CN115191931A

CN115191931A - Strabismus detection method, device and computer readable storage medium

Info

Publication number: CN115191931A
Application number: CN202210879822.6A
Authority: CN
Inventors: 黄琴华; 张毅; 李文权
Original assignee: Shenzhen Skyworth New World Technology Co ltd
Current assignee: Shenzhen Skyworth New World Technology Co ltd
Priority date: 2022-07-25
Filing date: 2022-07-25
Publication date: 2022-10-18

Abstract

The invention discloses a strabismus detection method, equipment and a computer readable storage medium, wherein the strabismus detection method comprises the following steps: acquiring a first eye image of the eyes of a target user, performing binocular eye socket image recognition on the first eye image, and acquiring a white eye position and a first pupil position of the eyes of the target user; generating a second pupil position of the target user's eye based on the white eye position; and comparing the first pupil position with the second pupil position to generate a deviation degree between the first pupil position and the second pupil position, and outputting the deviation degree as a reference basis for judging whether the eyes of the target user have strabismus. The method greatly facilitates the detection process of the strabismus of the eyes of the user, reduces the errors of manual visual measurement, and does not need to depend on the experience of doctors too much.

Description

Strabismus detection method, device and computer readable storage medium

Technical Field

The present invention relates to the field of eye detection, and in particular, to a strabismus detection method, device, and computer-readable storage medium.

Background

Strabismus is usually due to the long term, excessively tight or relaxed state of the eye muscles, resulting in a positive and an inward or outward deviation of one eye, such that when one eye is looking at, the visual axis of the other eye deviates from the parallel abnormal eye position. Oblique views from inside to outside are the two most common types of oblique views.

In medical ophthalmology, the patient that takes place the strabismus is most young, can't in time restore the strabismus through the operation, or the strabismus degree is not serious, inconvenient through the operation treatment to lead to the unable normal thing of looking of patient, influence the patient and carry out normal life. In addition, even in the current stage of spectacles or hospitals, the pupillary distance is mostly measured manually by using a ruler, and the strabismus is mainly judged by visual observation, so that on one hand, the requirements on the experience of doctors are high, and on the other hand, the condition that the diagnosis cannot be timely carried out on the slight strabismus, and the optimal treatment period is missed. The current squint detection approach is inconvenient for the user.

Therefore, a method for detecting the eye state of a user conveniently and quickly is needed.

The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.

Disclosure of Invention

The invention mainly aims to provide a strabismus detection method, equipment and a computer readable storage medium, and aims to solve the technical problem that the current strabismus detection mode is inconvenient for users.

In order to achieve the above object, the present invention provides a strabismus detection method, comprising the steps of:

acquiring a first eye image of the eyes of a target user, performing binocular eye socket image recognition on the first eye image, and acquiring a white eye position and a first pupil position of the eyes of the target user;

generating a second pupil location of the target user's eye based on the whiteeye location;

and comparing the first pupil position with the second pupil position to generate a deviation degree between the first pupil position and the second pupil position, and outputting the deviation degree as a reference basis for judging whether the eyes of the target user have strabismus.

Further, the white eye positions include a left white outside eye position, a left white inside eye position, a right white outside eye position, and a right white inside eye position, and the step of generating the second pupil position of the eye of the target user based on the white eye positions includes:

and generating a second left-eye pupil position and a second right-eye pupil position based on the left-eye white outside position, the left-eye white inside position, the right-eye white outside position and the right-eye white inside position, wherein the second pupil position comprises the second left-eye pupil position and the second right-eye pupil position.

Further, the step of generating a second left eye pupil position and a second right eye pupil position based on the left eye white lateral position, the left eye white medial position, the right eye white lateral position, and the right eye white medial position comprises:

generating a reference distance based on the left eye white outer side position, the left eye white inner side position, the right eye white outer side position, the right eye white inner side position and a preset calculation formula;

the preset calculation formula comprises:

wherein, N is the reference distance, D is the distance between the white outer side position of the left eye and the white outer side position of the right eye, and C is the distance between the white inner side position of the left eye and the white inner side position of the right eye;

and taking the position of the left-eye white inner side position, which is located at the left-eye white outer side position direction and is separated from the reference distance with the left-eye white inner side position, as the second left-eye pupil position, and taking the position of the right-eye white inner side position, which is located at the right-eye white outer side position direction and is separated from the reference distance with the right-eye white inner side position, as the second right-eye pupil position.

Further, the step of comparing the first pupil position with the second pupil position to generate a deviation between the first pupil position and the second pupil position includes:

comparing the first and second pupil locations to generate a pupil deviation between the first and second pupil locations;

comparing the first right eye pupil position with the second right eye pupil position to generate a right eye pupil deviation degree between the first right eye pupil position and the second right eye pupil position;

the degrees of deviation include the left eye pupil degree of deviation and the right eye pupil degree of deviation.

Further, prior to the step of obtaining a first eye image of the target user's eyes, the method includes:

outputting a preset target image on a display device positioned in front of a target user so that the target user gazes forwards;

when detecting the target user is in the state of gazing the front, the image acquisition of the target user eyes is carried out through two detection modules so as to obtain the first eye image.

Further, before the step of outputting the preset target image, the detection method includes:

acquiring a second eye image of the target user eye;

generating adjustment data of the distance between the two detection modules based on the second eye image;

and adjusting the distance between the two detection modules based on the adjustment data so as to match the positions of the two detection modules with the eyes of the target user.

Further, after the step of outputting the deviation degree, the method further includes:

acquiring training content and training intensity from a preset training content library according to the deviation degree;

outputting a training image based on the training content and the training intensity to train the target user's eyes.

Further, to achieve the above object, the present invention also provides an oblique-viewing detection apparatus including: the device comprises two detection modules and a processing module, wherein the two detection modules are arranged in a bilateral symmetry manner; the detection module comprises a display device, a reflection element and a camera element; the processing module is in communication connection with the camera element; a preset included angle is formed between the plane where the display device is located and the plane where the reflection element is located, the camera element is located on one side of the reflection surface of the reflection element, and the reflection surface is the surface, far away from the display device, of the reflection element; the light incidence direction of the camera element faces the reflecting surface, and the camera element is used for receiving the light reflected by the reflecting surface; the included angle between the front light-in direction of the camera element and the front light-out direction of the display device is twice of the preset included angle;

wherein, the processing module includes: a memory, a processor and a squint detection program stored on the memory and executable on the processor, the squint detection program when executed by the processor implementing the steps of the method of squint detection as described above.

Furthermore, the detection module also comprises an optical lens group and an eye box; the plane that optical lens group locates is parallel with the plane that display device locates, optical lens group, reflection element with display device arranges in proper order, the eye box is located optical lens group keeps away from one side of display device just interval preset distance between eye box and the optical lens group, the positive projection of the positive light-emitting direction of display device extremely in the eye box.

In addition, to achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a strabismus detection program, which when executed by a processor, implements the steps of the strabismus detection method as described above.

The embodiment of the invention provides a strabismus detection method, equipment and a computer readable storage medium, which are used for acquiring a first eye image of eyes of a target user, performing binocular eye socket image recognition on the first eye image, and acquiring a white eye position and a first pupil position of the eyes of the target user; generating a second pupil location of the target user's eye based on the whiteeye location; and comparing the first pupil position with the second pupil position to generate a deviation degree between the first pupil position and the second pupil position, and outputting the deviation degree to be used as a reference basis for judging whether the eyes of the target user have strabismus. The method comprises the steps of carrying out image recognition on eyes of a target user to obtain a white eye position and a first pupil position of the eyes of the user, wherein the white eye position is used for generating a second pupil position, the second pupil position is a standard pupil image of the user, and the first pupil position is compared with the second pupil position, so that the deviation degree between the first pupil position and the second pupil position is accurately obtained. The deviation degree can be used as a basis for judging whether the eyes of the user have strabismus. The method greatly facilitates the detection process of the strabismus of the eyes of the user, reduces the errors of manual visual measurement, and does not need to depend on the experience of doctors too much.

Drawings

FIG. 1 is a schematic structural diagram of a strabismus detection device in the strabismus detection method of the present invention;

FIG. 2 is a schematic diagram of a partial detail of the squint detection apparatus of the present invention;

FIG. 3 is a schematic structural diagram of an operating environment of a processing module in the squint detection apparatus according to the present invention;

FIG. 4 is a schematic flowchart of a squint detection method according to a first embodiment of the present invention;

FIG. 5 is a schematic flow chart illustrating a second embodiment of the strabismus detection method according to the present invention;

FIG. 6 is a schematic flowchart of a third embodiment of the strabismus detection method according to the present invention;

FIG. 7 is a schematic diagram of an eye of a target user in the strabismus detection method according to the present invention;

FIG. 8 is a schematic diagram of an eye of a target user for image recognition in the strabismus detection method according to the present invention;

FIG. 9 is a diagram illustrating eye quantization of a target user in the strabismus detection method according to the present invention;

fig. 10 is a diagram illustrating eye comparison of a target user in the strabismus detection method of the present invention.

Examples reference numbers illustrate:

reference numerals	Name(s)	Reference numerals	Name (R)
				1000	Strabismus detection device	10	Detection module
20	Display device with a light-shielding layer	30	Reflective element
				31	Reflecting surface	40	Image pickup device
50	Optical lens assembly	60	Eye box
				70	Light source emitting element	80	Processing module
90	Connecting mechanism	91	Adjusting and detecting module
				100	External display module	110	Voice prompt module

The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.

The main solution of the embodiment of the invention is as follows: acquiring a first eye image of the eyes of a target user, performing binocular eye socket image recognition on the first eye image, and acquiring a white eye position and a first pupil position of the eyes of the target user; generating a second pupil location of the target user's eye based on the whiteeye location; and comparing the first pupil position with the second pupil position to generate a deviation degree between the first pupil position and the second pupil position, and outputting the deviation degree as a reference basis for judging whether the eyes of the target user have strabismus.

The current squint detection mode is inconvenient for users.

The invention provides a solution, which is characterized in that the white eye position and the first pupil position of the eyes of a user are obtained by carrying out image recognition on the eyes of a target user, the white eye position is used for generating a second pupil position, the second pupil position is a standard pupil image of the user, and the first pupil position is compared with the second pupil position, so that the deviation degree between the first pupil position and the second pupil position is accurately obtained. The deviation degree can be used as a basis for judging whether the eyes of the user have strabismus. The method greatly facilitates the detection process of the strabismus of the eyes of the user, reduces the errors of manual visual measurement, and does not need to depend on the experience of doctors too much.

Referring to fig. 1, fig. 1 is a schematic structural diagram of an oblique-viewing detection apparatus in the oblique-viewing detection method of the present invention.

As shown in fig. 1, an oblique-view detecting apparatus 1000, the oblique-view detecting apparatus 1000 includes: the two detection modules 10 are arranged in a bilateral symmetry mode; the detection module 10 comprises a display device 20, a reflecting element 30 and a camera element 40; a preset included angle is formed between a plane where the display device 20 is located and a plane where the reflection element 30 is located, and the image pickup element 40 is located on one side of a reflection surface of the reflection element 30, wherein the reflection surface is a surface of the reflection element 30 away from the display device 20; the light incident direction of the image pickup device 40 faces the reflecting surface 31, and the image pickup device 40 is configured to receive the light reflected by the reflecting surface 31; the included angle between the front light-in direction of the image pickup element 40 and the front light-out direction of the display device 20 is twice the preset included angle.

In this embodiment, the squint detection apparatus 1000 further includes an auxiliary support (shown in the figure), and the auxiliary support can support the two detection modules 10 and maintain the position and structure relationship of each component in the detection modules 10 as shown in fig. 1. When the strabismus detection apparatus 1000 is used for detecting the eye condition of the user, the user looks at the two symmetrically arranged detection modules 10 with both eyes, and since the reflection element 30 reflects only invisible light (has high transparency to visible light), the user can view the picture displayed on the display device 20, and the display device 20 can attract the user to gaze forward with both eyes through the display picture. When the natural invisible light illuminates the eyes of the user, the invisible light is reflected by the eyes to the periphery, and since a preset included angle (an angle α in fig. 1) exists between the reflective element 30 and the image pickup element 40, the preset included angle may be set by a technician according to the relative position relationship of the components, and is not limited specifically here, and a part of the invisible light is reflected by the reflective surface 31 of the reflective element 30 and then reflected into the image pickup element 40, where the image pickup element 40 is located on one side of the reflective surface 31 of the reflective element 30. The light incident direction of the image pickup element 40 is directed toward the reflecting surface 31 so that the image pickup element 40 can receive the invisible light reflected by the reflecting surface 31 of the reflecting element 30. Further, referring to fig. 2, an included angle between the front light incident direction of the image capturing device 40 and the front light incident direction of the display device 20 is 2 α, and the invisible light reflected by the front surface of the eyes of the user is emitted again through the reflective device 30 and perpendicularly enters the image capturing device 40, so that the image capturing devices 40 in the two detection modules 10 generate front images of the eyes of the user according to the received invisible light. It can be understood that the front images of the eyes of the user generated in the present embodiment are generated when the user gazes at the display device 20 with both eyes, so that the influence of the distracting attention of the user on the examination when the doctor manually checks the images can be eliminated, and whether the user has the strabismus symptom can be conveniently determined based on the front images of the eyes of the user.

Further, the detection module 10 further includes an optical lens group 50 and an eye box 60; the plane where the optical lens group 50 is located is parallel to the plane where the display device 20 is located, the optical lens group 50, the reflection element 30 and the display device 20 are sequentially arranged, the eye box 60 is located on one side, away from the display device, of the optical lens group 50, a preset distance is arranged between the eye box 60 and the optical lens group 50 at intervals, and the front light emitting direction of the display device 20 is orthographically projected into the eye box 60.

In this embodiment, the detection module 10 further includes an optical lens assembly 50 and an eye box 60, the plane of the optical lens assembly 50 is parallel to the plane of the display device 20, and the reflective element 30 is located between the optical lens assembly 50 and the display device 20. The optical lens group 50 of the reflective element 30 can enlarge and project the displayed image on the display device 20 on the side of the display device 20 away from the human eye. Typically, the projection distance of the optical lens group 50 will be larger than 2m, so as to reproduce the scene for the user's normal eye. The spacing between the optic 50 of the eye box 60 is typically greater than 10mm. The specific separation distance may also be adjusted by a technician or user due to differences between different human eyes. The eye box 60 can limit the position of the eyes of the user, that is, the user can view the picture on the display device 20 and collect the front image of the eyes at the position of the eye box 60, so that the collected front image of the eyes can better meet the design requirement during collection, and the reliability of the front image of the eyes can be increased.

Further, the detection module 10 further includes a light source emitting element 70; the light source emitting element 70 is located on a side of the optical lens group 50 away from the reflecting element, wherein the light source emitting element 70 is used for emitting invisible light rays into the eye box 60.

In this embodiment, the detecting module 10 further includes a light source emitting element 70. The number of the light source emitting elements 70 may be one or more than one. The light source emitting element 70 is located on a side of the optical lens group 50 away from the reflecting element 30, and the light source emitting element 70 can emit invisible light to the eyes, so that the defect of invisible light in nature is overcome, and the collection of the front image of the eyes of the user is prevented from being influenced. And the invisible light generated by the light source emitting element 70 does not affect the user's view of the display device 20.

Further, the light source emitting element 70 is an infrared light source emitting element, and the infrared light source emitting element is used for emitting infrared light to the eyes of the user in the eye box.

In this embodiment, the light source emitting element 70 may be an infrared light source emitting element, such as an infrared LED lamp, which emits infrared light to the eyes of the user to enhance the imaging effect of the image capturing element 40.

Further, the reflective element 30 is an infrared reflective element, and the infrared reflective element is configured to reflect infrared light diffusely reflected by the eyes of the user.

In this embodiment, the reflective element 30 may be an infrared reflective element, and the infrared reflective element has high reflectivity to infrared light, so as to increase the amount of light entering the image capturing element 40 from the infrared light diffusely reflected by the eyes of the user.

Further, the strabismus detecting apparatus 1000 further comprises a processing module 80; the processing module 80 is in communication connection with the camera element 40; the processing module 80 is communicatively coupled to the display device 20.

In this embodiment, the visual inspection apparatus 1000 further includes a processing module 80, and the processing module 80 is an electronic device with a data processing function, such as a computer or a mobile phone. The processing module 80 may be in communication connection with the image pickup device 40 and the display device 20 in a wireless or wired manner. The processing module 80 acquires the left eye image and the right eye image of the user acquired by the two image pickup elements 40, so that the left eye image and the right eye image form a complete front eye image of the user and are output, and the eye condition of the user can be conveniently judged. The processing module 80 will also input the preset image data to the display device 20, so that the display device 20 displays the preset image.

Further, the strabismus detecting device 1000 further comprises a connecting mechanism 90; the two detection modules 10 which are arranged in bilateral symmetry are connected through the connecting mechanism 90, and the connecting mechanism 90 is used for adjusting the distance between the two detection modules 10.

In this embodiment, the strabismus detection device 1000 further includes a connection mechanism 90, the connection mechanism 90 connects the two detection modules 10, and the connection mechanism 90 can adjust the distance between the two detection modules 10, so that the strabismus detection device 1000 conforms to the actual interpupillary distance of the user.

Further, the connecting mechanism 90 further includes an adjusting and detecting module 91, and the adjusting and detecting module 91 is used for detecting an adjusting distance between two detecting modules 10.

In this embodiment, the strabismus detecting device 1000 further includes an adjusting detecting module 91, and the adjusting detecting module 91 can detect an adjusted distance between the two detecting modules 10, so as to obtain an actual pupil distance of the user, where the pupil distance of the user can be used as one of the bases for determining the eye condition of the user.

Further, the strabismus detecting device 1000 further comprises a voice prompt module 110; the voice prompt module 110 is communicatively connected to the processing module 80.

In this embodiment, the strabismus detecting device 1000 further includes a voice prompt module 110, and the voice prompt module 110 can receive an instruction from the processing module 80 to prompt the user to watch an image frame in the display device 20.

Further, the strabismus detecting apparatus 1000 further comprises an external display module 100; the external display module 100 is in communication connection with the display device 20; or/and the external display module 100 is in communication connection with the processing module 80.

In this embodiment, the strabismus detecting apparatus 1000 further includes an external display module 100. The external display module 100 may be a display screen, and the external display module 100 may be communicatively connected to the display device 20 or/and communicatively connected to the processing module 80 through a wireless network or a data line. Specifically, the external display module 100 may receive the image data of the display device 20 to display the same image as the display device 20, so that other people may view the image currently seen by the detected user. The external display module 100 may also receive the front eye image of the user sent by the processing module 80, so as to conveniently display the front eye image to the outside and conveniently determine the eye condition of the user.

As shown in fig. 3, fig. 3 is a schematic structural diagram of an operating environment of a processing module in the squint detecting apparatus according to the present invention.

The processing module in the embodiment of the invention can be a PC, and can also be an electronic terminal device with data receiving, data processing and data sending functions, such as a smart phone, a tablet computer and a portable computer.

As shown in fig. 1, the processing module may include: a processor 1001, e.g. a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. The communication bus 1002 is used to implement connection communication among these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.

Optionally, the processing module may further include a camera, a Radio Frequency (RF) circuit, a sensor, an audio circuit, a WiFi module, and the like. Such as light sensors, motion sensors, and other sensors, among others. Specifically, light sensor can include ambient light sensor and proximity sensor, and wherein, ambient light sensor can adjust the luminance of display screen according to the light and shade of ambient light, and proximity sensor can be when processing module moves to the ear, closes display screen and/or be shaded. As one of the motion sensors, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally, three axes), detect the magnitude and direction of gravity when the mobile terminal is stationary, and can be used for applications (such as horizontal and vertical screen switching, related games, magnetometer attitude calibration), vibration recognition related functions (such as pedometer and tapping) and the like for recognizing the attitude of the mobile terminal; of course, the processing module may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which are not described herein again.

Those skilled in the art will appreciate that the process module configuration shown in fig. 1 is not meant to be limiting, and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.

As shown in fig. 3, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a squint detection program.

In the processing module shown in fig. 3, the network interface 1004 is mainly used for connecting to a backend server and performing data communication with the backend server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to call the strabismus detection program stored in the memory 1005 and perform the following operations:

generating a second pupil position of the target user's eye based on the white eye position;

Further, the processor 1001 may call the strabismus detection program stored in the memory 1005, and also perform the following operations:

the white eye position includes a left white eye outside position, a left white eye inside position, a right white eye outside position, and a right white eye inside position, and the step of generating the second pupil position of the target user's eyes based on the white eye position includes:

Further, the processor 1001 may call the squint detection program stored in the memory 1005, and also perform the following operations:

the step of generating a second left eye pupil position and a second right eye pupil position based on the left eye white outside position, the left eye white inside position, the right eye white outside position, and the right eye white inside position comprises:

the preset calculation formula comprises:

the step of comparing the first pupil position and the second pupil position to generate a deviation degree between the first pupil position and the second pupil position comprises:

comparing the first and second left-eye pupil positions to generate a left-eye pupil deviation between the first and second left-eye pupil positions;

comparing the first right-eye pupil position with the second right-eye pupil position to generate a right-eye pupil deviation degree between the first right-eye pupil position and the second right-eye pupil position;

prior to the step of obtaining a first eye image of a target user's eyes, the method comprises:

when the target user is detected to be in a state of watching the front, image acquisition is carried out on the eyes of the target user through two detection modules so as to acquire the first eye image.

before the step of outputting the preset target image, the detection method includes:

acquiring a second eye image of the target user eye;

after the step of outputting the degree of deviation, the method further comprises:

Referring to fig. 4, a strabismus detection method according to a first embodiment of the present invention includes:

step S10, acquiring a first eye image of the eyes of a target user, performing binocular eye socket image recognition on the first eye image, and acquiring a white eye position and a first pupil position of the eyes of the target user;

in this embodiment, the implementation subject is a strabismus detection device (or a processing module in the strabismus detection device), the strabismus detection device may collect a first eye image of the target user through an image pickup element of the self-detection module (the first eye image may be a color image or an infrared image), and perform binocular eye socket image recognition on the first eye image, so as to generate a white eye position and a first pupil position of the eyes of the target user. It can be understood that, at present, there is a mature image recognition technology, and an image recognition algorithm with a function of recognizing specific features can be obtained only by marking features to be recognized on an image sample and putting the marked image into an image recognition algorithm for training, which is not described herein again.

Step S20, generating a second pupil position of the eyes of the target user based on the white eye position;

further, the white eye position includes a left white outside eye position, a left white inside eye position, a right white outside eye position and a right white inside eye position, and a second left pupil position and a second right pupil position are generated based on the left white outside eye position, the left white inside eye position, the right white outside eye position and the right white inside eye position, wherein the second pupil position includes the second left pupil position and the second right pupil position.

Specifically, the white positions include a left-eye white outside position, a left-eye white inside position, a right-eye white outside position, and a right-eye white inside position. The schematic eye diagram of the target user as shown in fig. 7, where the white of the right eye, the outer canthus of the right eye, the inner canthus of the right eye, the length of the left eye, and the length of the right eye are labeled. The white lateral position of the right eye is the position where the white and the outer canthus of the right eye are connected (the white lateral position of the right eye can also be the position of the outer canthus of the right eye, and the difference between the two positions is not great, so that a technician can set the white lateral position according to actual conditions), and the white medial position of the right eye is the edge position of the white of the right eye close to the inner canthus. Due to the symmetry of the left and right eyes, the positions of the outer side of the white of the left eye and the positions of the inner side of the white of the left eye can be determined by the same method, and the details are not repeated here. And identifying the left eye white outer side position, the left eye white inner side position, the right eye white outer side position and the right eye white inner side position of the eyes of the target user through an image identification technology to generate a second left eye pupil position and a second right eye pupil position. It will be appreciated that the generated second left-eye pupil position and second right-eye pupil position will be used as reference positions for the pupils of the eyes of the target user.

Further, generating a reference distance based on the left-eye white outer position, the left-eye white inner position, the right-eye white outer position, the right-eye white inner position and a preset calculation formula;

the preset calculation formula comprises:

Specifically, referring to fig. 8, fig. 8 is a schematic view of an eye of a target user for image recognition. D is a distance between the left-eye white outer position and the right-eye white outer position, C is a distance between the left-eye white inner position and the right-eye white inner position, (D-C)/4 = n, n is a reference distance. The position of the right-eye white inside point is the second right-eye pupil position, which is a position away from the right-eye white inside point by a distance of N in the direction of the right-eye white outside point. Similarly, the position where the left-eye white inner side position points to the left-eye white outer side position direction and the left-eye white inner side position is away from the reference distance is taken as the second left-eye pupil position. It is understood that the generated second left-eye pupil position is actually the midpoint position between the inner white left-eye position and the outer white left-eye position, and similarly, the generated second right-eye pupil position is also the midpoint position between the inner white right-eye position and the outer white left-eye position. And the second left eye pupil position and the second right eye pupil position are also used as reference positions for detecting the basis of strabismus.

Step S30, comparing the first pupil position with the second pupil position, generating a deviation between the first pupil position and the second pupil position, and outputting the deviation as a reference for determining whether there is strabismus in the eyes of the target user.

Further, the first pupil position includes a first left-eye pupil position and a first right-eye pupil position, and the first left-eye pupil position and the second left-eye pupil position are compared to generate a left-eye pupil deviation between the first left-eye pupil position and the second left-eye pupil position; comparing the first right eye pupil position with the second right eye pupil position to generate a right eye pupil deviation degree between the first right eye pupil position and the second right eye pupil position; the degrees of deviation include the left eye pupil degree of deviation and the right eye pupil degree of deviation.

Specifically, the first pupil position is an actual pupil position of the user identified from the eye image of the user by using an image identification technology, and it should be noted that both the first pupil position and the white eye position are identified based on the same eye image and the same identification algorithm, so that a relative position between the first pupil position and the white eye position may reflect an actual condition of the eye of the user. The first pupil position comprises a first left-eye pupil position and a first right-eye pupil position, and the first left-eye pupil position is correspondingly compared with the second left-eye pupil position, and the first right-eye pupil position is correspondingly compared with the second right-eye pupil position. Taking the right eye of the user as an example, as shown in fig. 9, the second right-eye pupil position is located at the center position (zero point position) of the quantization map based on the quantization map generated based on the right-eye white inside position, the right-eye white outside position, and the second right-eye pupil position. The first pupil position is placed in the quantization map generated with the second right-eye pupil position as the center for comparison, as shown in the comparison map of fig. 10, the position of the first right-eye pupil position in the quantization map is-20, that is, the generated right-eye pupil deviation degree is-20. And outputting the-20 as a basis for judging whether the target right eye has strabismus. Similarly, the left-eye pupil deviation can also be generated as above, and will not be described herein again.

It can be understood that, in this embodiment, a first eye image of the eyes of the target user is obtained, and the first eye image is subjected to binocular eye socket image recognition to obtain the white eye position and the first pupil position of the eyes of the target user; generating a second pupil location of the target user's eye based on the whiteeye location; and comparing the first pupil position with the second pupil position to generate a deviation degree between the first pupil position and the second pupil position, and outputting the deviation degree to be used as a reference basis for judging whether the eyes of the target user have strabismus. In this embodiment, an eye white position and a first pupil position of the eyes of the user are obtained by performing image recognition on the eyes of the target user, the eye white position is used to generate a second pupil position, the second pupil position is a standard pupil map of the user, and the first pupil position is compared with the second pupil position, so that a deviation between the first pupil position and the second pupil position is accurately obtained. The deviation degree can be used as a basis for judging whether the eyes of the user have strabismus. The method greatly facilitates the detection process of the strabismus of the eyes of the user, reduces the error of manual visual measurement, and does not need to depend on too much experience of doctors.

Referring to fig. 5, a second embodiment of the strabismus detection method of the present invention is proposed based on the first embodiment of the strabismus detection method of the present invention:

before the step S10, the strabismus detection method includes:

step S01, collecting a second eye image of the eyes of the target user;

in this embodiment, the second eye image of the target user is acquired through the two symmetrical detection modules, specifically, when the user wears the two symmetrical detection modules, the detection modules will shoot the eyes of the user, and the second eye image is acquired.

Step S02, generating adjusting data of the distance between the two detection modules based on the second eye image;

specifically, the white eye position (the position of the pupil of the user may not be acquired) is acquired from the second eye image by using the image recognition technology, and the white eye position includes a left eye white outer position, a left eye white inner position, a right eye white outer position and a right eye white inner position. The distance D between the white outer side position of the left eye and the white outer side position of the right eye and the distance C between the white inner side position of the left eye and the white inner side position of the right eye can be obtained based on the white positions including the white outer side position of the left eye, the white inner side position of the left eye, the white outer side position of the right eye and the white inner side position of the right eye. The reference distance N can be obtained based on D and C (refer to the first embodiment). Reference interpupillary distances of the two eyes of the user can be generated through C and N, wherein the reference interpupillary distances are generated according to the following formula: reference interpupillary distance = C +2N. And taking the reference pupil distance as the adjusting data.

Step S03, adjusting the distance between the two detection modules based on the adjustment data so as to match the positions of the two detection modules with the eyes of the target user;

the distance between the detection modules is adjusted based on the reference pupil distance, each detection module comprises a display device, the distance between the two display devices is adjusted by adjusting the distance between the detection modules, and therefore the distance between the two display devices is matched with the reference pupil distance of the eyes of a target user, and the user has a good watching effect when watching the display devices.

Step S04, outputting a preset target image on a display device positioned in front of a target user so that the target user can watch forward;

specifically, after the detection module is adjusted, a preset target image is output on the two display devices, so that a user can watch the front. In general, an optical lens group may be disposed in front of the display device, that is, a user views a preset target image on the display device through the optical lens group, and the optical lens group may present the preset target image on the display device at a position more than two meters in front of the eyes of the user, so as to restore a scene when the user gazes at the front.

And S05, when the target user is detected to be in a state of gazing ahead, carrying out image acquisition on the eyes of the target user through two detection modules so as to obtain the first eye image.

Specifically, the left sight line of the left eyeball of the user and the right sight line of the right eyeball of the user are respectively identified through eyeball tracking, the intersection point of the left sight line and the right sight line is used as the fixation point of the user, and after the fixation point is overlapped with the preset target image position presented by the display device, the state that the user is in the front fixation state is judged. And acquiring an image of the eyes of the target user through two detection modules so as to acquire a first eye image.

It is understood that the first eye image is an image when the user is gazing forward. Therefore, the reliability of the detection data on the eyes of the user generated based on the first eye image is higher.

Referring to fig. 6, a second embodiment of the strabismus detection method of the present invention is proposed based on the first embodiment of the strabismus detection method of the present invention:

after the step S30, the strabismus detection method includes:

step S301, acquiring training content and training intensity from a preset training content library according to the deviation degree;

specifically, the training content library will contain different types and different stages of training image data. And acquiring training content and training strength from the training content library based on the deviation degree. For example, the deviation degree is-20, where the minus sign (-) is the deviation direction, 20 is the deviation degree, the training class contents of the negative deviation direction type are matched from the training content library, and the training class contents of the stage corresponding to 20 (the deviation degree) are matched from the training class contents of the negative deviation direction type. In addition, the training intensity (e.g., the number of times of training) corresponding to 20 is also matched in the training content library.

Step S302, outputting a training image based on the training content and the training intensity to train the eyes of the target user.

Specifically, the training image is played on the display device in the detection module based on the matching of the training content and the training intensity. For example, the matched training content is played on the display device for a set number of times. The user can correct the strabismus of the eyes of the user by watching the picture of the display device.

In addition, an embodiment of the present invention further provides a strabismus detection device, where the strabismus detection device includes: the device comprises two detection modules and a processing module, wherein the two detection modules are arranged in a bilateral symmetry manner; the detection module comprises a display device, a reflection element and a camera element; the processing module is in communication connection with the camera element; a preset included angle is formed between the plane where the display device is located and the plane where the reflection element is located, the camera element is located on one side of the reflection surface of the reflection element, and the reflection surface is one surface, far away from the display device, of the reflection element; the light incidence direction of the camera element faces the reflecting surface, and the camera element is used for receiving the light reflected by the reflecting surface; the included angle between the front light-in direction of the camera element and the front light-out direction of the display device is twice of the preset included angle;

wherein, the processing module includes: a memory, a processor and a squint detection program stored on the memory and executable on the processor, the squint detection program when executed by the processor implementing the steps of the squint detection method as described above.

The specific implementation of the strabismus detection device of the present invention is substantially the same as the above embodiments of the anti-falling method of the strabismus detection device, and is not described herein again.

In addition, an embodiment of the present invention further provides a computer-readable storage medium, where the strabismus detection program is stored, and when executed by a processor, the strabismus detection program implements the steps of the strabismus detection method as described above.

The specific implementation of the medium of the present invention is substantially the same as the embodiments of the squint detection method described above, and will not be described herein again.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or system comprising the element.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or the portions contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) as described above and includes several instructions for enabling a terminal device (which may be a mobile phone, a computer, a server, a VR device, or a network device, etc.) to execute the method according to the embodiments of the present invention.

The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes performed by the present invention or directly or indirectly applied to other related technical fields are also included in the scope of the present invention.

Claims

1. A strabismus detection method is characterized by comprising the following steps:

2. The strabismus detection method of claim 1, wherein the white eye positions comprise a left white outer eye position, a left white inner eye position, a right white outer eye position and a right white inner eye position, and the step of generating the second pupil position of the target user's eye based on the white eye positions comprises:

3. The strabismus detection method of claim 2, wherein the step of generating a second left eye pupil position and a second right eye pupil position based on the left eye white lateral position, the left eye white medial position, the right eye white lateral position, and the right eye white medial position comprises:

the preset calculation formula comprises:

4. The strabismus detection method of claim 3, wherein the first pupil position comprises a first left-eye pupil position and a first right-eye pupil position, and the step of comparing the first pupil position and the second pupil position to generate the degree of deviation between the first pupil position and the second pupil position comprises:

5. The strabismus detection method of claim 1, wherein prior to the step of acquiring a first eye image of a target user's eyes, the method comprises:

6. The strabismus detection method as claimed in claim 5, wherein before the step of outputting a preset target image, the detection method comprises:

acquiring a second eye image of the target user's eyes;

7. The strabismus detection method of claim 1, wherein after the step of outputting the degree of deviation, the method further comprises:

8. An apparatus for strabismus detection, comprising: the device comprises two detection modules and a processing module, wherein the two detection modules are arranged in a bilateral symmetry manner; the detection module comprises a display device, a reflection element and a camera element; the processing module is in communication connection with the camera element; a preset included angle is formed between the plane where the display device is located and the plane where the reflection element is located, the camera element is located on one side of the reflection surface of the reflection element, and the reflection surface is one surface, far away from the display device, of the reflection element; the light incidence direction of the camera shooting element faces the reflecting surface, and the camera shooting element is used for receiving the light rays reflected by the reflecting surface; the included angle between the front light-in direction of the camera element and the front light-out direction of the display device is twice of the preset included angle;

wherein, the processing module includes: memory, a processor and a strabismus detection program stored on the memory and executable on the processor, the strabismus detection program when executed by the processor implementing the steps of the strabismus detection method according to any of claims 1 to 7.

9. The strabismus detection apparatus of claim 8, wherein the detection module further comprises an optical lens group and an eye box; the plane that optical lens group locates is parallel with the plane that display device locates, optical lens group, reflection element with display device arranges in proper order, the eye box is located optical lens group keeps away from one side of display device just interval preset distance between eye box and the optical lens group, the positive projection of the positive light-emitting direction of display device extremely in the eye box.

10. A computer-readable storage medium, characterized in that it has stored thereon a strabismus detection program which, when executed by a processor, implements the steps of the strabismus detection method according to any of claims 1 to 7.