Identity authentication method and apparatus, terminal and server

• US 10,601,821 B2
• Filed: 03/02/2017
• Issued: 03/24/2020
• Est. Priority Date: 09/03/2014
• Status: Active Grant

• Current Assignee: Advanced New Technologies Company Limited (Ant Group Co., Ltd.)
• Original Assignee: Alibaba Group Holding Ltd.
• Inventors: Du, Zhijun
• Primary Examiner(s): Pwu, Jeffrey C
• Assistant Examiner(s): Cheema, Ali H.
• Application Number:
  US15/448,534
• Publication Number:
  US 20170180362A1
• Time in Patent Office: 1,118 Days
• Field of Search: 382116, 382104, 382103, 382118, 382195, 382224, 340 52, 34820711, 345158, 726 7
• CPC Class Codes: G06F 21/30 Authentication, i.e. establishing the identity or authorisation of security principals
• CPC Class Codes: G06F 21/305 by remotely controlling device operation
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 21/35 communicating wirelessly
• CPC Class Codes: G06F 21/45 Structures or tools for the administration of authentication
• CPC Class Codes: G06F 2221/2101 Auditing as a secondary aspect
• CPC Class Codes: G06F 2221/2103 Challenge-response
• CPC Class Codes: G06F 2221/2115 Third party
• CPC Class Codes: G06F 2221/2117 User registration
• CPC Class Codes: G06V 30/142 using hand-held instruments; Constructional details of the instruments
• CPC Class Codes: G06V 40/164 using holistic features
• CPC Class Codes: G06V 40/169 Holistic features and representations, i.e. based on the facial image taken as a whole
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G06V 40/176 Dynamic expression
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: H04L 63/08 for authentication of entities cryptographic mechanisms or cryptographic arrangements for entity authentication H04L9/32
• CPC Class Codes: H04L 63/0861 using biometrical features, e.g. fingerprint, retina-scan cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231

Abstract

A method, an apparatus, a terminal, and a server for identity authentication are disclosed. The method includes: receiving dynamic face authentication prompt information sent by a server during identity authentication of a user; obtaining gesture recognition information of the dynamic face authentication prompt information by recognizing a facial gesture presented by the user; and sending the gesture recognition information to the server to enable the server to confirm that the identity authentication is successful for the user in response to verifying that the gesture recognition information is consistent with the dynamic face authentication prompt information. Using the embodiments of the present application, a highly secure authentication can be performed on an identity of a user through dynamic face authentication. As compared with existing authentication methods using an authentication password, authentication information will not be stolen by a malicious third party, thus improving the reliability of authentication. Moreover, a user may be recognized as a live user through dynamic face authentication, thereby further improving the accuracy of identity authentication and reducing potential security risks during authentication.

Claims

1. An identity authentication method comprising:

acquiring facial feature information of a user, the acquiring the facial feature information of the user including;

tracking a face of the user upon detecting the face of the user;

acquiring multiple face images, a time interval between acquiring a first face image of the multiple face images and acquiring a second image of the multiple face images being more than a preset time interval to avoid extraction of a same face image;

determining that a resolution of a respective face image of the multiple face images meets a preset resolution threshold;

extracting head gesture information from the respective face image, the head gesture information including at least one of following angles including a head lowering or raising angle, a face turning angle, or a head leaning angle; and

determining whether a respective angle of the angles in the respective face image falls within a preset angle range;

discarding the respective face image in response to determining that the respective angle does not fall within the preset angle range; and

extracting the facial feature information of the user from the respective face image in response to determining that the respective angle falls within the preset angle range;

using the facial feature information as first facial feature information of the user;

sending the first facial feature information of the user to a server to allow the server to send dynamic face authentication prompt information that is randomly extracted from multiple dynamic human face authentication prompt information data, in response to verifying that the first facial feature information matches second facial feature information of the user that is stored, the multiple dynamic human face authentication prompt information data including expression action prompt information and voice read prompt information;

receiving the dynamic face authentication prompt information sent by the server;

obtaining gesture recognition information of the dynamic face authentication prompt information by recognizing a facial gesture presented by the user; and

sending the gesture recognition information to the server to enable the server to confirm that an identity authentication is successful for the user upon verifying that the gesture recognition information is consistent with the dynamic face authentication prompt information.

2. The method of claim 1, further comprising:

acquiring the facial feature information of the user during a user registration;

using the facial feature information acquired during the registration as the second facial feature information of the user; and

sending the second facial feature information to the server to enable the server to store a correspondence relationship between a user name of the user and the second facial feature information.

3. The method of claim 1, wherein the extracting the facial feature information of the user from the respective face image in response to determining that the respective angle falls within the preset angle range comprises:

determining that the respective face image meets a feature extraction condition when each angle falls within the preset angle range.

4. The method of claim 1, wherein the obtaining the gesture recognition information comprises:

obtaining face tracking information by tracking the face of the user when the user presents a facial gesture according to the dynamic face authentication prompt information; and

analyzing the face tracking information to obtain the gesture recognition information of the user.

5. The method of claim 4, wherein the analyzing the face tracking information to obtain the gesture recognition information of the user comprises:

when the face tracking information is facial key point position information, obtaining expression gesture recognition information of the user by analyzing the facial key point position information;

or

when the face tracking information is head gesture information, obtaining head turning recognition information of the user by analyzing the head gesture information.

6. The method of claim 1, wherein the expression action prompt information includes opening a mouth.

7. The method of claim 6, wherein:

the dynamic face authentication prompt information comprises the voice read prompt information; and

the obtaining the gesture recognition information comprises;

obtaining mouth shapes and audio information of the user; and

recognizing one or more mouth shapes of the user when reading the voice read prompt information and obtaining voice information of the user from the audio information through voice recognition,

wherein;

the recognizing the one or more mouth shapes and the obtaining the voice information enable the server to determine whether the voice information is consistent with the voice read prompt information when verifying the gesture recognition information; and

the identity authentication is determined to be successful for the user upon verifying that the voice information is consistent with the voice read prompt information and the gesture recognition information is consistent with the dynamic face authentication prompt information.

8. Memory storing computer-readable instructions, executable by one or more processors, that cause the one or more processors to perform acts comprising:

acquiring multiple face images of a user, a time interval between acquiring a first face image of the multiple face images and acquiring a second image of the multiple face images being more than a preset time interval to avoid extraction of a same face image;

extracting head gesture information from a face image of the multiple face images, the head gesture information including at least one of following angles including a head lowering or raising angle, a face turning angle, or a head leaning angle;

determining whether a respective angle of the angles in the face image falls within a preset angle range;

discarding the face image in response to determining that the respective angle does not fall within the preset angle range; and

extracting facial feature information of the user from the face image in response to determining that the respective angle falls within the preset angle range; and

using the facial feature information as first facial feature information of the user;

sending the first facial feature information of the user to the server to allow the server to send the dynamic face authentication prompt information in response to verifying that the first facial feature information matches second facial feature information of the user that is stored;

receiving dynamic face authentication prompt information sent by a server during identity authentication of the user, the dynamic face authentication prompt information being randomly extracted from multiple dynamic human face authentication prompt information data including expression action prompt information and voice read prompt information;

obtaining gesture recognition information of the dynamic face authentication prompt information by recognizing a facial gesture presented by the user; and

sending the gesture recognition information to the server to enable the server to confirm that the identity authentication of the user is successful upon verifying that the gesture recognition information is consistent with the dynamic face authentication prompt information.

9. The memory of claim 8, wherein the obtaining the gesture recognition information comprises:

obtaining face tracking information by tracking the face of the user when the user presents a facial gesture according to the dynamic face authentication prompt information; and

analyzing the face tracking information to obtain the gesture recognition information of the user.

10. The memory of claim 9, wherein the analyzing the face tracking information to obtain the gesture recognition information of the user comprises:

obtaining expression gesture recognition information of the user by analyzing facial key point position information when the face tracking information is the facial key point position information;

or

obtaining head turning recognition information of the user by analyzing head gesture information when the face tracking information is the head gesture information.

11. The memory of claim 8, wherein the acts further comprise:

acquiring facial feature information of the user during a user registration;

using the facial feature information acquired during the registration as the second facial feature information of the user; and

sending the second facial feature information to the server to allow the server to store a correspondence relationship between a user name of the user and the second facial feature information.

12. The memory of claim 8, wherein the acquiring the multiple face images comprise:

determining that a resolution of the face image meets a preset resolution threshold;

extracting head gesture information from the face image, the head gesture information comprising at least one of following angles including a head lowering or raising angle, a face turning angle, or a head leaning angle;

determining that each angle of the angles in the face image falls within the preset angle range; and

determining that the face image meets a feature extraction condition.

13. The memory of claim 8, wherein the expression action prompt information includes opening a mouth.

14. The memory of claim 8, wherein the expression action prompt information comprises closing one or more eyes.

15. A terminal comprising:

one or more processors; and

memory storing computer-readable instructions, executable by the one or more processors, that cause the one or more processors to perform acts comprising;

acquiring multiple face images of a user, a time interval between acquiring a first face image of the multiple face images and acquiring a second image of the multiple face images being more than a preset time interval to avoid extraction of a same face image;

extracting head gesture information from a face image of the multiple face images, the head gesture information including at least one of following angles including a head lowering or raising angle, a face turning angle, or a head leaning angle;

determining whether a respective angle of the angles in the face image falls within a preset angle range;

discarding the face image in response to determining that the respective angle does not fall within the preset angle range; and

extracting facial feature information of the user from the face image in response to determining that the respective angle falls within the preset angle range;

using the facial feature information as first facial feature information of the user;

sending the first facial feature information of the user to a server to allow the server to send dynamic face authentication prompt information in response to verifying that the first facial feature information matches second facial feature information of the user that is stored;

receiving dynamic face authentication prompt information sent by the server;

obtaining gesture recognition information of the dynamic face authentication prompt information by recognizing a facial gesture presented by the user, the recognizing the facial gesture including comparing a respective coordinate distance between an upper key point position and a lower key point position of a mouth of the user; and

sending the gesture recognition information to the server to enable the server to confirm that the user passes the identity authentication upon verifying that the gesture recognition information is consistent with the dynamic face authentication prompt information.

16. The terminal of claim 15, wherein the acquiring the multiple face images comprises:

determining that a resolution of the face image meets a preset resolution threshold;

extracting head gesture information from the face image;

determining that each angle of the angles in the face image included in the head gesture information falls within the preset angle range; and

determining that the face image meets a feature extraction condition.

17. The terminal of claim 15, wherein:

the dynamic face authentication prompt information comprises voice read prompt information; and

the obtaining the gesture recognition information comprises;

obtaining mouth shapes and audio information of the user; and

recognizing one or more mouth shapes of the user when reading the voice read prompt information and obtaining voice information of the user from the audio information through voice recognition,

wherein;

the recognizing the one or more mouth shapes and the obtaining the voice information enable the server to determine whether the voice information is consistent with the voice read prompt information when verifying the gesture recognition information; and

the identity authentication is determined to be successful for the user upon verifying that the voice information is consistent with the voice read prompt information and the gesture recognition information is consistent with the dynamic face authentication prompt information.

18. The terminal of claim 15, wherein the acts further comprise:

acquiring the facial feature information of the user during a user registration;

using the facial feature information acquired during the registration as the second facial feature information of the user; and

sending the second facial feature information to the server to enable the server to store a correspondence relationship between a user name of the user and the second facial feature information.

19. The terminal of claim 15, wherein the obtaining the gesture recognition information comprises:

obtaining face tracking information by tracking the face of the user when the user presents a facial gesture according to the dynamic face authentication prompt information; and

analyzing the face tracking information to obtain the gesture recognition information of the user.

20. The terminal of claim 19, wherein the analyzing the face tracking information to obtain the gesture recognition information of the user comprises:

when the face tracking information is facial key point position information, obtaining expression gesture recognition information of the user by analyzing the facial key point position information;

or

when the face tracking information is head gesture information, obtaining head turning recognition information of the user by analyzing the head gesture information.