust the display parameters of the display module 120 and the imaging parameters of the imaging module 110 according to the optical adjustment parameters to correct the displayed image so that the user can experience the corrected visual imaging.

[0077] Optionally, the eye device further comprises: a data processing module;

[0078] Correction methods include:

[0079] The data processing module compares the fundus image with the image database to determine the degree of lesions in the eye to be tested.

[0080] Specifically, the image database used by the data processing module 160 can be obtained using an existing medical image training model for retinal lesions. The image database may include images corresponding to different lesions. For example, for diabetic retinopathy, there may be yellow-white exudation, blood spots, etc. in the fundus, and osteocyte-like pigment deposition in retinal pigment degeneration. The data processing module 160 compares and matches the features of the fundus image with the features in the image database, thereby determining whether there is a corresponding lesion and the extent of the corresponding lesion based on the degree of matching. For example, if the similarity between the fundus image and the image features of a certain type of lesion in the image database reaches 90%, it can be said that the risk of the eye to be tested being at a high risk of the corresponding lesion is high. If the similarity is only 20%, it can be said that the risk of the eye to be tested being at a low risk of the corresponding lesion is low. The eye device provided in the embodiment of the present invention can help users understand eye health in a timely manner, avoid delaying the user's diagnosis or treatment opportunities, and improve the convenience of use.

[0081] Furthermore, the judgment of the degree of lesions of the eye to be measured by the data processing module 160 can be linked to the optical adjustment parameters of the display image corrected by the adjustment module 140. For example, the judgment result of the degree of lesions of the eye to be measured is classified by the data processing module 160, that is, the normal fundus head portrait, the first lesion fundus image, the second lesion fundus image, etc. are obtained according to the classification of the fundus image. For the classification of each fundus image, the optical adjustment parameters of the display image can be obtained accordingly. In other words, when the adjustment module 140 compensates for the visual deformation, the display image can be adjusted according to the type of lesion of the fundus image, or the display image can be adjusted according to the current specific fundus image based on the model of the fundus image and the optical adjustment parameters. The corresponding adjustment sequence can also be set, for example, the display image is adjusted according to the classification of the fundus image first, and then the optical adjustment parameters are determined according to the specific fundus image, and the display image is adjusted to achieve the purpose of fine adjustment.

[0082] An embodiment of the present invention further provides an AR / VR device, wherein the AR / VR device may be a head-mounted AR / VR glasses, because it includes the eye device of any embodiment of the present invention, and thus has the same beneficial effects, which will not be described in detail here.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An eye device, characterized in that: include: Imaging module, display module, optical signal acquisition module, adjustment module and acquisition module; The imaging module is arranged on a side of the display module close to the eye to be tested, and the optical signal acquisition module is arranged on a side of the imaging module away from the eye to be tested; The imaging module is used to image the display image output by the display module on the retinal area of ​​the eye to be tested; the imaging module is also used to transmit the reflected light of the retinal area to the optical signal acquisition module; The optical signal acquisition module is used to obtain the fundus image of the eye to be tested according to the reflected light; The acquisition module is connected to the optical signal acquisition module, and the acquisition module is used to acquire optical adjustment parameters according to the fundus image; The adjustment module is connected to the display module, the imaging module and the acquisition module respectively; the adjustment module is used to adjust the display parameters of the display module and the imaging parameters of the imaging module according to the optical adjustment parameters to correct the displayed image.

2. The eye device according to claim 1, characterized in that: The acquisition module includes an adaptation unit, a deep learning unit and an output unit; The adapting unit is used for obtaining a data pair of the fundus image and the optical adjustment parameter according to different fundus images and the optical adjustment parameter for correcting the display image corresponding to each fundus image; The deep learning unit is used to train the model of the fundus image and the optical adjustment parameter based on a deep learning method; The output unit is used to output the optical adjustment parameter according to the fundus image and the model of the optical adjustment parameter.

3. The eye device according to claim 2, characterized in that: The deep learning method uses a natural language processing algorithm.

4. The ocular device according to claim 1, wherein: Also includes a data processing module; The data processing module is connected to the optical signal acquisition module; the data processing module is used to compare the fundus image with the image database to determine the degree of the pathological changes in the eye to be tested.

5. The ocular device according to any one of claims 1 to 4, characterized in that: The display parameters include brightness parameters and color parameters; the imaging parameters include imaging distance and imaging position.

6. The ocular device according to any one of claims 1 to 4, characterized in that: The imaging module adopts a microlens array.

7. A display correction method, characterized in that: The method is performed by the eye device according to any one of claims 1 to 6, wherein the eye device comprises: an imaging module, a display module, an optical signal acquisition module, an adjustment module and an acquisition module; The correction method comprises: The imaging module images the display image output by the display module on the retinal area of ​​the eye to be tested; and transmits the reflected light of the retinal area to the optical signal acquisition module; The optical signal acquisition module obtains the fundus image of the eye to be tested according to the reflected light; The acquisition module acquires optical adjustment parameters according to the fundus image; The adjustment module adjusts the display parameters of the display module and the imaging parameters of the imaging module according to the optical adjustment parameters to correct the displayed image.

8. The display correction method according to claim 7, characterized in that: The acquisition module includes an adaptation unit, a deep learning unit and an output unit; The correction method comprises: The adapting unit obtains a data pair of the fundus image and the optical adjustment parameter according to the different fundus images and the optical adjustment parameter for correcting the display image corresponding to each fundus image; The deep learning unit trains a model of the fundus image and the optical adjustment parameter based on a deep learning method; The output unit outputs the optical adjustment parameter according to the fundus image and the model of the optical adjustment parameter.

9. The display correction method according to claim 7, characterized in that: The eye device further comprises: a data processing module; The correction method comprises: The data processing module compares the fundus image with the image database to determine the degree of the pathological changes in the eye to be tested.

10. An AR / VR device, characterized in that: An ocular device comprising any one of claims 1-6.

Images