Multi-factor authentication system and method based on AR device

By combining voice recognition and palm print recognition on AR devices, using random number voice authentication and palm print authentication, the problem of insufficient user authentication security on AR devices is solved, and efficient and safe AR devices are achieved Authentication.

CN113918909BActive Publication Date: 2024-11-05JINAN UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111012004.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-08-31
Publication Date
2024-11-05
Estimated Expiration
2041-08-31

AI Technical Summary

Technical Problem

The user authentication method directly transplanted on AR devices in the prior art has security problems, such as shoulder-snooping and video recording attacks, and a single authentication factor cannot effectively protect the security of AR devices.

Method used

Using a multi-factor authentication system based on AR devices, combining voice recognition and palm print recognition, random number voice authentication and palm print authentication, user authentication is realized using voice recognition API and camera, and the mean hashing algorithm and interpolation hashing algorithm are used for Palm line characteristics comparison.

Benefits of technology

Effectively resist shoulder-snooping and video attacks, improve the security and authentication availability of AR devices, provide a safe and efficient multi-factor authentication method, and reduce hardware cost requirements.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113918909B_ABST
    Figure CN113918909B_ABST
Patent Text Reader

Abstract

The present invention discloses a multi-factor authentication system and method based on AR devices, the system includes an input module, a display module, a storage module and a verification module; wherein the input module is mainly responsible for the voice input of random number voice authentication and the palm print interception input of palm print authentication and transmits them to the storage module for storage or the verification module for verification; the display module is responsible for the user interface display of the AR device, including the display of the authentication method, the display of the random number and the display of the authentication result; the storage module is responsible for storing the password and palm print entered by the user; the verification module is responsible for reading the correction value and palm print input by the input module and the password and palm print in the storage module, and verifying, and returning the verification result to the display module for display. The present invention enriches the user authentication means of the AR device and improves the security of the AR device, and does not require the support of complex hardware equipment, and the use cost is relatively low, which is conducive to the practical application and promotion.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of identity authentication, and specifically relates to a multi-factor authentication system and method based on an AR device. Background Art

[0002] With the rapid development of AR technology, people will enjoy more and more convenience brought by AR technology in shopping, games, engineering and other fields. At present, the industry pays more attention to the development and display of AR content, but there is still a gap in the research on AR security issues. AR security has become an issue that needs to be solved urgently.

[0003] The current mainstream user authentication methods are knowledge-based authentication: such as string passwords, gesture passwords, etc., and authentication based on biometrics: fingerprint recognition, face recognition. However, if these mainstream user authentication methods are directly transplanted to AR devices, some security issues may arise. For example: using gesture passwords to enter unchangeable secrets for identity authentication in public places will usually be subject to attackers using shoulder surfing or video recording to steal the secret. AR devices require an authentication method that is more suitable for their interactive characteristics. Therefore, the present invention designs a random number password authentication: an initial random number (R) is generated by a secure random number generator and displayed on the user's screen. Then, the user inputs a correction value based on the random number voice, so that the result of adding it to the random number bit by bit and modulo 10 is equal to the user password, and the user password is concealed by replacing the user password with the correction value, which can effectively resist attacks such as shoulder surfing and video recording.

[0004] At the same time, a single authentication factor has limited security protection for AR, and the use of multiple authentication factors can better ensure the security of AR. Therefore, the present invention combines the other verification methods currently available on mobile devices (such as fingerprint and face recognition) and proposes a new verification method for AR identity authentication: palmprint recognition. Users only need to place their hands in front of the camera for identification, which is a more suitable authentication method for AR devices. In terms of security, the security and verification pass rate of palmprint recognition are also based on image processing and comparison algorithms. As long as the accuracy of the algorithm is guaranteed, the security of the entire solution can be guaranteed. Summary of the invention

[0005] The main purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art and provide a multi-factor authentication system and method based on AR devices.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In one aspect of the present invention, a multi-factor authentication system based on an AR device is provided, comprising an input module, a display module, a storage module, and a verification module;

[0008] The input module includes a voice recognition module and a palm print recognition module; the user inputs and recognizes voice and palm prints through the voice recognition module and the palm print recognition module; the input data is transmitted to the storage module or the verification module;

[0009] The display module is used for the user interface display of the AR device, including the display of the authentication mode options, the display of the random number and the display of the authentication result;

[0010] The storage module is used to receive and store the password and palm print entered by the user;

[0011] The verification module is used to read the user's voice and palm print input by the input module, and perform random number voice verification and palm print authentication with the password and palm print in the storage module, and return the verification result to the display module for display.

[0012] As a preferred technical solution, the input module, display module, storage module and verification module acquire data or read file data and communicate between modules through methods provided by C# scripts.

[0013] As a preferred technical solution, the speech recognition module is used for speech input and recognition, specifically:

[0014] Receive user's voice input;

[0015] Upload the recorded voice input clips for recognition through the voice recognition API;

[0016] Get the return result through the speech recognition API;

[0017] The returned result is transmitted to the storage module for storage, or transmitted to the verification module for random number voice authentication.

[0018] As a preferred technical solution, the palmprint recognition module is used for voice input and recognition, specifically:

[0019] The user places his palm in front of the camera of the palm print recognition module and clicks the palm print capture button to obtain the user's palm image.

[0020] Convert the user's palm image into YUV mode, and use the skin color threshold in the YUV mode to filter to obtain a binary black and white palm image;

[0021] Using the black and white user's palm image as a mask, obtain the user's palm image with the background removed;

[0022] According to the black and white user palm image, the user palm center is obtained based on the distance transformation and the region of interest, and the inscribed circle of the user palm center is obtained according to its maximum radius, and the inscribed square of the inscribed circle is intercepted to obtain the user palm print pattern;

[0023] The user's palm print pattern is transmitted to the storage module for storage, or transmitted to the verification module for palm print authentication.

[0024] As a preferred technical solution, the random number voice authentication is specifically as follows:

[0025] The verification module generates a random number with the same number of digits as the password and transmits it to the display module for display;

[0026] The user performs calculations based on the preset password and the current random number, and inputs a correction value through the voice recognition module;

[0027] The verification module reads the password pre-set by the user in the storage module and the correction value input by the input module, and verifies whether the result after adding the random number and the correction value bit by bit and modulo 10 bit by bit is equal to the password pre-set by the user. If so, the authentication result is set to authentication passed, otherwise it is set to authentication failed, and the authentication result is returned to the display module for display.

[0028] As a preferred technical solution, the palmprint authentication is specifically as follows:

[0029] The verification module reads the user's palm print pattern pre-entered by the user in the storage module and the user's palm print pattern input by the input module.

[0030] The mean hash algorithm and the interpolation hash algorithm are used to calculate the similarity between the input user palm print pattern and the pre-entered user palm print pattern. If the similarity is lower than the set threshold, the authentication result is set to authentication passed, otherwise it is set to authentication failed, and the authentication result is returned to the display module for display.

[0031] Another aspect of the present invention further provides a multi-factor authentication method based on an AR device, which is applied to the multi-factor authentication system based on an AR device, and includes the following steps:

[0032] S1. The user registers an account with the multi-factor authentication system and saves basic personal information in the storage module of the multi-factor authentication system;

[0033] S2. The user inputs the user password and the user's palm print for random number voice authentication through the input module, and the multi-factor authentication system binds the user password to the user account and stores them in the storage module;

[0034] S3, the multi-factor authentication system intercepts the user's palm print and extracts the user's palm print features, and binds the user's palm print features to the user account and stores them in the storage module;

[0035] S4. Select the user account that needs to be logged in;

[0036] S5. The multi-factor authentication system generates a random number and verifies the correction value entered by the user. If the verification fails, the user account to be logged in is reselected;

[0037] S6. The user inputs the palm print through the input module, and the verification module intercepts the user's palm print and extracts the user's palm print features, and then compares the user's palm print features with the palm print features of known users for verification. If the verification fails, the user account to be logged in is reselected; if the verification succeeds, the verification is completed.

[0038] As a preferred technical solution, the multi-factor authentication system intercepts the user's palm print and extracts the user's palm print features, specifically comprising the following steps:

[0039] S31, the multi-factor authentication system captures the user's palm image;

[0040] S32, converting the user palm image obtained in step S31 into a YUV mode, filtering using a skin color threshold in the YUV mode to obtain a binary black-and-white image, and using the black-and-white image as a mask to obtain a user palm image with the background removed;

[0041] S33. According to the black and white image obtained in step S32, the center of the palm is obtained based on the distance transformation and the region of interest, and the inscribed circle of the palm is drawn according to the maximum radius, and the inscribed square of the inscribed circle is intercepted to obtain the user's palm print pattern.

[0042] As a preferred technical solution, the multi-factor authentication system generates a random number and verifies the correction value input by the user, specifically including the following steps:

[0043] S51, the multi-factor authentication system generates a random number for authentication using a random number generation algorithm, and displays the random number to the user through a display module;

[0044] S52, the user calculates the correction value according to the random number obtained in step S51 and the user password and inputs it into the system through voice input module;

[0045] S53. The multi-factor authentication system verifies the correction value entered by the user and returns a verification result, and displays the verification result to the user through a display module.

[0046] As a preferred technical solution, the verification module intercepts the user's palm print and extracts the user's palm print features, and then compares the user's palm print features with the known user's palm print features for verification, which specifically includes the following steps:

[0047] S61, the verification module captures a user's palm image;

[0048] S62, converting the user palm image obtained in step S61 into a YUV mode, filtering using a skin color threshold in the YUV mode to obtain a binary black-and-white palm image, and using the black-and-white image as a mask to obtain a user palm image with the background removed;

[0049] S63, according to the black and white image obtained in step S62, the center of the palm is obtained based on the distance transformation and the region of interest, and the inscribed circle of the palm is drawn according to the maximum radius, and the inscribed square of the inscribed circle is intercepted to obtain the palm print pattern of the user;

[0050] S64, using a mean hash algorithm and a difference hash algorithm to perform similarity calculation on the palm print pattern of the user obtained in step S63 and the palm print pattern of the selected login user account;

[0051] S65. Determine whether the verification is successful based on the palm print similarity obtained in step S64, and display the result to the user through a display module.

[0052] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0053] (1) The present invention proposes a multi-factor AR device user authentication method, which provides a safe and efficient polyphonetic character user authentication method for many AR devices, enriches the user authentication means of AR devices and improves the security of AR devices, and can take into account both the security and usability of user authentication.

[0054] (2) The present invention does not require the support of complex hardware equipment, and can complete user identification and authentication by relying solely on the AR camera and microphone commonly found on AR devices. The cost of use is relatively low, which is very conducive to the practical application and promotion of the present invention.

[0055] (3) The random number voice authentication scheme proposed in the present invention can effectively resist shoulder surfing and video recording attacks, enrich the identity authentication methods of AR devices and improve the security of AR devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a schematic diagram of the architecture of a multi-factor authentication system based on an AR device according to an embodiment of the present invention;

[0057] Figure 2 is an operation flow chart of random number voice authentication according to an embodiment of the present invention;

[0058] Figure 3It is the user interface of the random number voice authentication in the embodiment of the present invention.

[0059] Figure 4 is an operation flow chart of palmprint extraction and recognition according to an embodiment of the present invention;

[0060] Figure 5 This is the user interface for palmprint authentication in the embodiment of the present invention.

[0061] Figure 6 It is an intuitive schematic diagram of palmprint extraction and recognition according to an embodiment of the present invention. DETAILED DESCRIPTION

[0062] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0063] Example

[0064] like Figure 1 As shown, this embodiment provides a multi-factor authentication system based on an AR device, characterized in that it includes an input module, a display module, a storage module and a verification module;

[0065] The input module includes a voice recognition module and a palm print recognition module; the user inputs and recognizes voice and palm prints through the voice recognition module and the palm print recognition module; the input data is transmitted to the storage module or the verification module;

[0066] The display module is used for the user interface display of the AR device, including the display of the authentication method, the display of the random number and the display of the authentication result;

[0067] The storage module is used to receive and store the password and palm print entered by the user;

[0068] The verification module is used to read the user's voice and palm print input by the input module, and perform random number voice verification and palm print authentication with the password and palm print in the storage module, and return the verification result to the display module for display;

[0069] The input module, display module, storage module and verification module acquire data or read file data and communicate between modules through the method provided by the C# script.

[0070] The working steps of the speech recognition module are:

[0071] Receive user's voice input;

[0072] Upload the recorded voice input clips for recognition through the voice recognition API;

[0073] Get the return result through the speech recognition API;

[0074] The returned result is transmitted to the storage module for storage, or transmitted to the verification module for random number voice authentication.

[0075] like Figure 5 , Figure 6 As shown, the working steps of the palmprint recognition module are:

[0076] The user places his palm in front of the camera of the palm print recognition module and clicks the palm print capture button to obtain the user's palm image.

[0077] Convert the user's palm image into YUV mode, and use the skin color threshold in the YUV mode to filter to obtain a binary black and white palm image;

[0078] Using the black and white user's palm image as a mask, obtain the user's palm image with the background removed;

[0079] According to the black and white user palm image, the user palm center is obtained based on the distance transformation and the region of interest, and the inscribed circle of the user palm center is obtained according to its maximum radius, and the inscribed square of the inscribed circle is intercepted to obtain the user palm print pattern;

[0080] The user's palm print pattern is transmitted to the storage module for storage, or transmitted to the verification module for palm print authentication.

[0081] like Figure 2 As shown, the random number voice authentication is specifically:

[0082] The verification module generates a random number with the same number of digits as the password and transmits it to the display module for display;

[0083] The user performs calculations based on the preset password and the current random number, and inputs a correction value through the voice recognition module;

[0084] The verification module reads the password pre-set by the user in the storage module and the correction value input by the input module, and verifies whether the result after adding the random number and the correction value bit by bit and modulo 10 bit by bit is equal to the password pre-set by the user. If so, the authentication result is set to authentication passed, otherwise it is set to authentication failed, and the authentication result is returned to the display module for display.

[0085] like Figure 3 , Figure 4 As shown, the palmprint authentication is specifically as follows:

[0086] The verification module reads the user's palm print pattern pre-entered by the user in the storage module and the user's palm print pattern input by the input module.

[0087] The mean hash algorithm and the interpolation hash algorithm are used to calculate the similarity between the input user palm print pattern and the pre-entered user palm print pattern. If the similarity is lower than the set threshold, the authentication result is set to authentication passed, otherwise it is set to authentication failed, and the authentication result is returned to the display module for display.

[0088] It should be noted here that the system provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure can be divided into different functional modules to complete all or part of the functions described above.

[0089] like Figure 2 As shown, in another embodiment of the present application, a multi-factor authentication method based on an AR device is also provided, which is applied to the multi-factor authentication system based on an AR device in the above embodiment, and includes the following steps:

[0090] S1. When a user uses an AR device for the first time, he / she needs to register an account with the multi-factor authentication system and save his / her basic personal information in the storage module of the multi-factor authentication system.

[0091] S2. In the user password entry stage, the user enters the user password for random number voice authentication through the input module, and the system binds the user password to the user account and stores it in the storage module;

[0092] S3, the user places his palm in front of the camera, and the multi-factor authentication system captures the user's palm print and extracts the user's palm print features, and binds the user's palm print features to the user account and stores them in the storage module;

[0093] like Figure 6 As shown, the multi-factor authentication system intercepts the user's palm print and extracts the user's palm print features, specifically including the following steps:

[0094] S31, the multi-factor authentication system captures the user's palm image;

[0095] S32, converting the user palm image obtained in step S31 into a YUV mode, filtering using a skin color threshold in the YUV mode to obtain a binary black-and-white palm image, and using the black-and-white image as a mask to obtain a user palm image with the background removed;

[0096] S33: According to the black and white image obtained in step S32, the center of the palm is obtained based on the distance transformation and the region of interest, and the inscribed circle of the palm is drawn according to the maximum radius. The inscribed square of the inscribed circle is intercepted to obtain the palm print pattern of the user.

[0097] S4. Select the user account that needs to be logged in;

[0098] S5. The multi-factor authentication system generates a random number and verifies the correction value entered by the user. If the verification fails, the user account to be logged in is reselected;

[0099] like Figure 4 As shown, the multi-factor authentication system generates a random number and verifies the correction value input by the user, specifically including the following steps:

[0100] S51, the multi-factor authentication system generates a random number for authentication using a random number generation algorithm, and displays the random number to the user through a display module;

[0101] S52, the user calculates the correction value according to the random number obtained in step S51 and the user password and inputs it into the system through voice input module;

[0102] S53. The multi-factor authentication system verifies the correction value entered by the user and returns a verification result, and displays the verification result to the user through a display module.

[0103] S6. The user inputs the palm print through the input module, and the multi-factor authentication system intercepts the user's palm print and extracts the user's palm print features, and then compares the user's palm print features with the palm print features of known users for verification. If the verification fails, the user account that needs to be logged in is reselected; if the verification succeeds, the verification is completed.

[0104] The multi-factor authentication system intercepts the user's palm print and extracts the user's palm print features, and then compares the user's palm print features with the known user's palm print features for verification, which specifically includes the following steps:

[0105] S61, the multi-factor authentication system captures the user's palm image;

[0106] S62, converting the user palm image obtained in step S61 into a YUV mode, filtering using a skin color threshold in the YUV mode to obtain a binary black-and-white image, and using the black-and-white image as a mask to obtain a user palm image with the background removed;

[0107] S63, according to the black and white picture obtained in step S62, the center of the palm is obtained based on the distance transformation and the region of interest, and the inscribed circle of the palm is drawn according to the maximum radius. The inscribed square of the inscribed circle is intercepted to obtain the palm print pattern of the user;

[0108] S64, using a mean hash algorithm and a difference hash algorithm to perform similarity calculation on the palm print pattern of the user obtained in step S63 and the palm print pattern of the selected login user account;

[0109] S65. Determine whether the verification is successful based on the palm print similarity obtained in step S64. If the similarity is lower than the set threshold, set the authentication result as successful. Otherwise, set it as failed. Return the authentication result to the display module for display.

[0110] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0111] The above embodiments are preferred implementation modes of the present invention, but the implementation modes of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present invention should be equivalent replacement methods and are included in the protection scope of the present invention.

Claims

1. A multi-factor authentication system based on AR devices, characterized in that: It includes an input module, a display module, a storage module and a verification module; The input module includes a voice recognition module and a palm print recognition module; the user inputs and recognizes voice and palm prints through the voice recognition module and the palm print recognition module; the input data is transmitted to the storage module or the verification module; The display module is used for the user interface display of the AR device, including the display of the authentication mode options, the display of the random number and the display of the authentication result; The storage module is used to receive and store the password and palm print entered by the user; The verification module is used to read the user's voice and palm print input by the input module, and perform random number voice authentication and palm print authentication with the password and palm print in the storage module, and return the authentication result to the display module for display; The random number voice authentication is specifically: The verification module generates a random number with the same number of digits as the password and transmits it to the display module for display; The user performs calculations based on the preset password and the current random number, and inputs a correction value through the voice recognition module; The verification module reads the password preset by the user in the storage module and the correction value input by the input module, and verifies whether the result after adding the random number and the correction value bit by bit and modulo 10 bit by bit is equal to the password preset by the user. If so, the authentication result is set as authentication passed, otherwise it is set as authentication failed, and the authentication result is returned to the display module for display; The palmprint authentication is specifically as follows: The verification module reads the user's palm print pattern pre-entered by the user in the storage module and the user's palm print pattern input by the input module; The mean hash algorithm and the interpolation hash algorithm are used to calculate the similarity between the input user palm print pattern and the pre-entered user palm print pattern. If the similarity is lower than the set threshold, the authentication result is set to authentication passed, otherwise it is set to authentication failed, and the authentication result is returned to the display module for display.

2. According to claim 1, the multi-factor authentication system based on AR device is characterized in that: The input module, display module, storage module and verification module acquire data or read file data and communicate between modules through the method provided by the C# script.

3. According to claim 1, the multi-factor authentication system based on AR device is characterized in that: The speech recognition module is used for speech input and recognition, specifically: Receive user's voice input; Upload the recorded voice input clips for recognition through the voice recognition API; Get the return result through the speech recognition API; The returned result is transmitted to the storage module for storage, or transmitted to the verification module for random number voice authentication.

4. According to claim 1, the multi-factor authentication system based on AR device is characterized in that: The palmprint recognition module is used to input and recognize palmprints, specifically: The user places his palm in front of the camera of the palm print recognition module and clicks the palm print capture button to obtain a picture of the user's palm; Convert the user's palm image into YUV mode, and use the skin color threshold in the YUV mode to filter to obtain a binary black and white palm image; Using the black and white user's palm image as a mask, obtain the user's palm image with the background removed; According to the black and white user palm image, the user palm center is obtained based on the distance transformation and the region of interest, and the inscribed circle of the user palm center is obtained according to its maximum radius, and the inscribed square of the inscribed circle is intercepted to obtain the user palm print pattern; The user's palm print pattern is transmitted to the storage module for storage, or transmitted to the verification module for palm print authentication.

5. A multi-factor authentication method based on an AR device, characterized in that: The multi-factor authentication system based on an AR device applied to any one of claims 1 to 4 comprises the following steps: The user registers an account with the multi-factor authentication system and saves basic personal information in the storage module of the multi-factor authentication system; The user inputs the user password and the user's palm print for random number voice authentication through the input module, and the multi-factor authentication system binds the user password to the user account and stores them in the storage module; The multi-factor authentication system intercepts the user's palm print and extracts the user's palm print features, binds the user's palm print features to the user account and stores them in the storage module; Select the user account you want to log in to; The multi-factor authentication system generates a random number and verifies the correct value entered by the user. If the verification fails, the user account that needs to be logged in is reselected; The user inputs the palm print through the input module, the verification module intercepts the user's palm print and extracts the user's palm print features, and then compares the user's palm print features with the palm print features of known users for authentication. If the authentication fails, the user account that needs to be logged in is reselected; if the authentication is successful, the authentication is completed.

6. According to claim 5, the multi-factor authentication method based on AR device is characterized in that: The multi-factor authentication system intercepts the user's palm print and extracts the user's palm print features, specifically comprising the following steps: The multi-factor authentication system captures the user's palm image; The user's palm image is converted into a YUV mode, and the skin color threshold in the YUV mode is used for filtering to obtain a binary black-and-white image. The black-and-white image is used as a mask to obtain the user's palm image with the background removed. According to the obtained black and white picture, the center of the palm is obtained based on the distance transformation and the region of interest, and the inscribed circle of the palm is drawn according to the maximum radius, and the inscribed square of the inscribed circle is intercepted to obtain the user's palm print pattern.

7. The multi-factor authentication method based on AR device according to claim 5, characterized in that: The multi-factor authentication system generates a random number and verifies the correction value input by the user, specifically including the following steps: The multi-factor authentication system generates a random number for authentication using a random number generation algorithm and displays the random number to the user through a display module; The user calculates the correction value based on the displayed random number and the user password and inputs it into the system through voice input module; The multi-factor authentication system verifies the correction value entered by the user and returns the verification result, and displays the verification result to the user through the display module.

8. The multi-factor authentication method based on AR device according to claim 5, characterized in that: The verification module intercepts the user's palm print and extracts the user's palm print features, and then compares the user's palm print features with the known user's palm print features for authentication, which specifically includes the following steps: The verification module captures the user's palm image; The user's palm image is converted into a YUV mode, and the skin color threshold in the YUV mode is used for filtering to obtain a binary black-and-white palm image. The black-and-white image is used as a mask to obtain the user's palm image with the background removed. According to the obtained black and white picture, the center of the palm is obtained based on the distance transformation and the region of interest, and the inscribed circle of the palm is drawn according to the maximum radius, and the inscribed square of the inscribed circle is intercepted to obtain the user's palm print pattern; Use mean hash algorithm and difference hash algorithm to calculate the similarity between the user's palm print pattern and the palm print pattern of the selected user account; The authentication is determined based on the obtained palm print similarity, and the result is displayed to the user through the display module.