Identity access method and device of virtual reality equipment, equipment, medium and program product

Abstract

The invention provides an identity access method for virtual reality equipment, which can be applied to the technical field of artificial intelligence. The identity access method of the virtual reality equipment comprises the following steps: in response to a situation that a to-be-identified object wears the virtual reality equipment, under the condition that the authorization of the to-be-identified object to collected eye information is acquired, performing iris authentication and dynamic authentication on the to-be-identified object, the dynamic authentication is realized by monitoring the change of pupils of the to-be-identified object; obtaining a first authentication authority through the iris authentication; obtaining a second authentication authority through the dynamic authentication; and giving an identity access permission to the to-be-identified object in response to the fact that the first authentication permission and the second authentication permission are successful in authentication. The invention further provides an identity access device and equipment of the virtual reality equipment, a storage medium and a program product.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and more specifically, to an identity access method, apparatus, device, medium and program product for a virtual reality device. Background Art

[0002] With the development of science and technology, virtual reality technology has been gradually improved, and a variety of virtual reality devices have entered social life and are applied to all aspects of the real world. With the application of virtual reality devices, the demand for the security of virtual reality devices and user identity authentication has gradually become prominent. How to achieve fast and convenient identity authentication for users of virtual reality devices, ensure that the user of the device is indeed the owner himself, to prevent the user's identity from being impersonated, and at the same time avoid the risk of the user's identity being impersonated due to the loss of access credentials, is a problem that needs to be considered and solved.

[0003] The current technologies for identity authentication of virtual reality devices mainly include: password credential authentication technology and face recognition authentication technology. Password credential authentication technology is: after the user wears the virtual reality device, the user's hand clicks on the virtual keyboard to complete the password input, and the background user credentials are compared to complete the authentication access. Face recognition authentication technology is: the camera on the head-mounted virtual reality device captures facial features from various angles, splices the images to form facial data, and completes identity authentication after realizing the recognition and comparison of facial features.

[0004] The current identity authentication technology has the following problems.

[0005] Password Credential Authentication Technology:

[0006] 1. Susceptible to theft and impersonation: A password is a static authentication method. Users may forget their passwords, or their passwords may be stolen, guessed, or misappropriated by others, resulting in security risks.

[0007] 2. Poor user experience: Users need to remember passwords and enter them manually, which may increase user authentication time and reduce user experience.

[0008] 3. Risk of password theft: In a virtual reality environment, users may be spied on or monitored when entering their passwords, and their passwords may be guessed based on the location and order of finger clicks, increasing the risk of password leakage.

[0009] Face recognition verification technology:

[0010] 1. Affected by light and environment: In low light or complex environments, the accuracy of face recognition may be affected, resulting in authentication failure or misidentification.

[0011] 2. Vulnerable to attacks: Facial recognition technology may be attacked by counterfeit photos and videos, making the authentication process easy to be deceived.

[0012] 3. Privacy issues: Facial recognition requires obtaining the user’s facial information, which may cause privacy leaks and cause concerns. Summary of the invention

[0013] In view of the above problems, the present disclosure provides a method, apparatus, device, medium and program product for identity access of a virtual reality device.

[0014] According to a first aspect of the present disclosure, there is provided an identity access method for a virtual reality device, comprising: in response to an object to be identified wearing the virtual reality device, and in the case of obtaining authorization from the object to be identified for collecting eye information, performing iris authentication and dynamic authentication on the object to be identified, wherein the dynamic authentication is achieved by monitoring changes in the pupils of the object to be identified; obtaining a first authentication authority through iris authentication; obtaining a second authentication authority through dynamic authentication; and in response to the first authentication authority and the second authentication authority being authenticated, granting the object to be identified an identity access authority.

[0015] According to an embodiment of the present disclosure, performing iris authentication on an object to be identified includes: collecting an eye image of the object to be identified; performing iris positioning on the eye image to determine the iris position; segmenting an iris area image, a sclera area image, and an eye skin area image from the eye image based on the iris position; extracting iris area image features, sclera area image features, and eye skin area image features for feature fusion to form a multimodal iris feature; storing the multimodal iris feature of the object to be identified; and in response to the object to be identified being a non-first-time registered user, matching the multimodal iris feature with a registered multimodal iris feature to determine a first authentication authority, wherein matching the multimodal iris feature with a registered multimodal iris feature to determine the first authentication authority includes: in response to the multimodal iris feature matching one of the registered multimodal iris features, setting the first authentication authority to authentication passed.

[0016] According to an embodiment of the present disclosure, collecting the eye image of the object to be identified includes: supplementing the light of the object to be identified by a constant backlight of a screen of a virtual reality device; and capturing the eye image by two cameras inside the virtual reality device.

[0017] According to an embodiment of the present disclosure, extracting iris region image features, sclera region image features, and periocular skin region image features for feature fusion includes: extracting iris region image features, sclera region image features, and periocular skin region image features respectively based on different feature extraction methods; unifying iris region image features, sclera region image features, and periocular skin region image features into features of the same dimension based on a deep feature embedding network; and performing feature fusion based on a fusion strategy.

[0018] According to an embodiment of the present disclosure, storing the multimodal iris features of the object to be identified includes: adding a timestamp to the multimodal iris features; and in response to the object to be identified being a first-time registered user, adding a registration identifier to the multimodal iris features as registered multimodal iris features.

[0019] According to an embodiment of the present disclosure, in response to the object to be identified being a user who is not registering for the first time, dynamic authentication is performed on the object to be identified.

[0020] According to an embodiment of the present disclosure, dynamic authentication of the object to be identified includes: controlling the screen of the virtual reality device to display an annular aperture on the screen in the form of ripple diffusion and contraction; monitoring the pupil of the object to be identified according to the change of the annular aperture; and in response to the change of the pupil, setting the second authentication authority to authentication passed.

[0021] According to an embodiment of the present disclosure, changes in the annular aperture include changes in brightness, size, and distance.

[0022] A second aspect of the present disclosure provides an identity access device for a virtual reality device, comprising: an identification module, for, in response to an object to be identified wearing the virtual reality device, performing iris authentication and dynamic authentication on the object to be identified in the case of obtaining authorization from the object to be identified for collecting eye information, wherein the dynamic authentication is achieved by monitoring changes in the pupils of the object to be identified; a first access module, for obtaining a first authentication authority through iris authentication; a second access module, for obtaining a second authentication authority through dynamic authentication; and an authorization module, for granting the object to be identified identity access authority in response to the first authentication authority and the second authentication authority being authenticated.

[0023] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0024] The fourth aspect of the present disclosure further provides a computer-readable storage medium having a computer program or instructions stored thereon, which implements the steps of the above method when the above computer program or instructions are executed by a processor.

[0025] The fifth aspect of the present disclosure further provides a computer program product, including a computer program or instructions, which implement the steps of the above method when the above computer program or instructions are executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0027] Figure 1 A diagram schematically shows an application scenario of the identity admission method, apparatus, device, medium, and program product of a virtual reality device according to an embodiment of the present disclosure;

[0028] Figure 2 A flowchart of an identity admission method for a virtual reality device according to an embodiment of the present disclosure is schematically shown;

[0029] Figure 3 A flowchart of performing iris authentication on an object to be identified according to an embodiment of the present disclosure is schematically shown;

[0030] Figure 4 A flowchart of dynamically authenticating an object to be identified according to an embodiment of the present disclosure is schematically shown;

[0031] Figure 5 A flowchart schematically shows an identity admission process of a virtual reality device according to an embodiment of the present disclosure;

[0032] Figure 6 A structural block diagram of an identity admission device for a virtual reality device according to an embodiment of the present disclosure is schematically shown;

[0033] Figure 7 A structural block diagram schematically shows the functional modules of the first admission module and the second admission module according to an embodiment of the present disclosure; and

[0034] Figure 8 A block diagram of an electronic device suitable for implementing an identity admission method for a virtual reality device according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0035] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0036] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0037] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0038] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0039] In the technical solution of the present disclosure, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0040] To facilitate a better understanding of the identity access method, apparatus, device, medium, and program product of a virtual reality device according to an embodiment of the present disclosure, the relevant terms involved in the embodiment of the present disclosure are introduced as follows.

[0041] Iris technology: It is a technology based on the iris of the eyeball for identity recognition. The human eyeball is composed of sclera, iris, pupil, lens, retina and other parts. The iris is formed during the fetal development stage and remains unchanged throughout the life course, which determines the uniqueness of the iris characteristics and also ensures the uniqueness of identity recognition.

[0042] Virtual reality technology: Virtual reality technology (VR) is a computer simulation system that can create and experience a virtual world. It uses computers to generate a simulated environment to immerse users in the environment.

[0043] The identity access method of a virtual reality device provided by an embodiment of the present disclosure includes: in response to an object to be identified wearing a virtual reality device, and in the case of obtaining authorization from the object to be identified for collecting eye information, performing iris authentication and dynamic authentication on the object to be identified, wherein the dynamic authentication is achieved by monitoring changes in the pupils of the object to be identified; obtaining a first authentication authority through iris authentication; obtaining a second authentication authority through dynamic authentication; and in response to the first authentication authority and the second authentication authority being authenticated, granting the identity access authority to the object to be identified.

[0044] The identity access method for a virtual reality device provided by the embodiment of the present disclosure has the following technical effects:

[0045] 1. Provide a more accurate and anti-theft identity access method. As one of the biometric features, the iris is formed during the fetal development stage and remains unchanged throughout the life course. This ensures the uniqueness of the iris feature and also determines the uniqueness of identity recognition. Using the iris for identity authentication is more accurate and reduces the potential risk of identity fraud and misjudgment.

[0046] 2. Provide a more private and more acceptable identity access method. With the increasing awareness of protecting personal privacy, iris information is more concealed than facial information, can better hide the user's personal characteristics, and can be better accepted by users, thereby protecting the user's image privacy from being violated and hiding appearance characteristics.

[0047] 3. Provide a more comprehensive dynamic identity access method, adding dynamic authentication on the basis of iris authentication, monitoring the size change of the pupil according to the brightness change of the screen light source to determine whether it is a real user. Double authentication makes the authentication process safer and more reliable.

[0048] Figure 1 The following schematically shows an application scenario diagram of the identity admission method for a virtual reality device according to an embodiment of the present disclosure.

[0049] like Figure 1 As shown, the application scenario 100 according to this embodiment may include wearing a virtual display device to experience a virtual world. The network 104 is used as a medium for providing a communication link between the first virtual reality device 101, the second virtual reality device 102, the third virtual reality device 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0050] The first virtual reality device 101, the second virtual reality device 102, and the third virtual reality device 103 are electronic devices with display screens and support web browsing. Users can use the first virtual reality device 101, the second virtual reality device 102, and the third virtual reality device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various applications can be installed on the first virtual reality device 101, the second virtual reality device 102, and the third virtual reality device 103, such as video playback applications, game entertainment applications, tool applications, creative design applications, education and learning applications, life service applications, etc. (only for example).

[0051] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the virtual reality devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the virtual reality devices.

[0052] It should be understood that Figure 1 The number of virtual reality devices, networks, and servers in the embodiment is only for illustration. Any number of terminal devices, networks, and servers may be provided as required.

[0053] The following will be based on Figure 1 The scene described by Figure 2~Figure 5 The identity access method of the virtual reality device of the disclosed embodiment is described in detail.

[0054] Figure 2 The following schematically shows a flow chart of an identity admission method for a virtual reality device according to an embodiment of the present disclosure.

[0055] like Figure 2 As shown, the identity access method of the virtual reality device of this embodiment includes operations S210 to S240, and operations S210 to S240 of this embodiment can be performed by the virtual reality device.

[0056] In operation S210, in response to the subject to be identified wearing the virtual reality device, and in the case of obtaining the authorization of the subject to be identified for collecting eye information, iris authentication and dynamic authentication are performed on the subject to be identified, wherein the dynamic authentication is achieved by monitoring changes in the pupils of the subject to be identified.

[0057] In an embodiment of the present disclosure, before obtaining user information (such as the user's image or video information), the user's consent or authorization may be obtained. Specifically, after monitoring that the object to be identified is wearing a virtual reality device, a request to obtain user information may be sent to the object to be identified, for example, obtaining the authorization of the object to be identified to collect eye information. When the object to be identified authorizes the collection of eye information, iris authentication and dynamic authentication are performed on the object to be identified.

[0058] In some embodiments, the user's authorization to collect eye information includes: collecting the user's eye image, monitoring eye pupil changes, etc. The user's eye image includes an eye image (ie, an eyeball image) and an image of the skin area around the eye.

[0059] Dynamic authentication is used to monitor whether the object to be identified is a living object, to prevent the problem of identity fraud when using photos for identity authentication. Specifically, dynamic monitoring can be performed by monitoring the changes in the pupils of the object to be identified, for example, monitoring the changes in the pupils of the object to be identified with changes in ambient light.

[0060] The identity access method for a virtual reality device provided in the embodiment of the present disclosure uses a dual authentication method of iris authentication and dynamic authentication to authenticate the user wearing the virtual reality device in order to ensure that the virtual reality device is used by a real person who is a registrant (e.g., owner) of the virtual reality device, thereby making the identity access process more secure and reliable.

[0061] In operation S220, a first authentication authority is acquired through iris authentication.

[0062] Obtaining the first authentication authority through iris authentication includes: image acquisition, iris positioning, iris segmentation, iris feature extraction, data storage, iris authentication and other operations. In the following, reference will be made to Figure 3 The operation process of obtaining the first authentication authority through iris authentication is described in detail.

[0063] In operation S230, a second authentication authority is acquired through dynamic authentication.

[0064] Obtaining the second authentication authority through dynamic authentication includes: adjusting the aperture, monitoring pupil changes, dynamic authentication and other operations. In the following, reference will be made to Figure 4 A detailed description of the operational process of obtaining the second authentication authority through dynamic authentication.

[0065] In operation S240, in response to the first authentication authority and the second authentication authority being authenticated, the identity access authority of the object to be identified is granted.

[0066] In some embodiments, only when the authentication results of iris authentication and dynamic authentication are both passed, it is determined that the object to be identified is the real person wearing the virtual reality device, and the object to be identified is allowed to use the virtual reality device. Due to the uniqueness of the iris and the more concealed iris information, iris authentication improves the accuracy of identity authentication, reduces the risk of identity fraud and misjudgment, and hides the user's appearance features; dynamic authentication can prevent the use of photos, videos, etc. to obtain authorization to use virtual reality devices, reduce the risk of being deceived, and reduce the risk of the device owner (i.e., registrant) identity being used; dual authentication makes the identity access process safer and more reliable.

[0067] It should be noted that in the embodiments of the present disclosure, a corresponding operation entry may be provided for the user to choose to agree or reject the automated decision result. That is, before the user information is automatically processed / decided, an instruction to agree or reject the processing / decision entered by the user through the corresponding operation entry may be obtained. If the user agrees to the processing / decision, the user information is automatically processed / decided, that is, operations S210 and S240 are executed. If the user refuses to perform the processing / decision, the expert decision process is entered.

[0068] Figure 3 The flowchart of performing iris authentication on an object to be identified according to an embodiment of the present disclosure is schematically shown.

[0069] like Figure 3 As shown, performing iris authentication on the object to be identified includes operations S310 to S360. Operations S310 to S360 of this embodiment can be executed by a virtual reality device.

[0070] In operation S310 , an eye image of a subject to be identified is acquired.

[0071] In some embodiments, collecting the eye image of the object to be identified includes: providing fill light to the object to be identified by using a constant backlight of a screen of a virtual reality device; and capturing the eye image by using two cameras inside the virtual reality device.

[0072] In some embodiments, after the user puts on the head-mounted virtual reality device, he enters the authentication access process of the virtual reality device and becomes the role to be authenticated (i.e., the object to be identified). The virtual reality device prompts the object to be identified through the screen to start authentication, and then keeps the screen displaying a constant backlight to fill in the light for the object to be identified. For example, after starting the authentication, the screen displays a constant pure white backlight to fill in the light for iris photography of the object to be identified. It should be noted that the use of the constant backlight of the screen to fill in the light for the object to be identified is only exemplary and not a limitation of the embodiments of the present disclosure. In other embodiments, other methods may be used to fill in the light for the object to be identified.

[0073] Inside the head-mounted virtual reality device, eye images are captured by two cameras on the inner lens of the device. Specifically, the built-in camera of the device is used to capture features such as the two eyeballs and irises of the object to be identified. The built-in camera can be used to capture multiple eye images for each eye, so as to select an iris image that meets the requirements from the multiple eye images.

[0074] In some embodiments, the collection of eye images of the object to be identified is performed based on the head-mounted virtual reality device itself. It can be performed automatically only after the user wears the virtual reality device. No extra operations are required, which is simple and fast in terms of safety and reliability.

[0075] After the eye image of the object to be identified is acquired, in operation S320, iris positioning is performed on the eye image to determine the iris position.

[0076] In some embodiments, before performing iris positioning on an eye image, it is necessary to first perform a quality assessment on multiple collected eye images to determine whether these images are defocused, whether there is blurred lighting, whether there is eyelash occlusion, whether the pupil is excessively deformed, etc., and select an eye image with the clearest iris texture, no occlusion, and no deformation from these images for iris positioning. Determining the iris position includes determining the size and position of the inner and outer circles of the iris. For example, the iris position can be determined by an edge detection algorithm. If the image quality assessment passes and the iris position is determined, the selected eye image is subjected to the next segmentation operation.

[0077] Exemplarily, for the collected eye images, if there is no eye image that passes the quality assessment and can locate the iris position among all the eye images, the eye image of the object to be identified is re-collected.

[0078] In operation S330, an iris region image, a sclera region image, and an eye skin region image are segmented from the eye image based on the iris position.

[0079] In some embodiments, pupil size may change with changes in light intensity, causing deformation of the annular area of ​​the iris. Therefore, before segmenting the eye image after iris positioning, the eye image can be normalized to reduce the impact of changes in ambient light intensity on pupil size, and the normalized eye image can be segmented.

[0080] The iris position provides an accurate spatial reference for the segmentation operation. Based on the iris position, the position of the sclera can be determined, and then the range of the periocular area can be determined to improve the accuracy of the segmentation. The eye image segmentation can be divided into iris elements and non-iris elements. The iris element (i.e., iris) is the main identification part of the embodiment, and the non-iris element is the secondary identification part of the embodiment. The non-iris element includes sclera, periocular skin, eyelashes, etc. Specifically, the eye image can be segmented into iris area image, sclera area image, and periocular skin area image. For example, the normalized eye image is segmented using the Transformer segmentation method based on deep learning, and the iris area image, sclera area image, and periocular skin area image are segmented from the eye image for multimodal iris feature extraction. It should be noted that the segmentation of the eye image based on the Transformer segmentation method is only exemplary and not a limitation of the embodiments of the present disclosure. In other embodiments, other segmentation methods can be used to segment the eye image.

[0081] In some embodiments, after the iris region image, sclera region image, and periocular skin region image are segmented, the segmented images can be evaluated, and the NICE.1 competition algorithm evaluation indicators such as accuracy (ACC), precision (Precision), recall (Recal), F1 score (F1 Score), and mean intersection over union (mIoU) can be used to quantify whether the segmentation indicators are qualified. For example, the iris region image is evaluated, and the NICE.1 competition algorithm evaluation indicators are used to quantify whether the iris segmentation indicators are qualified. If the indicators are qualified, the multimodal iris feature extraction stage is entered; if the indicators are unqualified, re-authentication is performed, for example, the eye image of the object to be identified is re-collected. The segmented iris region image, sclera region image, and periocular skin region image are used to extract multimodal iris features.

[0082] In operation S340, the image features of the iris region, the image features of the sclera region, and the image features of the skin region around the eye are extracted and fused to form a multi-modal iris feature.

[0083] In some embodiments, the iris, sclera, and skin around the eye have their own texture information. Specifically, the iris and sclera (i.e., the white part of the eye) together constitute the main structure of the eyeball that is displayed externally. The iris and sclera have different texture features. The iris is a ring-shaped, fine stripe structure, while the sclera is generally white with sparse vascular texture. The skin texture around the eye socket also presents usable biological features, such as fine wrinkles and pores on the skin. Selecting iris region features, sclera region features, and skin region features around the eye for feature combination (e.g., forming a trimodal iris feature) can obtain identity features of more dimensions, increase the amount of information for recognition, and help enhance the uniqueness of recognition.

[0084] According to an embodiment of the present disclosure, extracting iris region image features, sclera region image features, and periocular skin region image features for feature fusion includes: extracting iris region image features, sclera region image features, and periocular skin region image features respectively based on different feature extraction methods; unifying iris region image features, sclera region image features, and periocular skin region image features into features of the same dimension based on a deep feature embedding network; and performing feature fusion based on a fusion strategy.

[0085] Since the iris region, sclera region, and periocular skin region have their own texture features, different feature extraction methods can be used to extract iris region image features, sclera region image features, and periocular skin region image features, respectively. For example, a Gabor wavelet filter is used to extract the texture of the iris region, and wavelet filters with different parameters are used to extract the vascular texture of the sclera region. Through wavelet filters with different parameters (for example, different frequencies and different directions), rich multi-scale features can be extracted in the iris region and the sclera region. For the image features of the periocular skin region, a wavelet filter can be used for feature extraction, or other feature extraction methods can be used for feature extraction. It should be noted that the use of a wavelet filter for feature extraction is only exemplary and not a limitation of the embodiments of the present disclosure. In other embodiments, other methods can be used to extract iris region image features, sclera region image features, and periocular skin region image features. In addition, geometric features such as the contour of the periocular skin and the inner and outer edges of the iris can be extracted by an edge detection algorithm, which will not be described here.

[0086] After extracting the image features of the iris region, the image features of the sclera region, and the image features of the skin region around the eyes, these features need to be aligned and normalized to ensure feature fusion at a uniform scale, brightness, and rotation angle, thereby improving the comparison accuracy. Specifically, by utilizing a deep feature embedding network (e.g., a multi-branch convolutional neural network, a shared parameter network), the image features of the iris region, the image features of the sclera region, and the image features of the skin region around the eyes are unified into features of the same dimension, and features of different modalities (iris, sclera, and skin texture around the eyes) are mapped to the same feature space. It should be noted that the use of a deep feature embedding network to unify the iris features, sclera features, and skin texture features around the eyes into features of the same dimension is merely exemplary and is not a limitation to the embodiments of the present disclosure. In other embodiments, other methods may be used to align and normalize these features.

[0087] In some embodiments, the iris region image features, sclera region image features, and periocular skin region image features in the same feature space may be fused into a hyperspace feature vector (i.e., a multimodal iris feature) based on a fusion strategy. Specifically, the fusion strategy may be to use an attention mechanism to focus on the most recognizable region in the eye image, for example, by generating a weight distribution in a weighted manner, increasing the weight of the iris region, assigning lower weights to the sclera region and the skin texture region, and fusion of the iris region image features, sclera region image features, and periocular skin region image features into a hyperspace feature vector based on their respective weights.

[0088] In some embodiments, a multi-input convolutional neural network (CNN) is used to achieve feature fusion. The iris region image, sclera region image, and periocular skin region image segmented from the eye image of the object to be identified are input respectively, and different branches of the multi-input convolutional neural network extract the deep features of each modality, and then the cross-modal feature fusion is achieved through a fully connected layer or an attention mechanism to form a multi-modal iris feature.

[0089] In the embodiments of the present disclosure, different feature extraction methods are used to extract rich multi-scale features from the iris area, sclera area and skin area around the eye, thereby increasing the amount of information for recognition and enhancing the uniqueness of recognition. A multimodal fusion feature extraction method is introduced to fuse iris features with other biological features (such as sclera, skin texture around the eye socket, etc.) to form a multimodal iris feature description, which helps to improve recognition accuracy.

[0090] In some embodiments, after the multimodal iris feature is formed, the multimodal iris feature can be evaluated and the multimodal iris feature extraction evaluation index can be calculated. Specifically, the obtained multimodal iris feature is evaluated by calculating the three indicators of false reception rate (FAR), false rejection rate (FRR), and equal error rate (EER). If the evaluation passes, the multimodal iris feature is stored in the local cache area of ​​the head-mounted virtual reality device; otherwise, re-authentication is required.

[0091] In operation S350, the multimodal iris features of the object to be recognized are stored.

[0092] Storing the multimodal iris features of the object to be identified includes: adding a timestamp to the multimodal iris features; and in response to the object to be identified being a first-time registered user, adding a registration identifier to the multimodal iris features as registered multimodal iris features.

[0093] In some embodiments, after the multimodal iris feature is formed, a timestamp corresponding to the time of this acquisition (for example, a timestamp unique identifier ID) may be added to the multimodal iris feature, and the multimodal iris feature may be identified, and the identified multimodal iris feature may be stored in a storage area of ​​the virtual reality device. When a subsequent matching operation is performed, the multimodal iris feature can be quickly found from the storage area based on the timestamp to be compared with the multimodal iris feature retained during the first registration and authentication.

[0094] Furthermore, if the object to be identified is a user who registers for the first time, after adding the timestamp mark to the multi-model iris feature, a registration mark may be added to the multi-model iris feature, for example, a registered multi-modal iris feature mark. The multi-model iris feature with the registration mark added is stored in the storage area as a registered multi-modal iris feature, and is used to compare with the multi-modal iris feature formed each time the iris feature extraction operation performs feature extraction.

[0095] In an embodiment of the present disclosure, there may be multiple registered multimodal iris features, and the virtual reality device may allow multiple users to register, and add a respective registration mark to each registrant to form multiple registered multimodal iris features. Multiple users share the right to use the virtual reality device. For example, a head-mounted virtual display device may include three or more registered users.

[0096] Exemplarily, storing the identified multimodal iris features in the local storage area of ​​the virtual reality device can achieve rapid and convenient finding of the multimodal iris features during iris authentication, thereby improving authentication efficiency; and it helps to perform iris authentication based on the head-mounted virtual reality device itself, without the need for extra operations (without the need for other equipment), and is simple and portable.

[0097] After the multimodal iris feature is stored, in operation S360, in response to the object to be identified being a user who is not registering for the first time, the multimodal iris feature is matched with the registered multimodal iris feature to determine the first authentication authority.

[0098] Matching the multimodal iris feature with the registered multimodal iris features to determine the first authentication authority includes: in response to the multimodal iris feature matching one of the registered multimodal iris features, setting the first authentication authority to authentication passed.

[0099] In some embodiments, the multi-model iris features formed based on the eye image of the object to be identified are matched with the stored registered multi-modal iris features, the object to be identified is authenticated, and it is determined whether the object to be identified has the right to use the virtual reality device. For example, the head-mounted virtual display device may include three registered users, and the multi-model iris features of the object to be identified are matched with the registered multi-modal iris features of the three registered users respectively. If the multi-modal iris features of the object to be identified match one of the registered multi-modal iris features, the object to be identified is one of the multiple registered users and has the right to use the virtual reality device, and the iris authentication result of the object to be identified is set to authentication passed.

[0100] A deep learning-based feature matching strategy can be used to match the multimodal iris features with the stored registered multimodal iris features. For example, the ArcFace algorithm based on the classification loss function can be used for matching. If the match is successful, the iris authentication is passed. If the multimodal iris features do not match the registered multimodal iris features, the authentication fails, and the eye image of the object to be identified can be recaptured for iris authentication. It should be noted that the use of the ArcFace algorithm for matching is only exemplary and is not a limitation to the embodiments of the present application. In other embodiments, other feature matching algorithms can be used.

[0101] In some embodiments, after iris authentication is passed, identity access condition one is met.

[0102] The identity access method of the virtual reality device provided by the embodiment of the present disclosure uses multimodal iris features for identity authentication. For users, compared with facial information, multimodal iris features are more concealed, and do not collect user appearance features, so users are more accepting. The user's iris and other images are transformed into multimodal iris feature vectors through information conversion, and the multimodal iris feature vectors are stored locally in the virtual reality device to increase the hiding of user information. In addition, user privacy is not collected arbitrarily in violation of regulations, privacy protection is good, and user acceptance is high.

[0103] The embodiments of the present disclosure adopt a multimodal iris feature extraction method in the iris feature extraction module. The multimodal iris features include iris image features, sclera image features, and periocular skin image features, and a feature fusion strategy is used for feature fusion. The introduction of a multimodal fusion iris feature extraction method can significantly improve the robustness and anti-counterfeiting ability of the system.

[0104] In the process of iris authentication of the object to be identified in the embodiment of the present disclosure, image acquisition, iris positioning, iris segmentation, iris segmentation evaluation, feature extraction, feature extraction evaluation, data storage and iris authentication operations are all performed by the head-mounted virtual reality device itself. All authentication processes can be automatically performed after the user only needs to wear the virtual reality device, and the implementation method is simple and fast.

[0105] According to an embodiment of the present disclosure, in response to the object to be identified being a non-first-time registered user, the object to be identified is dynamically authenticated. Figure 4 Describe in detail the operational process of dynamic authentication of the object to be identified.

[0106] After determining that the object to be identified is not a first-time registered user, dynamic authentication is performed on the object to be identified, which can avoid unnecessary authentication operations and improve authentication efficiency. For example, if the object to be identified is a first-time registered user, dynamic authentication is not required.

[0107] Figure 4 A flowchart of dynamically authenticating an object to be identified according to an embodiment of the present disclosure is schematically shown.

[0108] like Figure 4 As shown, the dynamic authentication of the object to be identified includes operations S410 to S430.

[0109] In operation S410, the screen of the virtual reality device is controlled to display a ring-shaped aperture in the screen in the form of ripple expansion and contraction.

[0110] The screen of the virtual reality device can display various forms of ambient light. Specifically, the screen of the virtual reality device can display constant light, changing light, etc. For example, when collecting eye images, a constant backlight is displayed. Here, in order to better monitor the changes in the pupils of the object to be identified, the screen displays a ring aperture in the form of ripple expansion and contraction.

[0111] In operation S420, the pupil of the object to be identified is monitored according to the change of the annular aperture.

[0112] According to an embodiment of the present disclosure, changes in the annular aperture include changes in brightness, size, and distance.

[0113] In some embodiments, by changing the distance, size or brightness of the annular aperture displayed on the screen, the ambient light source changes, stimulating the expansion and contraction of the pupil size, so that the change in the light source corresponds to the slight change in the expansion and contraction of the pupil size, and the pupil change corresponds to the change in the ripple aperture of the screen. By stimulating pupil changes with various forms of ambient light, it is helpful to quickly monitor pupil changes, thereby quickly performing dynamic authentication and improving authentication efficiency.

[0114] According to an embodiment of the present disclosure, monitoring the pupil of the object to be identified according to changes in the annular aperture includes: monitoring the pupil based on an infrared sensor inside the virtual reality device.

[0115] In some embodiments, an infrared sensor in front of the eyeball inside a head-mounted virtual reality device is used to capture changes in pupil size of the object to be identified in real time, and changes in pupil size are captured according to changes in ambient light sources (for example, real-time changes in the annular aperture of the screen). For example, when the light is strong, the pupil of the real person to be authenticated will shrink, and when the light is weak, the pupil of the real person to be authenticated will dilate.

[0116] In operation S430, in response to the pupil changing, the second authentication authority is set to authentication passed.

[0117] The pupil changes in size corresponding to the ring aperture light source, and the virtual reality device can determine that it is a real person who is performing identity authentication, and set the second authentication authority to pass the authentication; otherwise, the real identity of the authenticator is in doubt, and a re-authentication or authentication failure prompt is prompted. After the pupil monitoring passes, the second identity access condition is met.

[0118] Exemplarily, in the process of dynamic authentication of the object to be identified, light source changes, pupil monitoring and dynamic authentication are all performed by the head-mounted virtual reality device itself, and can be performed automatically only after the user wears the virtual reality device.

[0119] In some embodiments, if both iris authentication and pupil change authentication (i.e., identity access condition one and identity access condition two) are authenticated, that is, double-layer authentication is passed, it can be determined that the object to be identified is a real person performing iris recognition authentication, and is the registrant himself, and the object to be identified is granted identity access authority.

[0120] The identity access method for a virtual reality device provided by the embodiment of the present disclosure controls the screen of the virtual reality device to display ambient light in the form of ripple diffusion and contraction, which can quickly and effectively stimulate pupil changes, improve authentication efficiency, and shorten authentication time; it adopts iris recognition technology combined with dynamic pupil change monitoring technology, and ensures that the iris authenticated user is indeed the user himself while ensuring that it is the real user who is performing the authentication, rather than the attacker directly using the iris image to bypass the real person for authentication, thereby increasing the security of virtual reality device access on the basis of practicality.

[0121] The embodiments of the present disclosure are based on the head-mounted virtual reality device itself. All authentication processes can be automatically performed after the user wears the virtual reality device, without the need for extra operations. The user's learning cost is not increased on the basis of authority control over the use of the virtual reality device, and the requirements of safety and reliability are achieved simply and quickly.

[0122] Figure 5The following is a flowchart schematically showing an identity admission process of a virtual reality device according to an embodiment of the present disclosure.

[0123] like Figure 5 As shown, the identity access process of the virtual reality device includes: 501 image acquisition, 502 iris positioning, 503 iris segmentation, 504 iris segmentation evaluation, 505 feature extraction, 506 feature extraction evaluation, 507 data storage, 508 iris authentication, 509 light source change, 510 pupil monitoring, 511 identity access, and 512 re-authentication.

[0124] In some embodiments, in response to the object to be identified wearing the virtual reality device, in step 501, image acquisition is performed to acquire the eye image of the object to be identified; in step 502, iris positioning is performed to locate the iris on the eye image and determine the iris position; in step 503, iris segmentation is performed to segment the iris area image, sclera area image, and eye skin area image from the eye image based on the iris position; in step 504, iris segmentation evaluation is performed to evaluate the result of iris segmentation. If the evaluation fails, the process proceeds to step 512 for re-authentication. If the evaluation passes, the process proceeds to step 505; in step 505, Feature extraction, extracting iris area image features, sclera area image features, and periocular skin area image features for feature fusion to form multimodal iris features; in step 506, feature extraction evaluation is performed to evaluate the multimodal iris features of the object to be identified. If the evaluation fails, go to step 512 for re-authentication. If the evaluation passes, go to step 507; in step 507, data storage is performed to store the multimodal iris features of the object to be identified, and determine whether the object to be identified is a first-time registered user. If it is a first-time registered user, the process ends. If it is not a first-time registered user, go to steps 508 and 509.

[0125] In step 508, iris authentication is performed, the multimodal iris feature is matched with the registered multimodal iris feature, and the first authentication authority is determined. If the iris authentication fails (i.e., the multimodal iris feature does not match the registered multimodal iris feature), the process proceeds to step 512 for re-authentication. If the iris authentication passes (i.e., the multimodal iris feature matches one of the registered multimodal iris features), the process proceeds to step 511.

[0126] In step 509, the light source is changed to control the screen of the virtual reality device to display a ring-shaped aperture in the form of ripple diffusion and contraction. In step 510, pupil monitoring is performed to monitor the pupil of the object to be identified according to the change of the ring-shaped aperture. If the pupil monitoring fails (i.e., the pupil has not changed), the process proceeds to step 512 for re-authentication. If the pupil monitoring passes (i.e., the pupil has changed), the process proceeds to step 511.

[0127] In step 511, identity access is performed. In response to the first authentication authority and the second authentication authority being authenticated, the identity access authority of the object to be identified is granted, and the process ends.

[0128] In some embodiments, identity precondition one and identity access condition two are serial conditions, and identity access can be enabled only when they are met at the same time. Identity access means that the identity information of the person to be authenticated does belong to the owner of this virtual reality device, the information is true, and the person has the right to access and use it.

[0129] In the embodiment of the present disclosure, when the judgment condition is not passed, the re-authentication step is entered, and the virtual reality device screen will prompt the person to be authenticated that re-authentication is required, and the previous steps such as image acquisition are repeated for re-authentication.

[0130] The identity access method of the virtual reality device provided in the embodiment of the present disclosure verifies the biometric features of the user of the virtual reality device, such as the iris, sclera, and skin around the eyes, through iris recognition technology to ensure that the registrant himself is using the device, and at the same time monitors the corresponding scaling of the pupil size through the brightness change of the ambient light to ensure that the registrant is wearing the virtual reality device for verification, rather than using a processed iris image for fraudulent authentication. The identity access method provides a more accurate, more private, and more comprehensive and secure identity access mechanism for virtual reality devices.

[0131] Based on the above-mentioned identity access method for virtual reality device, the present disclosure also provides an identity access device for virtual reality device. Figure 6 The device is described in detail.

[0132] Figure 6 The structural block diagram of the identity admission device of the virtual reality device according to the embodiment of the present disclosure is schematically shown.

[0133] like Figure 6 As shown, the identity access device 600 of the virtual reality device of this embodiment includes an identification module 610, a first access module 620, a second access module 630 and an authorization module 640.

[0134] The recognition module 610 is used for performing iris authentication and dynamic authentication on the object to be identified in response to the object to be identified wearing the virtual reality device, and obtaining the authorization of the object to be identified for collecting eye information, wherein the dynamic authentication is achieved by monitoring the changes in the pupils of the object to be identified. In one embodiment, the recognition module 610 can be used to perform the operation S210 described above, which will not be repeated here.

[0135] The first access module 620 is used to obtain the first authentication authority through iris authentication. In one embodiment, the first access module 620 can be used to perform the operation S220 described above, which will not be repeated here.

[0136] The second access module 630 is used to obtain the second authentication authority through dynamic authentication. In one embodiment, the second access module 630 can be used to perform the operation S230 described above, which will not be repeated here.

[0137] The authorization module 640 is used to grant the identity access authority to the object to be identified in response to the first authentication authority and the second authentication authority being authenticated. In one embodiment, the authorization module 640 can be used to perform the operation S240 described above, which will not be repeated here.

[0138] According to an embodiment of the present disclosure, the first admission module 620 is also used to perform the above-mentioned operations S310 to S360, which will not be repeated here.

[0139] According to an embodiment of the present disclosure, the second admission module 630 is also used to perform the above-mentioned operations S410 to S430, which will not be repeated here.

[0140] According to an embodiment of the present disclosure, the first access module 620 includes multiple functional modules for performing iris authentication on the object to be identified, and the second access module 630 also includes multiple functional modules for performing dynamic authentication on the object to be identified. Figure 7 Each functional module of the first admission module 620 and the second admission module 630 is described in detail.

[0141] Figure 7 The structural block diagram of the functional modules of the first admission module and the second admission module according to an embodiment of the present disclosure is schematically shown.

[0142] like Figure 7 As shown, the functional modules of the first access module and the second access module of the identity access device of the virtual reality device include: an image acquisition module 701, an iris positioning module 702, an iris segmentation module 703, an iris feature extraction module 704, a data storage module 705, an iris authentication module 706, a light source change module 707, a pupil monitoring module 708 and a dynamic authentication module 709.

[0143] According to an embodiment of the present disclosure, the first access module 620 includes an image acquisition module 701, an iris positioning module 702, an iris segmentation module 703, an iris feature extraction module 704, a data storage module 705, and an iris authentication module 706, and these functional modules are used for iris authentication of the object to be identified. Specifically, the image acquisition module 701 can perform the above operation S310; the iris positioning module 702 can perform the above operation S320; the iris segmentation module 703 can perform the above operation S330; the iris feature extraction module 704 can perform the above operation S340; the data storage module 705 can perform the above operation S350; and the iris authentication module 706 can perform the above operation S360.

[0144] According to an embodiment of the present disclosure, the second admission module 630 includes a light source change module 707, a pupil monitoring module 708 and a dynamic authentication module 709, which are used to dynamically authenticate the object to be identified. Specifically, the light source change module 707 can perform the above operation S410; the pupil monitoring module 708 can perform the above operation S420; and the dynamic authentication module 709 can perform the above operation S430.

[0145] The detailed method steps for identity access of the object to be identified have been described in detail in the identity access method of the virtual reality device. Here, the specific implementation of each functional module in the identity access device of the virtual reality device will not be described in detail.

[0146] According to an embodiment of the present disclosure, any multiple modules among the identification module 610, the first access module 620, the second access module 630 and the authorization module 640, or any multiple modules among the image acquisition module 701, the iris positioning module 702, the iris segmentation module 703, the iris feature extraction module 704, the data storage module 705 and the iris authentication module 706, or any multiple modules among the light source change module 707, the pupil monitoring module 708 and the dynamic authentication module 709 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the identification module 610, the first access module 620, the second access module 630, the authorization module 640, the image acquisition module 701, the iris positioning module 702, the iris segmentation module 703, the iris feature extraction module 704, the data storage module 705, the iris authentication module 706, the light source change module 707, the pupil monitoring module 708, and the dynamic authentication module 709 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging circuits, or can be implemented in any one of the three implementation methods of software, hardware, and firmware, or in an appropriate combination of any of them. Alternatively, at least one of the identification module 610, the first access module 620, the second access module 630, the authorization module 640, the image acquisition module 701, the iris positioning module 702, the iris segmentation module 703, the iris feature extraction module 704, the data storage module 705, the iris authentication module 706, the light source change module 707, the pupil monitoring module 708, and the dynamic authentication module 709 can be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is executed.

[0147] Figure 8 A block diagram of an electronic device suitable for implementing an identity admission method for a virtual reality device according to an embodiment of the present disclosure is schematically shown.

[0148] like Figure 8As shown, the electronic device 800 according to an embodiment of the present disclosure includes a processor 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage part 808 to a random access memory (RAM) 803. The processor 801 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 801 may also include an onboard memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0149] In RAM 803, various programs and data required for the operation of electronic device 800 are stored. Processor 801, ROM 802 and RAM 803 are connected to each other via bus 804. Processor 801 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 802 and / or RAM 803. It should be noted that the program can also be stored in one or more memories other than ROM 802 and RAM 803. Processor 801 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0150] According to an embodiment of the present disclosure, the electronic device 800 may further include an input / output (I / O) interface 805, which is also connected to the bus 804. The electronic device 800 may further include one or more of the following components connected to the input / output (I / O) interface 805: an input portion 806 including a keyboard, a mouse, etc.; an output portion 807 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 808 including a hard disk, etc.; and a communication portion 809 including a network interface card such as a LAN card, a modem, etc. The communication portion 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the input / output (I / O) interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed, so that the computer program read therefrom is installed into the storage portion 808 as needed.

[0151] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0152] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 802 and / or RAM 803 described above and / or one or more memories other than ROM 802 and RAM 803.

[0153] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the identity access method of the virtual reality device provided by the embodiment of the present disclosure.

[0154] The above functions defined in the system / device of the embodiment of the present disclosure are executed when the computer program is executed by the processor 801. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0155] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 809, and / or installed from a removable medium 811. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0156] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 809, and / or installed from the removable medium 811. When the computer program is executed by the processor 801, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0157] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0158] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0159] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0160] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for identity access of a virtual reality device, characterized in that: The method comprises: In response to the subject to be identified wearing the virtual reality device, and in the case of obtaining the authorization of the subject to be identified for collecting eye information, iris authentication and dynamic authentication are performed on the subject to be identified, wherein the dynamic authentication is achieved by monitoring changes in the pupils of the subject to be identified; Acquiring a first authentication authority through the iris authentication; Acquiring a second authentication authority through the dynamic authentication; and In response to the first authentication authority and the second authentication authority being authenticated, the identity access authority of the object to be identified is granted.

2. The method according to claim 1, characterized in that The performing iris authentication on the object to be identified comprises: Acquiring an eye image of the object to be identified; Performing iris positioning on the eye image to determine the iris position; Segmenting an iris region image, a sclera region image, and an eye skin region image from the eye image based on the iris position; Extract the image features of the iris area, the sclera area, and the skin area around the eye for feature fusion to form multimodal iris features; storing the multimodal iris features of the object to be identified; and In response to the object to be identified being a user who is not registering for the first time, matching the multimodal iris feature with the registered multimodal iris feature to determine the first authentication authority, The matching of the multimodal iris feature with the registered multimodal iris feature to determine the first authentication authority includes: In response to the multimodal iris feature matching one of the registered multimodal iris features, the first authentication authority is set to authentication passed.

3. The method according to claim 2, characterized in that The acquiring of the eye image of the object to be identified comprises: Filling the object to be identified with light by means of a constant backlight of the screen of the virtual reality device; and The eye image is captured by two cameras inside the virtual reality device.

4. The method according to claim 2, characterized in that: The extracting of the image features of the iris region, the image features of the sclera region, and the image features of the skin region around the eye for feature fusion comprises: Based on different feature extraction methods, respectively extract the image features of the iris region, the image features of the sclera region, and the image features of the skin region around the eye; Unifying the iris region image features, the sclera region image features, and the periocular skin region image features into features of the same dimension based on a deep feature embedding network; and Feature fusion is performed based on fusion strategy.

5. The method according to claim 2, characterized in that: The storing of the multimodal iris features of the object to be identified comprises: Adding a timestamp to the multiple models' iris features; and In response to the object to be identified being a first-time registered user, a registration mark is added to the multi-modal iris feature as the registered multi-modal iris feature.

6. The method according to claim 2, characterized in that In response to the object to be identified being a user who is not registering for the first time, dynamically authenticating the object to be identified.

7. The method according to claim 1, characterized in that The dynamically authenticating the object to be identified comprises: Controlling the screen of the virtual reality device to display a ring-shaped aperture in the screen in the form of ripple expansion and contraction; Monitoring the pupil of the object to be identified according to the change of the annular aperture; and In response to the pupil changing, the second authentication authority is set to authentication passed.

8. The method according to claim 7, characterized in that The changes of the annular aperture include changes in brightness, size and distance.

9. An identity access device for a virtual reality device, characterized in that: The device comprises: an identification module, configured to, in response to the subject to be identified wearing the virtual reality device, perform iris authentication and dynamic authentication on the subject to be identified in the case where the subject to be identified authorizes the collection of eye information, wherein the dynamic authentication is achieved by monitoring changes in the pupils of the subject to be identified; A first access module, used for obtaining a first authentication authority through the iris authentication; A second access module, configured to obtain a second authentication authority through the dynamic authentication; and The authorization module is used to grant the identity access authority to the object to be identified in response to the first authentication authority and the second authentication authority being authenticated.

10. An electronic device, comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images