WO2020259127A1

WO2020259127A1 - Registration method, registration device, headset equipment and storage medium

Info

Publication number: WO2020259127A1
Application number: PCT/CN2020/090954
Authority: WO
Inventors: 徐乃江
Original assignee: Oppo广东移动通信有限公司
Priority date: 2019-06-26
Filing date: 2020-05-19
Publication date: 2020-12-30
Also published as: CN110287687A

Abstract

A registration method, a registration device (10), a headset equipment (100) and a storage medium. The registration method comprises: (S14) controlling a display (40) of the headset equipment (100) to display a guide image, the guide image comprising a target region; (S16) collecting a pupil image and a sclera image; and (S20) storing the sclera image as an authentication image if the pupil image matches the target region.

Description

Registration method, registration device, head-mounted device and storage medium

Priority information

This application requests the priority and rights of the patent application with the patent application number 201910559202.2 filed with the State Intellectual Property Office of China on June 26, 2019, and the full text is incorporated herein by reference.

Technical field

This application relates to the field of electronic technology, and in particular to a registration method, registration device, headset and storage medium.

Background technique

The headset of the related art is usually unlocked by human eyes.

Summary of the invention

This application provides a registration method, registration device, headset, and storage medium.

The embodiment of the present application provides a method for registering a headset. The registration method includes:

Controlling the display of the head-mounted device to display a guide image, the guide image including a target area;

Collect pupil images and scleral images;

In the case where the pupil image matches the target area, the scleral image is saved as an authentication image.

The embodiment of the present application provides a registration device for a headset. The registration device includes a guide module, a collection module, and a registration module. The guide module is used to control the display of the head-mounted device to display a guide image, the guide image includes a target area; the collection module is used to collect pupil images and Scleral image; the registration module is used to save the scleral image as an authentication image when the pupil image matches the target area.

The head-mounted device of the embodiment of the present application includes a display and a processor, the processor is connected to the display, the processor is used to control the display to display a guide image, the guide image includes a target area; and is used to collect pupil images And a scleral image; and for saving the scleral image as an authentication image when the pupil image matches the target area.

The head-mounted device of the embodiment of the present application includes a memory and a processor, and the memory stores one or more programs, and when the programs are executed by the processor, the above-mentioned head-mounted device registration method is implemented. The registration method includes: controlling the display of the head-mounted device to display a guide image, the guide image including a target area; collecting a pupil image and a sclera image; when the pupil image matches the target area, saving all The scleral image is used as the authentication image.

One or more non-volatile computer-readable storage media containing computer-executable instructions, when the computer-executable instructions are executed by one or more processors, cause the processors to execute the head-mounted device described above Registration method. The registration method includes: controlling the display of the head-mounted device to display a guide image, the guide image including a target area; collecting a pupil image and a sclera image; when the pupil image matches the target area, saving all The scleral image is used as the authentication image.

In the registration method, head-mounted device, and storage medium of the embodiments of the present application, the user is guided to register by guiding the target area of the image. When the pupil image matches the target area, saving the scleral image as the authentication image can make the authentication image more accurate And complete, thereby improving the accuracy of sclera unlocking.

The additional aspects and advantages of the embodiments of the present application will be partially given in the following description, and some will become obvious from the following description, or be understood through the practice of the present application.

Description of the drawings

The above and/or additional aspects and advantages of the present application will become obvious and easy to understand from the following description of the embodiments in conjunction with the accompanying drawings, in which:

Fig. 1 is a three-dimensional schematic diagram of a head-mounted device according to an embodiment of the present application;

2 is a schematic plan view of a head-mounted device according to another embodiment of the present application;

3 is a schematic plan view of a partial structure of a head-mounted device according to an embodiment of the present application;

4 is a schematic diagram of the adjustment process of the head-mounted device according to the embodiment of the present application;

FIG. 5 is another schematic diagram of the adjustment process of the head-mounted device according to the embodiment of the present application;

6 is a schematic plan view of a partial structure of a head-mounted device according to another embodiment of the present application;

7 is a schematic plan view of a partial structure of a head-mounted device according to another embodiment of the present application;

FIG. 8 is a schematic flowchart of a method for registering a headset according to an embodiment of the present application;

FIG. 9 is a schematic diagram of modules of a registration device of a head-mounted device according to an embodiment of the present application;

FIG. 10 is a schematic diagram of modules of a head-mounted device according to an embodiment of the present application;

FIG. 11 is a schematic diagram of a scene of a method for registering a headset according to an embodiment of the present application;

FIG. 12 is a schematic flowchart of a method for registering a headset according to another embodiment of the present application;

FIG. 13 is a schematic diagram of a scene of a method for registering a headset according to another embodiment of the present application;

14 is a schematic flowchart of a method for registering a headset according to another embodiment of the present application;

FIG. 15 is a schematic diagram of a scene of a registration method of a headset according to another embodiment of the present application;

FIG. 16 is a schematic flowchart of a method for registering a headset according to another embodiment of the present application;

FIG. 17 is a schematic diagram of a scene of a registration method of a headset according to still another embodiment of the present application;

FIG. 18 is a schematic diagram of another scene of a registration method of a headset according to still another embodiment of the present application;

FIG. 19 is a schematic flowchart of a method for registering a headset according to another embodiment of the present application;

20 is a schematic flowchart of a method for registering a headset according to another embodiment of the present application;

FIG. 21 is a schematic flowchart of a method for registering a headset according to another embodiment of the present application;

22 is a schematic flowchart of a method for registering a headset according to another embodiment of the present application;

FIG. 23 is a schematic flowchart of a method for registering a headset according to another embodiment of the present application;

FIG. 24 is a schematic flowchart of a method for registering a headset according to another embodiment of the present application.

Symbol description:

Housing 20, receiving groove 22, housing top wall 24, housing bottom wall 26, notch 262, housing side wall 28, supporting member 30, first bracket 32, first bending portion 322, second bracket 34, second bending Section 342, elastic band 36, display 40, refractive component 50, refractive cavity 52, light-transmitting liquid 54, first film layer 56, second film layer 58, side wall 59, adjusting mechanism 60, cavity 62, sliding Groove 622, sliding member 64, driving part 66, knob 662, lead screw 664, gear 666, rack 668, driving motor 669, motor shaft 6691, input 6692, adjusting cavity 68;

The head-mounted device 100, the registration device 10, the guiding module 14, the collection module 16, the registration module 20, the processor 101, the memory 102, and the eyes 200.

Detailed ways

The embodiments of the present application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals indicate the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary, and are intended to explain the application, but should not be understood as a limitation to the application.

8 and 10, the registration method of the head-mounted device 100 of the embodiment of the present application includes controlling the display 40 of the head-mounted device 100 to display a guide image, and the guide image includes a target area; collecting pupil images and scleral images; If the target area matches, save the scleral image as the authentication image.

Referring to FIGS. 10 and 12, in some embodiments, the registration method further includes: controlling the head-mounted device 100 to prompt the first prompt information; obtaining input information corresponding to the first prompt information; and determining the head-mounted device 100 according to the input information The authentication password is used to add and/or delete the authentication image.

Referring to FIG. 10 and FIG. 14, in some embodiments, the registration method further includes: controlling the head mounted device 100 to prompt second prompt information, and the second prompt information is related to the target area.

Referring to FIG. 16, in some embodiments, the registration method further includes: in the case where the pupil image matches the target area, controlling the color of the target area from the first color to the second color.

Referring to FIG. 19, in some embodiments, the registration method further includes: determining the gaze area of the guide image according to the pupil image; in the case where the gaze area matches the target area, determining that the pupil image matches the target area.

Referring to FIG. 20, in some embodiments, the authentication image includes authentication feature information, and saving the scleral image as the authentication image includes: performing feature enhancement processing on the scleral image; performing feature extraction on the processed scleral image to obtain the authentication feature information .

Please refer to FIG. 21. In some embodiments, the registration method further includes: acquiring a sclera unlock image; determining whether the sclera unlock image matches the authentication image; unlocking the headset 100 when the sclera unlock image matches the authentication image.

Referring to FIG. 22, in some embodiments, determining whether the scleral unlock image matches the authentication image includes: performing feature enhancement processing on the sclera unlock image; performing feature extraction on the processed sclera unlock image to obtain unlock feature information; In the case that the unlocking feature information matches the authentication feature information, it is determined that the scleral unlocking image matches the authentication image.

Referring to FIG. 23, in some embodiments, the registration method further includes: obtaining training pictures; according to the training pictures, a machine learning algorithm is used to train a matching judgment model, and the matching judgment model is used to determine whether the scleral unlock image matches the authentication image.

10 and 24, in some embodiments, the head-mounted device 100 includes an infrared camera, and collecting scleral unlocking images includes: collecting infrared images through the infrared camera; processing the infrared images to obtain the scleral unlocking images; the registration method includes: In the case that the subject is a living body, enter the step of determining whether the sclera unlocking image matches the authentication image; in the case that the subject is not a living body, the infrared image is ignored.

Please refer to FIG. 8 and FIG. 9, the registration device 10 of the head-mounted device 100 of the present application. The registration device 10 includes a guide module 14, an acquisition module 16, and a registration module 20. The guide module 14 is used to control the display 40 of the head-mounted device 100 to display a guide image, and the guide image includes a target area; the acquisition module 16 is used to collect pupil images and scleral images The registration module 20 is used to save the scleral image as an authentication image when the pupil image matches the target area.

8 and 10, the head-mounted device 100 of the present application includes a display 40 and a processor 101, the processor 101 is connected to the display 40, and the processor 101 is used to control the display 40 to display a guide image, and the guide image includes a target area; and To collect pupil images and scleral images; and to save the scleral image as an authentication image when the pupil image matches the target area.

10 and 12, in some embodiments, the processor 101 is used to control the head-mounted device 100 to prompt the first prompt information; and used to obtain input information corresponding to the first prompt information; The information determines the authentication password of the headset 100, and the authentication password is used to add and/or delete the authentication image.

Referring to FIG. 10 and FIG. 14, in some embodiments, the processor 101 is configured to control the head-mounted device 100 to prompt the second prompt information, and the second prompt information is related to the target area.

Referring to FIGS. 10 and 16, in some embodiments, the processor 101 is configured to control the color of the target area from the first color to the second color when the pupil image matches the target area.

10 and 19, in some embodiments, the processor 101 is used to determine the gaze area of the guide image according to the pupil image; and used to determine the pupil image and the target area when the gaze area matches the target area match.

10 and 20, in some embodiments, the authentication image includes authentication feature information, and the processor 101 is used to perform feature enhancement processing on the scleral image; and used to perform feature extraction on the processed scleral image to obtain authentication Characteristic information.

10 and 21, in some embodiments, the processor 101 is used to collect the scleral unlock image; and used to determine whether the scleral unlock image matches the authentication image; and used to match the sclera unlock image with the authentication image In this case, the headset 100 is unlocked.

10 and 22, in some embodiments, the processor 101 is used to perform feature enhancement processing on the scleral unlock image; and used to perform feature extraction on the processed sclera unlock image to obtain unlock feature information; and In the case where the unlocking feature information matches the authentication feature information, it is determined that the scleral unlocking image matches the authentication image.

10 and FIG. 23, in some embodiments, the processor 101 is used to obtain training pictures; and used to train a matching judgment model using a machine learning algorithm according to the training pictures, and the matching judgment model is used to determine the sclera unlock image and authentication Whether the images match.

10 and 24, in some embodiments, the head-mounted device 100 includes an infrared camera, and the processor 101 is used to collect infrared images through the infrared camera; and used to process the infrared images to obtain the scleral unlock image; and Determine whether the subject of the infrared image is alive according to the infrared image; and used to determine whether the sclera unlock image matches the authentication image when the subject is alive; and used to determine whether the subject is not alive , Ignore the infrared image.

Please refer to FIG. 10, the head-mounted device 100 of the embodiment of the present application includes a processor 101 and a memory 102. The memory 102 stores one or more programs, and when the programs are executed by the processor 101, the registration method of the head-mounted device 100 of any one of the foregoing embodiments is implemented.

Please refer to FIG. 10, a non-volatile computer-readable storage medium containing computer-executable instructions according to an embodiment of the present application. When the computer-executable instructions are executed by one or more processors 101, the processor 101 can execute the foregoing The registration method of any embodiment.

Referring to FIGS. 1 and 2, the head-mounted device 100 of the embodiment of the present application includes a housing 20, a supporting member 30, a display 40, a refractive member 50 and an adjustment mechanism 60.

The housing 20 is an external component of the headset 100 and plays a role of protecting and fixing the internal components of the headset 100. By enclosing the internal components by the housing 20, it is possible to avoid direct damage to these internal components by external factors.

Specifically, in this embodiment, the housing 20 can be used to house and fix at least one of the display 40, the diopter 50, and the adjustment mechanism 60. In the example of FIG. 2, the housing 20 is formed with a receiving groove 22, and the display 40 and the diopter 50 are received in the receiving groove 22. The adjustment mechanism 60 is partially exposed from the housing 20.

The housing 20 further includes a housing front wall 21, a housing top wall 24, a housing bottom wall 26 and a housing side wall 28. A gap 262 is formed in the middle of the housing bottom wall 26 facing the housing top wall 24. In other words, the housing 20 is roughly shaped like a "B". When the user wears the head-mounted device 100, the head-mounted device 100 can be erected on the bridge of the user's nose through the gap 262, which can ensure the stability of the head-mounted device 100 and the comfort of the user. The adjusting mechanism 60 may be partially exposed from the side wall 28 of the housing for the user to adjust the refractive component 50.

In addition, the housing 20 may be formed by processing aluminum alloy by a computer numerical control (Computerized Numerical Control, CNC) machine tool, or may be formed of polycarbonate (PC) or PC and acrylonitrile-butadiene-styrene (Acrylonitrile Butadiene Styrene plastic). , ABS) injection molding. The specific manufacturing method and specific materials of the housing 20 are not limited here.

The supporting member 30 is used to support the head mounted device 100. When the user wears the head-mounted device 100, the head-mounted device 100 may be fixed on the head of the user through the supporting member 30. In the example of FIG. 2, the supporting member 30 includes a first bracket 32, a second bracket 34 and an elastic band 36.

The first bracket 32 and the second bracket 34 are symmetrically arranged about the gap 262. Specifically, the first bracket 32 and the second bracket 34 are rotatably arranged on the edge of the housing 20. When the user does not need to use the headset 100, the first bracket 32 and the second bracket 34 can be stacked close to the housing 20. To facilitate storage. When the user needs to use the head mounted device 100, the first bracket 32 and the second bracket 34 can be deployed to realize the function of supporting the first bracket 32 and the second bracket 34.

A first bending portion 322 is formed at one end of the first bracket 32 away from the housing 20, and the first bending portion 322 is bent toward the bottom wall 26 of the housing. In this way, when the user wears the head-mounted device 100, the first bent portion 322 can be erected on the user's ear, so that the head-mounted device 100 is not easy to slip off.

Similarly, a second bending portion 342 is formed at an end of the second bracket 34 away from the housing 20, and the second bending portion 342 is bent toward the bottom wall 26 of the housing. The explanation and description of the second bending portion 342 can refer to the first bending portion 322, and to avoid redundancy, it will not be repeated here.

The elastic band 36 detachably connects the first bracket 32 and the second bracket 34. In this way, when the user wears the head-mounted device 100 for strenuous activities, the head-mounted device 100 can be further fixed by the elastic band 36 to prevent the head-mounted device 100 from loosening or even falling during the strenuous activity. It can be understood that in other examples, the elastic band 36 may also be omitted.

In this embodiment, the display 40 includes an OLED display screen. The OLED display screen does not require a backlight, which is beneficial to the lightness and thinness of the head-mounted device 100. Moreover, the OLED screen has a large viewing angle and low power consumption, which is conducive to saving power consumption.

Of course, the display 40 may also be an LED display or a Micro LED display. These displays are merely examples and the embodiments of the present application are not limited thereto.

Please also refer to FIG. 3, the refractive component 50 is arranged on the side of the display 40. The refractive component 50 includes a refractive cavity 52, a light-transmitting liquid 54, a first film layer 56, a second film layer 58 and a side wall 59.

The light-transmitting liquid 54 is disposed in the refractive cavity 52. The adjustment mechanism 60 is used to adjust the amount of the light-transmitting liquid 54 to adjust the shape of the refractive member 50. Specifically, the second film layer 58 is disposed relative to the first film layer 56, the sidewall 59 connects the first film layer 56 and the second film layer 58, and the first film layer 56, the second film layer 58, and the sidewall 59 The refractive cavity 52 and the adjusting mechanism 60 are used to adjust the amount of the transparent liquid 54 to change the shape of the first film layer 56 and/or the second film layer 58.

In this way, the refractive function of the refractive member 50 is realized. Specifically, "changing the shape of the first film layer 56 and/or the second film layer 58" includes three cases: the first case: changing the shape of the first film layer 56 without changing the shape of the second film layer 58; The second case: the shape of the first film layer 56 is not changed and the shape of the second film layer 58 is changed; the third case: the shape of the first film layer 56 is changed and the shape of the second film layer 58 is changed. Please note that for the convenience of explanation, in this embodiment, the first case is taken as an example for description.

The first film layer 56 may have elasticity. It can be understood that when the amount of the light-transmitting liquid 54 in the refractive cavity 52 changes, the pressure in the refractive cavity 52 also changes, so that the shape of the refractive component 50 changes.

In an example, the adjusting mechanism 60 reduces the amount of the light-transmitting liquid 54 in the refractive cavity 52, the pressure in the refractive cavity 52 is reduced, and the pressure difference between the pressure outside the refractive cavity 52 and the pressure in the refractive cavity 52 As it increases, the refractive cavity 52 becomes more concave.

In another example, the adjustment mechanism 60 increases the amount of the light-transmitting liquid 54 in the refractive cavity 52, the pressure in the refractive cavity 52 increases, and the pressure outside the refractive cavity 52 is equal to the pressure in the refractive cavity 52. The difference is reduced, and the refractive cavity 52 is more convex.

In this way, the form of the refractive member 50 can be adjusted by adjusting the amount of the light-transmitting liquid 54.

The adjustment mechanism 60 is connected to the diopter 50. The adjustment mechanism 60 is used to adjust the form of the diopter 50 to adjust the refractive power of the diopter 50. Specifically, the adjustment mechanism 60 includes a cavity 62, a sliding member 64, a driving part 66, an adjustment cavity 68 and a switch 61.

The sliding member 64 is slidably arranged in the cavity 62, the driving member 66 is connected to the sliding member 64, the cavity 62 and the sliding member 64 jointly define an adjustment cavity 68, the adjustment cavity 68 is connected to the refractive cavity 52 through the side wall 59, and the driving member 66 is used to drive the sliding member 64 to slide relative to the cavity 62 to adjust the volume of the adjustment cavity 68 to adjust the amount of the light-transmitting liquid 54 in the refractive cavity 52.

In this way, the volume of the adjusting cavity 68 is adjusted by the sliding member 64 to adjust the amount of the light-transmitting liquid 54 in the refractive cavity 52. In an example, please refer to FIG. 4, the sliding member 64 slides away from the side wall 59, the volume of the adjustment cavity 68 increases, the pressure in the adjustment cavity 68 decreases, and the light-transmitting liquid 54 in the refractive cavity 52 enters Adjusting the cavity 68, the first film layer 56 is more and more recessed inward.

In another example, please refer to FIG. 5, the sliding member 64 slides toward the side wall 59, the volume of the adjusting cavity 68 decreases, the pressure in the adjusting cavity 68 increases, and the light-transmitting liquid 54 in the adjusting cavity 68 enters In the refractive cavity 52, the first film layer 56 protrudes more and more outward.

The side wall 59 is formed with a flow channel 591, and the flow channel 591 communicates with the adjusting cavity 68 and the refractive cavity 52. The adjustment mechanism 60 includes a switch 61 provided in the flow channel 591, and the switch 61 is used to control the open and close state of the flow channel 591.

In this embodiment, the number of switches 61 is two. Both switches 61 are one-way switches. One switch 61 is used to control the flow of light-transmitting liquid 54 from the adjusting cavity 68 to the refractive cavity 52, and the other switch 61 It is used to control the light-transmitting liquid 54 to flow from the refractive cavity 52 to the regulating cavity 68.

In this way, the flow of the light-transmitting liquid 54 between the adjusting cavity 68 and the refractive cavity 52 is realized through the switch 61 to maintain the pressure balance on both sides of the side wall 59. As mentioned above, the change in the volume of the adjustment cavity 68 will cause the pressure in the adjustment cavity 68 to change, thereby causing the flow of the transparent liquid 54 between the adjustment cavity 68 and the refractive cavity 52. The switch 61 controls the opening and closing state of the flow channel 591 to control whether the flow of the light-transmitting liquid 54 between the adjusting cavity 68 and the refractive cavity 52 can be realized, thereby controlling the adjustment of the shape of the refractive component 50.

In an example, please refer to FIG. 4, the switch 61 that controls the flow of the transparent liquid 54 from the refractive cavity 52 to the adjustment cavity 68 is turned on, the sliding member 64 slides away from the side wall 59, and the volume of the adjustment cavity 68 increases. The pressure in the adjustment cavity 68 decreases, the light-transmitting liquid 54 in the refractive cavity 52 enters the adjustment cavity 68 through the switch 61, and the first film layer 56 is more and more inwardly recessed.

In another example, the switch 61 that controls the flow of the light-transmitting liquid 54 from the refractive cavity 52 to the adjustment cavity 68 is closed. Even if the slider 64 slides away from the side wall 59, the volume of the adjustment cavity 68 increases and the adjustment cavity 68 The pressure inside decreases, the light-transmitting liquid 54 in the refractive cavity 52 cannot enter the adjustment cavity 68, and the shape of the first film layer 56 does not change.

In another example, please refer to FIG. 5, the switch 61 that controls the flow of the light-transmitting liquid 54 from the adjusting cavity 68 to the refractive cavity 52 is opened, the sliding member 64 slides toward the side wall 59, and the volume of the adjusting cavity 68 decreases. , The pressure in the regulating cavity 68 increases, the light-transmitting liquid 54 in the regulating cavity 68 enters the refractive cavity 52 through the switch 61, and the first film layer 56 protrudes more and more outward.

In another example, the switch 61 that controls the flow of the light-transmitting liquid 54 from the adjusting cavity 68 to the refractive cavity 52 is closed. Even if the slider 64 slides toward the side wall 59, the volume of the adjusting cavity 68 decreases, and the adjusting cavity 68 The internal pressure increases, the transparent liquid 54 in the regulating cavity 68 cannot enter the refractive cavity 52, and the shape of the first film layer 56 does not change.

The driving component 66 can realize its function of driving the sliding member 64 to slide based on various structures and principles.

In the examples of FIGS. 1, 2, 3, 4, and 5, the driving part 66 includes a knob 662 and a screw 664, the screw 664 is connected to the knob 662 and the sliding member 64, and the knob 662 is used to drive the screw 664 to rotate The sliding member 64 is driven to slide relative to the cavity 62.

In this way, the slider 64 can be driven by the knob 662 and the lead screw 664. Since the screw 664 and the knob 662 cooperate to convert the rotary motion of the knob 662 into the linear motion of the screw 664, when the user rotates the knob 662, the screw 664 can drive the slider 64 to slide relative to the cavity 62, thereby causing adjustment The volume change of the cavity 68 further adjusts the amount of the transparent liquid 54 in the refractive cavity 52. The knob 662 can be exposed from the housing 20 to facilitate the user to rotate.

Specifically, a threaded part is formed on the knob 662, a threaded part that matches the knob 662 is formed on the screw 664, and the knob 662 and the screw 664 are threadedly connected.

While the knob 662 is rotating, the switch 61 can be opened correspondingly. In this way, the light-transmitting liquid 54 can flow, and the pressure balance on both sides of the side wall 59 is ensured.

In an example, the knob 662 rotates clockwise and the sliding member 64 slides away from the side wall 59 to turn on the switch 61 that controls the flow of the light-transmitting liquid 54 from the refractive cavity 52 to the adjustment cavity 68. In another example, the knob 662 rotates counterclockwise and the sliding member 64 slides toward the side wall 59 to turn on the switch 61 that controls the flow of the light-transmitting liquid 54 from the adjusting cavity 68 to the refractive cavity 52.

Please note that in this embodiment, the rotation angle of the knob 662 is not associated with the diopter power of the diopter 50, and the user only needs to rotate the knob 662 to a position with the best visual experience. Of course, in other embodiments, the rotation angle of the knob 662 and the diopter power of the diopter 50 may also be correlated. Here, it is not limited whether the rotation angle of the knob 662 and the diopter power of the diopter 50 are related.

Referring to FIG. 6, the driving component 66 includes a gear 666 and a rack 668 meshing with the gear 666. The rack 668 connects the gear 666 and the sliding member 64. The gear 666 is used to drive the rack 668 to move to drive the sliding member 64 relative to the cavity. 62 slide.

In this way, the sliding member 64 is driven by the gear 666 and the rack 668. Since the gear 666 and the rack 668 cooperate to convert the rotary motion of the gear 666 into the linear motion of the rack 668, when the user rotates the gear 666, the rack 668 can drive the slider 64 to slide relative to the cavity 62, thereby causing adjustment The volume change of the cavity 68 further adjusts the amount of the transparent liquid 54 in the refractive cavity 52. The gear 666 can be exposed from the housing 20 to facilitate the rotation of the user.

Similarly, while the gear 666 rotates, the switch 61 can be opened correspondingly. In this way, the light-permeable liquid 54 can flow, and the pressure balance on both sides of the side wall 59 is ensured.

In an example, the gear 666 rotates clockwise so that the rack 668 is meshed with the gear 666, the length of the rack 668 is shortened, and the sliding member 64 is pulled to move away from the side wall 59, and the light-transmitting liquid 54 is controlled from refractive The switch 61 from the cavity 52 to the regulating cavity 68 is opened.

In another example, the gear 666 rotates counterclockwise so that the rack 668 meshed with the gear 666 is disengaged from the gear 666, the length of the rack 668 increases, and the sliding member 64 is pushed to move toward the side wall 59, which will control the penetration The switch 61 of the optical liquid 54 flowing from the adjusting cavity 68 to the refractive cavity 52 is turned on.

Similarly, in this embodiment, the rotation angle of the gear 666 and the diopter power of the diopter 50 are not associated, and the user only needs to rotate the gear 666 to a position with the best visual experience. Of course, in other embodiments, the rotation angle of the gear 666 and the refractive power of the diopter 50 may also be correlated. Here, it is not limited whether the rotation angle of the gear 666 is related to the diopter power of the diopter 50.

Referring to FIG. 7, the driving component 66 includes a driving motor 669, a motor shaft 6691 of the driving motor 669 is connected to the sliding member 64, and the driving motor 669 is used to drive the sliding member 64 to slide relative to the cavity 62.

In this way, the sliding member 64 is driven by the driving motor 668. Specifically, the driving motor 669 may be a linear motor. The linear motor has a simple structure and directly generates linear motion without passing through an intermediate conversion mechanism, which can reduce the motion inertia and improve the dynamic response performance and positioning accuracy. The sliding member 64 is driven by the driving motor 668, so that the driving of the sliding member 64 is editable. For example, the drive motor 668 can be correlated with the power of refraction through prior calibration. The user can directly input the refractive power, and the driving motor 668 automatically operates to drive the sliding member 64 to slide to the corresponding position.

Further, the driving component 66 may also include an input 6692, and the input 6692 includes but is not limited to devices such as buttons, knobs, or touch screens. In the example of FIG. 7, the input 6692 is a button, and two buttons are respectively disposed on opposite sides of the cavity 62. The keys can be exposed from the housing 20 to facilitate the user to press. The button can control the operating time of the driving motor 669 according to the number or duration of external force pressing, thereby controlling the sliding distance of the sliding member 64.

Similarly, while the driving motor 669 is working, the switch 61 can be opened correspondingly. In this way, the light-transmitting liquid 54 can flow, and the pressure balance on both sides of the side wall 59 is ensured.

In an example, the user presses one of the two buttons to drive the motor shaft 6691 to extend, and the motor shaft 6691 pushes the slider 64 to move toward the side wall 59, which will control the flow of the transparent liquid 54 from the regulating cavity 68. The switch 61 to the refractive cavity 52 is turned on.

In another example, when the user presses the other of the two buttons, the motor shaft 6691 is shortened, and the motor shaft 6691 pulls the slider 64 to move away from the side wall 59, which will control the light-transmitting liquid 54 from the refractive cavity. The switch 61 flowing 52 to the adjustment chamber 68 is opened.

It should be noted that the structure of the refractive component 50 not only includes the above refractive cavity 52, the light-transmitting liquid 54, the first film layer 56, the second film layer 58 and the side wall 59, as long as the refractive component 50 can achieve diopter The effect of the change can be. For example, in other manners, the refractive component 50 includes a plurality of lenses and a driving member, and the driving member is used to drive each lens from the storage position to the refractive position. In this way, the refractive power of the diopter 50 can be changed by combining a plurality of lenses. Of course, the driving member can also drive each lens moved to the refractive position to move on the refractive axis, thereby changing the refractive power of the refractive component 50.

Therefore, the shape of the refractive component described above includes the shape and state of the refractive component, and the structure of the above refractive cavity 52, light-transmitting liquid 54, first film layer 56, second film layer 58, and sidewall 59 The shape of the first film layer 56 and/or the second film layer 58 is changed to achieve the change of diopter; the structure of the above multiple lenses and the driving member can realize the change of diopter by changing the state of the lens.

In summary, the embodiment of the present application provides a head-mounted device 100, which includes a display 40, a diopter 50, and an adjustment mechanism 60. The refractive member 50 is provided on the side of the display 40. The adjustment mechanism 60 is connected to the diopter 50, and the adjustment mechanism 60 is used to adjust the form of the diopter 50 to adjust the diopter of the diopter 50.

The head-mounted device 100 of the embodiment of the present application adjusts the shape of the refractive member 50 through the adjustment mechanism 60 to adjust the refractive power of the refractive member 50, so that users with refractive errors can see the images displayed on the display 40 clearly, which is beneficial to improve users. Experience.

Moreover, in the head-mounted device 100 of the embodiment of the present application, the refractive component 50 and the adjustment mechanism 60 can linearly correct the refractive power, so that everyone with different refractive power can wear it flexibly. At the same time, the volume of the refractive component 50 and the adjustment mechanism 60 is small, which does not affect the wearing experience of the head-mounted device 100. Users do not need to buy a lot of lenses, which can reduce the price.

Referring to FIG. 8, an embodiment of the present application provides a method for registering a headset 100. Registration methods include:

Step S14: controlling the display 40 of the head mounted device 100 to display a guide image, the guide image including the target area;

Step S16: Collect pupil images and scleral images;

Step S20: When the pupil image matches the target area, save the scleral image as the authentication image.

Referring to FIG. 9, an embodiment of the present application provides a registration device 10 of a head-mounted device 100. The registration device 10 includes a guide module 14, an acquisition module 16, and a registration module 20. The guide module 14 is used to control the display 40 of the head-mounted device 100 to display a guide image, and the guide image includes a target area; the acquisition module 16 is used to collect pupil images and scleral images The registration module 20 is used to save the scleral image as an authentication image when the pupil image matches the target area.

Please refer to FIG. 10, an embodiment of the present application provides a head-mounted device 100. The head mounted device 100 includes a display 40 and a processor 101. The processor 101 is connected to the display 40. The processor 101 is used to control the display 40 to display a guide image, the guide image includes a target area; and is used to collect pupil images and scleral images; and In the case where the pupil image matches the target area, the scleral image is saved as the authentication image.

The registration method of the head-mounted device 100, the registration device 10, and the head-mounted device 100 of the embodiment of the present application guide the user to register by guiding the target area of the image, and save the scleral image as the authentication image when the pupil image matches the target area, The authentication image can be made more accurate and complete, thereby improving the accuracy of sclera unlocking.

Understandably, the sclera is the opaque white part of the outermost layer of the eye. The blood vessel structure in the sclera is formed randomly and is unique for each person, which makes the scleral texture can be used for identification.

Specifically, the headset 100 may be an electronic device such as electronic glasses, electronic helmets, and headphones. The head mounted device 100 may also be an electronic device or a head mount display (HMD) of a smart watch. The specific form of the headset 100 is not limited here.

Please note that, for the convenience of description, the embodiment of the present application takes the head-mounted device 100 as an example of electronic glasses to explain the registration method of the head-mounted device 100 in the embodiment of the present application. This does not mean that the specific form of the headset 100 is limited.

The headset of the related art is usually unlocked by password unlocking or iris unlocking. When the user unlocks with a password, he needs to input numbers or words. Since the input and interaction of the headset mainly rely on smart handles or gesture recognition, password unlocking is not convenient enough and the unlocking time is long, resulting in poor user experience. Moreover, the password unlocking can be cracked by flashing the machine or an algorithm, which is less secure.

When the user unlocks through the iris unlocking method, the iris texture is less, the surface pigment is more or the instability caused by the light is strong, making the black iris difficult to read. In addition, it is difficult to miniaturize the image acquisition equipment that realizes iris recognition, and the image distortion caused by the use of ordinary lenses reduces the recognition reliability, and switching to customized equipment will increase the cost. In other words, it is difficult for an image acquisition device that realizes iris recognition to meet the requirements of miniaturization, low distortion, and low cost. Moreover, iris recognition needs to process a large amount of data, which requires high software and hardware. In addition, iris recognition requires higher positioning of eyes and pupils.

The headset 100 usually needs to be registered before being unlocked by human eyes. However, due to the user's habitual habits and other problems, such as squinting and closing the eyes, the user's eye image is often incomplete when registering, resulting in incomplete sample library, resulting in a low unlock success rate.

In the registration method of the head-mounted device 100 of this embodiment, when the pupil image matches the target area, the scleral image is saved as the authentication image, so that the user can unlock the head-mounted device 100 through the sclera when using the head-mounted device 100. In this way, the user can complete the unlocking while putting on the glasses, which can increase the unlocking speed and realize a senseless unlocking. Moreover, the scleral acquisition method is more convenient, and the acquisition equipment is cheaper and durable. Compared with iris recognition, only a common RGB camera with more than 1 million pixels can complete the scleral image acquisition, which can reduce the cost.

In step S14, the number of guide images may be one or more. When the number of guide images is multiple, step S14 to step S20 can be performed in a loop.

Referring to FIG. 11, in an example, the number of guide images is 4, which are guide image P1, guide image P2, guide image P3, and guide image P4. The target area of the guide image P1 is P11, the target area of the guide image P2 is P21, the target area of the guide image P3 is P31, and the target area of the guide image P4 is P41. First, the display 40 displays the guide image P1, and the head mounted device 100 collects the pupil image and the scleral image corresponding to the guide image P1, and when the pupil image matches the target area, the scleral image is saved as an authentication image. Then, the display 40 displays the guide image P2, and the head mounted device 100 collects the pupil image and the scleral image corresponding to the guide image P2, and when the pupil image matches the target area P21, the scleral image is saved as an authentication image. Next, the display 40 displays the guide image P3, and the head mounted device 100 collects the pupil image and the scleral image corresponding to the guide image P3, and when the pupil image matches the target area P31, the scleral image is saved as an authentication image. Finally, the display 40 displays the guide image P4, and the head mounted device 100 collects the pupil image and the scleral image corresponding to the guide image P4, and when the pupil image matches the target area P41, the scleral image is saved as an authentication image. At this point, the registration is complete.

Referring to FIGS. 1 and 2, the head mounted device 100 may include a collection device 110, and the collection device 110 is used to collect pupil images and scleral images of the user's eye 200. The number of the collection device 110 can be one, that is, the same collection device 110 can be used to collect pupil images and scleral images. The number of collection devices 110 may be two, that is, different collection devices 110 can be used to collect pupil images and scleral images respectively. Of course, the number of collection devices 110 may also be 3, 4 or other numbers. The specific number of collection devices 110 is not limited here.

In addition, pupil images and scleral images can be collected separately at the same time, or can be captured from the same eye image. It is also possible to collect pupil images first, and then collect scleral images when the pupil image matches the target area. The acquisition sequence and acquisition methods of pupil images and scleral images are not limited here.

In this embodiment, the number of the collection device 110 is one. The capture device 110 captures an eye image. In step S16, the processor 101 captures the eye image into a pupil image and a sclera image. Specifically, the image can be intercepted by binarization. Image binarization is based on the large gray value of the sclera in the human eye image, and a reasonable threshold is adopted to achieve the binarization of the eye image. For example, a threshold can be set, the area larger than the threshold is regarded as the scleral image, and the area smaller than the threshold is regarded as the non-scleral image, and its gray value is directly set to 0, so as to realize the interception of the scleral image. The method of capturing the pupil image is similar to the method of capturing the scleral image, and will not be repeated here.

In addition, the collection device 110 may include at least one of an RGB camera, a black and white camera, and an infrared camera. When the collection device 110 includes an infrared camera, the infrared camera can be matched with an infrared fill light.

In step S20, "the pupil image matches the target area" may refer to judging that the user's gaze direction falls within the target area according to the pupil image.

"Save scleral image as authentication image" can refer to directly save the scleral image, and then match the scleral image with the scleral unlock image in the subsequent unlock matching; it can also refer to processing the scleral image to obtain authentication feature information and save the authentication feature information. In the subsequent unlock matching, the scleral unlock image is authenticated according to the authentication feature information. The specific method of saving the scleral image as the authentication image is not limited here.

Referring to Figure 12, in some embodiments, the registration method includes:

Step S11: Control the head mounted device 100 to prompt the first prompt information;

Step S12: Obtain input information corresponding to the first prompt information;

Step S13: Determine the authentication password of the headset 100 according to the input information, the authentication password is used to add and/or delete the authentication image.

In some embodiments, the processor 101 is used to control the head mounted device 100 to prompt the first prompt information; and used to obtain input information corresponding to the first prompt information; and used to determine the authentication of the head mounted device 100 according to the input information. Password, the authentication password is used to add and/or delete the authentication image.

In this way, it is possible to prevent others from adding or deleting authentication images at will, and to improve the security of the headset 100. Specifically, in step S11, the first prompt information may be voice, text, or image. In the case that the first prompt information is voice, the first prompt information may be broadcast through the electro-acoustic element of the headset 100. In the case that the first prompt information is text or image, the first prompt information may be displayed through the display 40 of the head mounted device 100.

In step S12, the input information can be obtained through the acoustic and electrical components, the handle, or the camera of the headset 100. In other words, the user can input information through voice, text or gesture input. The specific method for the user to input the input information is not limited here.

In step S13, the authentication password can be English letters, numbers, other characters, etc. Of course, the authentication password can be a combination of at least two of English letters, numbers, and other characters.

In one example, the headset 100 includes a speaker. After the user enters the sclera registration process, the speaker prompts: "Please set a 6-digit unlocking password as a credential for adding or deleting the sclera." Then, the user inputs the password by voice: "123456" , The processor 101 obtains the voice input by the user, and determines that the authentication password is "123456" according to the voice. Then the monitor displays the guide image, collects the pupil image and the scleral image, and saves the scleral image as the authentication image when the pupil image matches the target area of the scleral image. When the user subsequently wants to delete the saved scleral image, the headset 100 prompts the user to enter a password. When the password entered by the user is also “123456”, the headset 100 deletes the saved scleral image.

Referring to FIG. 13, in another example, the head-mounted device 100 includes a display 40. After the user enters the sclera registration process, the display 40 displays: "Please set a 6-digit unlock password as a credential for adding or deleting the sclera." Then, the user Input the password: "123456" through the mobile phone, the processor 101 obtains the signal transmitted by the mobile phone, and determines the authentication password as "123456" according to the signal. Then the monitor displays the guide image, collects the pupil image and the scleral image, and saves the scleral image as the authentication image when the pupil image matches the target area of the scleral image. When the user subsequently wants to delete the saved scleral image, the headset 100 prompts the user to enter a password. When the password entered by the user is also “123456”, the headset 100 deletes the saved scleral image.

Please refer to Figure 14. In some embodiments, the registration method includes:

Step S15: Control the head mounted device 100 to prompt the second prompt information, the second prompt information is related to the target area.

In some embodiments, the processor 101 is configured to control the head mounted device 100 to prompt the second prompt information, and the second prompt information is related to the target area.

In this way, the user is prompted to look at the target area. Similarly, the second prompt information can be voice, text or image. In the case that the second prompt information is voice, the second prompt information may be broadcast through the electro-acoustic element of the headset 100. In the case that the second prompt information is text or image, the second prompt information may be displayed through the display 40 of the head mounted device 100.

In an example, the headset 100 includes a speaker, and the speaker prompts: "Please look at the upper dot." The display 40 displays the guide image P1, and the target area P11 of the guide image P1 is above the display 40. Next, the pupil image and the scleral image are collected, and when the pupil image matches the target area of the scleral image, the scleral image is saved as an authentication image. Then, the speaker prompts: "Please look at the dot below." The display 40 displays the guide image P2, and the target area P21 of the guide image P2 is below the display 40. Next, the pupil image and the scleral image are collected, and when the pupil image matches the target area of the scleral image, the scleral image is saved as an authentication image. Then, the speaker prompts: "Please look at the dot on the left." The display 40 displays the guide image P3, and the target area P31 of the guide image P3 is on the left side of the display 40. Next, the pupil image and the scleral image are collected, and when the pupil image matches the target area of the scleral image, the scleral image is saved as an authentication image. Finally, the speaker prompts: "Please look at the dot on the right." The display 40 displays the guide image P4, and the target area P41 of the guide image P4 is above the display 40. Next, the pupil image and the scleral image are collected, and when the pupil image matches the target area of the scleral image, the scleral image is saved as an authentication image.

Please refer to FIG. 15. In another example, the head-mounted device 100 includes a display 40, and the display 40 displays: "Please look at the upper dot." The display 40 displays the guide image P1, and the target area P11 of the guide image P1 is above the display 40. Next, the pupil image and the scleral image are collected, and when the pupil image matches the target area of the scleral image, the scleral image is saved as an authentication image. Then, the display 40 displays: "Please look at the dot below". The display 40 displays the guide image P2, and the target area P21 of the guide image P2 is below the display 40. Next, the pupil image and the scleral image are collected, and when the pupil image matches the target area of the scleral image, the scleral image is saved as an authentication image. Then, the display 40 displays: "Please look at the dot on the left". The display 40 displays the guide image P3, and the target area P31 of the guide image P3 is on the left side of the display 40. Next, the pupil image and the scleral image are collected, and when the pupil image matches the target area of the scleral image, the scleral image is saved as an authentication image. Finally, the display 40 displays: "Please look at the dot on the right." The display 40 displays the guide image P4, and the target area P41 of the guide image P4 is above the display 40. Next, the pupil image and the scleral image are collected, and when the pupil image matches the target area of the scleral image, the scleral image is saved as an authentication image.

In addition, before prompting the user to gaze at the target area, the user can also be prompted with third prompt information, such as: "wear glasses in a comfortable posture and follow the plane guide to complete registration." After the guide is completed, the user can also be prompted with the fourth prompt message. For example: "Registered successfully!" In this way, users can be further guided, which is conducive to improving user experience.

Please refer to Figure 16. In some embodiments, the registration method includes:

Step S17: When the pupil image matches the target area, control the color of the target area from the first color to the second color.

In some embodiments, the processor 101 is configured to control the color of the target area from the first color to the second color when the pupil image matches the target area.

In this way, the user is reminded that the pupil image matches the target area. Specifically, in this embodiment, the first color is red, and the second color is green. It can be understood that in still other embodiments, the first color and the second color may be other colors. In addition, other methods can be used to prompt the user to match the pupil image with the target area.

Referring to FIG. 17, in an example, the display 40 displays a guide image P1, and the target area P11 of the guide image P1 is above the display 40. Next, the pupil image and the scleral image are collected, and when the pupil image matches the target area of the scleral image, the scleral image is saved as an authentication image. Then, the control display 40 displays: "Matching is successful!"

Referring to FIG. 18, in an example, the display 40 displays a guide image P1, and the target area P11 of the guide image P1 is above the display 40. Next, the pupil image and the scleral image are collected, and when the pupil image matches the target area of the scleral image, the scleral image is saved as an authentication image. Then, the control target area is changed from the first color to the second color.

For example, in a case where the pupil image matches the target area, the head mounted device 100 is controlled to vibrate. Or, when the pupil image matches the target area, control the electro-acoustic element of the head-mounted device 100 to announce: "Matching is successful!" The specific method for prompting the user to match the pupil image with the target area is not limited here.

Referring to Figure 19, in some embodiments, the registration method includes:

Step S18: Determine the gaze area of the guide image according to the pupil image;

Step S19: When the gaze area matches the target area, it is determined that the pupil image matches the target area.

In some embodiments, the processor 101 is configured to determine the gaze area of the guide image according to the pupil image; and, when the gaze area matches the target area, determine that the pupil image matches the target area.

In this way, it is determined that the pupil image matches the target area. Specifically, after the gaze area of the user on the guide image is determined according to the pupil image, in step S19, the deviation value between the gaze area and the target area can be calculated, and if the deviation value is less than or equal to the preset deviation threshold, the gaze is determined The area matches the target area.

Referring to FIG. 20, in some embodiments, the authentication image includes authentication feature information, and step S20 includes:

Step S202: Perform feature enhancement processing on the scleral image;

Step S204: Perform feature extraction on the processed scleral image to obtain authentication feature information.

In some embodiments, the authentication image includes authentication feature information, and the processor 101 is used to perform feature enhancement processing on the scleral image; and used to perform feature extraction on the processed scleral image to obtain the authentication feature information.

In this way, saving the scleral image as an authentication image is realized. Specifically, in step S202, the scleral image can be extracted first. If a color image is acquired, each pixel contains three components R, G, and B. Since the G component of the image has the highest gray value, G can be extracted. The components form a picture, and then the G-component picture is enhanced by the histogram equalization method to obtain the scleral image with enhanced features. It can be understood that the feature enhancement processing can filter out the background other than the blood vessel texture in the scleral image.

In step S204, a Scale-invariant Feature Transform (SIFT) algorithm may be used to extract feature points to obtain authentication feature information. Specifically, the following steps may be sequentially performed on the processed scleral image: Gaussian difference filtering; detecting scale space extreme points; accurately locating feature points; determining the main direction of feature points; generating SIFT feature vectors and serving as SIFT feature descriptors. Then, the authentication feature information can be obtained according to the obtained SIFT feature descriptor.

Please refer to Figure 21. In some embodiments, the registration method includes:

Step S22: Acquire an unlocked sclera image;

Step S26: Determine whether the sclera unlock image matches the authentication image;

Step S28: when the sclera unlock image matches the authentication image, unlock the headset 100.

In some embodiments, the processor 101 is used to collect a scleral unlock image; and used to determine whether the sclera unlock image matches the authentication image; and used to unlock the headset 100 when the sclera unlock image matches the authentication image. .

In this way, the unlocking of the headset is realized. Specifically, in step S22, the device that collects the sclera unlock image may be the collection device 110. In step S26, the number of authentication images may be one or more. In the case where the number of authentication images is multiple, it may be determined whether the scleral unlocking image matches each authentication image, and when the scleral unlocking image matches each authentication image, the head mounted device 100 is unlocked.

In step S28, unlocking the headset 100 may refer to switching the headset 100 from the sleep state to the running state. Alternatively, the head-mounted device 100 is in a running state, but is locked, and the user cannot operate or interfere. Unlocking the head-mounted device 100 allows the user to operate the head-mounted device 100. It can also refer to unlocking one or more functions of the headset 100. The specific form of unlocking the headset 100 is not limited here.

Referring to FIG. 22, in some embodiments, step S26 includes:

Step S262: Perform feature enhancement processing on the scleral unlock image;

Step S264: Perform feature extraction on the processed sclera unlock image to obtain unlock feature information;

Step S266: When the unlocking feature information matches the authentication feature information, it is determined that the scleral unlocking image matches the authentication image.

In some embodiments, the processor 101 is used to perform feature enhancement processing on the scleral unlock image; and used to perform feature extraction on the processed sclera unlock image to obtain unlock feature information; If the information matches, it is determined that the scleral unlock image matches the authentication image.

In this way, it is possible to determine whether the scleral unlock image matches the authentication image. As mentioned above, feature enhancement processing can be performed on the scleral image; feature extraction can be performed on the processed scleral image to obtain authentication feature information. Therefore, the scleral unlock image can be processed in a manner similar to the scleral image to obtain unlock feature information and match the unlock feature information with the authentication feature information.

Specifically, the Euclidean distance between the feature information and the feature point descriptor corresponding to the authentication feature letter can be unlocked as the similarity criterion for feature point matching. The smaller the Euclidean distance, the higher the degree of similarity. When the Euclidean distance is less than the preset unlocking threshold, it can be determined that the unlocking feature information matches the authentication feature information, thereby determining that the scleral unlocking image matches the authentication image, and then unlocking the headset 100.

The specific method of performing feature enhancement processing on the sclera unlock image and performing feature extraction on the processed sclera unlock image to obtain unlocking feature information can refer to the previous part of processing the scleral image, which will not be repeated here.

Please refer to Figure 23. In some embodiments, the registration method includes:

Step S23: Obtain training pictures;

Step S24: Use a machine learning algorithm to train a matching judgment model according to the training pictures, and the matching judgment model is used to determine whether the scleral unlock image matches the authentication image.

In some embodiments, the processor 101 is used to obtain training pictures; and used to train a matching judgment model using a machine learning algorithm based on the training pictures, and the matching judgment model is used to determine whether the sclera unlock image matches the authentication image.

In this way, the accuracy of unlocking the sclera can be improved. Specifically, in step S23, the training pictures may include special training pictures such as a dark-light sclera picture, a reflective sclera picture, a multi-angle sclera picture, and a twin sclera picture. In this way, the adaptability of the wearable device 100 to scenes such as dark light, reflection, twins, etc., can be further improved.

Specifically, the machine learning algorithm can be selected from decision trees, random forest algorithms, logistic regression, support vector machines (Support Vector Machine, SVM), naive Bayes, K nearest neighbor algorithm, K means algorithm, AdaBoost algorithm, neural network, Any one of Markov and its components.

Referring to FIG. 24, in some embodiments, the head mounted device 100 includes an infrared camera, and step S22 includes:

Step S222: Collect infrared images through an infrared camera;

Step S224: processing the infrared image to obtain the sclera unlocking image;

Registration methods include:

Step S25: Determine whether the subject of the infrared image is a living body according to the infrared image; and if the subject is a living body, go to step S26;

Step S27: If the subject is not a living body, ignore the infrared image.

In some embodiments, the head-mounted device 100 includes an infrared camera, and the processor 101 is used to collect infrared images through the infrared camera; and used to process the infrared images to obtain the scleral unlock image; and used to determine the infrared image based on the infrared image. Whether the subject is a living body; and for determining whether the sclera unlock image matches the authentication image when the subject is a living body; and for ignoring the infrared image when the subject is not a living body.

In this way, the live detection of unlocking the sclera is realized. It is understandable that due to the reflection of infrared light by the cornea, the infrared image captured by the infrared camera will have a "flare" phenomenon in the pupil area. Therefore, this phenomenon can be used to complete the live detection of sclera recognition, thereby improving the prevention of scleral unlocking. Attack ability. In this way, it is possible to prevent the sclera unlock image forged by photos, videos or masks from unlocking the headset 100.

Specifically, the infrared camera may include an infrared projector and an infrared receiver. The infrared projector is used to emit and reflect infrared rays, and the infrared receiver is used to collect infrared images of the user's eyes. Unlike RGB cameras, the feature point extraction of infrared cameras is based on infrared images.

It is understandable that the active lighting method of the infrared projector can obtain the infrared image of the sclera with more stable brightness, which can avoid the problem of poor scleral image quality collected by the RGB camera under dark light conditions, and can reduce the configuration complexity of the scleral recognition algorithm. It is helpful to improve the success rate of unlock recognition.

Please refer to FIG. 10, an embodiment of the present application provides a head-mounted device 100. The head mounted device 100 includes a processor 101 and a memory 102. The memory 102 stores one or more programs, and when the programs are executed by the processor 101, the registration method of the head-mounted device 100 of any one of the foregoing embodiments is implemented.

For example, perform: Step S14: Control the display 40 of the head mounted device 100 to display a guide image, and the guide image includes the target area; Step S16: Collect pupil images and scleral images; Step S20: Save the sclera when the pupil image matches the target area The image serves as the authentication image.

The embodiment of the present application also provides a computer-readable storage medium. One or more non-volatile computer-readable storage media containing computer-executable instructions, when the computer-executable instructions are executed by one or more processors 101, cause the processor 101 to execute the registration method of any of the foregoing embodiments.

The head-mounted device 100 and the computer-readable storage medium of the embodiment of the present application guide the user to register by guiding the target area of the image. When the pupil image matches the target area, saving the scleral image as the authentication image can make the authentication image more accurate And complete, thereby improving the accuracy of sclera unlocking.

Those skilled in the art can understand that the structure shown in the figure is only a schematic diagram of part of the structure related to the solution of the present application, and does not constitute a limitation on the headset 100 to which the solution of the present application is applied. The device 100 may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it may include the processes of the above-mentioned method embodiments. Among them, the storage medium may be a magnetic disk, an optical disc, a read-only memory (Read-Only Memory, ROM), etc.

The above examples only express a few implementations of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation to the patent scope of the present application. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can be made, and these all fall within the protection scope of this application. Therefore, the scope of protection of the patent of this application shall be subject to the appended claims.

Claims

A method for registering a headset, characterized in that, the registering method includes:

Controlling the display of the head-mounted device to display a guide image, the guide image including a target area;

Collect pupil images and scleral images;

In the case where the pupil image matches the target area, the scleral image is saved as an authentication image.
The method for registering a head-mounted device according to claim 1, wherein the registering method comprises:

Controlling the headset to prompt first prompt information;

Acquiring input information corresponding to the first prompt information;

The authentication password of the headset is determined according to the input information, and the authentication password is used to add and/or delete the authentication image.
The method for registering a head-mounted device according to claim 1, wherein the registering method comprises:

Control the headset to prompt second prompt information, where the second prompt information is related to the target area.
The method for registering a head-mounted device according to claim 1, wherein the registering method comprises:

In a case where the pupil image matches the target area, controlling the color of the target area from a first color to a second color.
The method for registering a head-mounted device according to claim 1, wherein the registering method comprises:

Determining the gaze area of the guide image according to the pupil image;

In a case where the gaze area matches the target area, it is determined that the pupil image matches the target area.
The method for registering a head-mounted device according to claim 1, wherein the authentication image includes authentication feature information, and saving the sclera image as the authentication image includes:

Performing feature enhancement processing on the scleral image;

Perform feature extraction on the processed scleral image to obtain authentication feature information.
The method for registering a headset according to claim 6, wherein the registering method comprises:

Acquire unlocking images of sclera;

Determining whether the sclera unlock image matches the authentication image;

In the case where the scleral unlock image matches the authentication image, unlock the headset.
The method for registering a head-mounted device according to claim 7, wherein the head-mounted device comprises an infrared camera, and collecting images of the sclera unlocking includes:

Collecting infrared images through the infrared camera;

Processing the infrared image to obtain the sclera unlocking image;

The registration method includes:

Determining whether the subject of the infrared image is a living body according to the infrared image;

In the case that the subject is a living body, enter the step of determining whether the sclera unlocking image matches the authentication image;

In the case that the subject is not a living body, the infrared image is ignored.
A registration device for a head-mounted device, wherein the registration device includes a guide module, a collection module, and a registration module, and the guide module is used to control a display of the head-mounted device to display a guide image, and the guide image includes Target area; the acquisition module is used to acquire pupil images and scleral images; the registration module is used to save the scleral image as an authentication image when the pupil image matches the target area.
A head-mounted device, characterized in that the head-mounted device includes a display and a processor, the processor is connected to the display, and the processor is used to control the display to display a guide image, and the guide image includes a target area And used to collect pupil images and scleral images; and used to save the scleral image as an authentication image when the pupil image matches the target area.
The head-mounted device according to claim 10, wherein the processor is used to control the head-mounted device to prompt first prompt information; and used to obtain input information corresponding to the first prompt information; and The authentication password of the headset is determined according to the input information, and the authentication password is used to add and/or delete the authentication image.
The head-mounted device according to claim 10, wherein the processor is configured to control the head-mounted device to prompt second prompt information, and the second prompt information is related to the target area.
The head-mounted device according to claim 10, wherein the processor is configured to control the color of the target area from a first color to a second color when the pupil image matches the target area. colour.
The head-mounted device according to claim 10, wherein the processor is configured to determine the gaze area of the guide image according to the pupil image; and is configured to match the gaze area with the target area Next, it is determined that the pupil image matches the target area.
The head-mounted device according to claim 10, wherein the authentication image includes authentication feature information, and the processor is used to perform feature enhancement processing on the scleral image; and used to perform feature enhancement processing on the scleral image after processing; Perform feature extraction to obtain authentication feature information.
The head-mounted device according to claim 15, wherein the processor is used to collect a sclera unlock image; and used to determine whether the sclera unlock image matches the authentication image; and used to unlock the sclera If the image matches the authentication image, unlock the headset.
The head-mounted device according to claim 16, wherein the head-mounted device comprises an infrared camera, and the processor is used for collecting infrared images through the infrared camera; and used for processing the infrared image to obtain the Sclera unlock image; and used to determine whether the subject of the infrared image is a living body according to the infrared image; and used to determine the sclera unlock image and the authentication when the subject is a living body Whether the images match; and for ignoring the infrared image when the subject is not a living body.
The head-mounted device according to claim 10, wherein the head-mounted device comprises:

A refractive member provided on one side of the display; and

An adjustment mechanism connected to the refractive component, and the adjustment mechanism is used to adjust the form of the refractive component to adjust the refractive power of the refractive component.
A head-mounted device, characterized in that, the head-mounted device includes a memory and a processor, the memory stores one or more programs, and when the programs are executed by the processor, any of claims 1-8 is implemented. The registration method of the headset described in item 1.
A non-volatile computer-readable storage medium containing computer-executable instructions, wherein when the computer-executable instructions are executed by one or more processors, the processor is caused to execute claims 1-8 The registration method of a headset described in any one of.