HK1221795B - Method and device for identity authentication, terminal and server - Google Patents

Description

Identity authentication method, device, terminal and server

Technical Field

The present application relates to the field of communication technologies, and in particular to identity authentication methods, devices, terminals, and servers.

Background Art

With the development of smart terminals and network applications, users can access various network applications through various application clients installed on their terminals, such as social instant messaging applications and shopping applications. During the access process, user identity authentication is often required so that users can use various application functions after passing the identity authentication.

In existing technologies, identity authentication often requires users to enter a password on an authentication interface. The server verifies that the entered password matches the password used during user registration, confirming that the user has passed authentication. However, passwords are often simple combinations of numbers and letters, making them easily stolen by malicious third parties. Therefore, existing identity authentication methods are less reliable, making it easy for user information to be stolen and resulting in low authentication security.

Summary of the Invention

The present application provides an identity authentication method, device, terminal and server to solve the problem that the identity authentication methods in the prior art have poor reliability and low security.

According to a first aspect of an embodiment of the present application, there is provided an identity authentication method, the method comprising:

When the user performs identity authentication, the server receives the dynamic face authentication prompt information;

Obtaining gesture recognition information of the dynamic facial authentication prompt information by identifying the facial gesture presented by the user;

The gesture recognition information is sent to the server, so that the server determines that the user has passed the identity authentication when verifying that the gesture recognition information is consistent with the face dynamic authentication prompt information.

According to a second aspect of an embodiment of the present application, there is provided an identity authentication method, the method comprising:

When the user authenticates his/her identity, a dynamic facial authentication prompt message is sent to the terminal;

receiving gesture recognition information sent by the terminal, wherein the gesture recognition information is gesture recognition information obtained by the terminal by recognizing the facial gesture presented by the user according to the dynamic facial authentication prompt information;

When it is verified that the gesture recognition information is consistent with the face dynamic authentication prompt information, it is determined that the user has passed the identity authentication.

According to a third aspect of an embodiment of the present application, there is provided an identity authentication device, the device comprising:

The receiving unit is used to receive the face dynamic authentication prompt information sent by the server when the user performs identity authentication;

A recognition unit, configured to obtain gesture recognition information of the dynamic facial authentication prompt information by recognizing the facial gesture presented by the user;

The sending unit is used to send the gesture recognition information to the server, so that the server determines that the user has passed the identity authentication when verifying that the gesture recognition information is consistent with the face dynamic authentication prompt information.

According to a fourth aspect of an embodiment of the present application, there is provided an identity authentication device, the device comprising:

The sending unit is used to send dynamic face authentication prompt information to the terminal when the user performs identity authentication;

a receiving unit, configured to receive gesture recognition information sent by the terminal, wherein the gesture recognition information is gesture recognition information obtained by the terminal by recognizing the facial gesture presented by the user according to the dynamic facial authentication prompt information;

The determination unit is configured to determine that the user has passed the identity authentication when verifying that the gesture recognition information is consistent with the face dynamic authentication prompt information.

According to a fifth aspect of an embodiment of the present application, a terminal is provided, including:

a processor; a memory for storing instructions executable by the processor;

Wherein, the processor is configured to:

When the user performs identity authentication, the server receives the dynamic face authentication prompt information;

Obtaining gesture recognition information of the dynamic facial authentication prompt information by identifying the facial gesture presented by the user;

The gesture recognition information is sent to the server, so that the server determines that the user has passed the identity authentication when verifying that the gesture recognition information is consistent with the face dynamic authentication prompt information.

According to a sixth aspect of an embodiment of the present application, a server is provided, including:

a processor; a memory for storing instructions executable by the processor;

Wherein, the processor is configured to:

When the user authenticates his/her identity, a dynamic facial authentication prompt message is sent to the terminal;

receiving gesture recognition information sent by the terminal, wherein the gesture recognition information is gesture recognition information obtained by the terminal by recognizing the facial gesture presented by the user according to the dynamic facial authentication prompt information;

When it is verified that the gesture recognition information is consistent with the face dynamic authentication prompt information, it is determined that the user has passed the identity authentication.

In the embodiment of the present application, when authenticating a user, the server sends a dynamic authentication prompt message to the terminal. The terminal obtains posture recognition information of the dynamic facial authentication prompt message by identifying the facial posture presented by the user, and sends it to the server. When the server verifies that the posture recognition information is consistent with the dynamic facial authentication prompt message, it determines that the user has passed the identity authentication. Applying the embodiment of the present application, the user's identity can be authenticated with high security through dynamic facial authentication. Compared with the existing authentication method using an authentication password, the authentication information cannot be stolen by malicious third parties, which improves the reliability of authentication. In addition, dynamic facial authentication can identify the user as a live user, thereby further improving the accuracy of identity authentication and reducing security risks in the authentication process.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic diagram of an identity authentication scenario according to an embodiment of the present application;

FIG2A is a flow chart of an embodiment of the identity authentication method of the present application;

FIG2B is a flow chart of another embodiment of the identity authentication method of the present application;

FIG3A is a flow chart of another embodiment of the identity authentication method of the present application;

FIG3B is a schematic diagram of a head posture during face recognition in an embodiment of the present application;

FIG4A is a flow chart of another embodiment of the identity authentication method of the present application;

FIG4B and FIG4C are schematic diagrams of facial key points in an embodiment of the present application;

FIG5 is a hardware structure diagram of the device where the identity authentication device of this application is located;

FIG6 is a block diagram of an embodiment of the identity authentication device of the present application;

FIG7 is a block diagram of another embodiment of the identity authentication device of the present application.

DETAILED DESCRIPTION

Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It should be understood that although the terms first, second, third, etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

In a scenario based on Internet communication, users can access various network applications through various application clients installed on their terminals. During the access process, users often need to perform identity authentication. However, in the prior art, authentication passwords are usually used to authenticate user identities. Authentication passwords are usually simple combinations of numbers and letters, which can be easily stolen by malicious third parties. Therefore, existing identity authentication methods are less reliable and less secure. Based on this, see Figure 1, which is a schematic diagram of an application scenario for implementing identity authentication in an embodiment of the present application: users complete identity authentication of users through interaction between their terminals and servers. Communication between the terminal and the server can be completed based on a network, which includes various wireless networks or wired networks, and this embodiment of the present application does not limit this. Among them, the terminal can specifically be a mobile phone, a tablet computer, a personal computer, etc. In the application scenario shown in Figure 1, two databases can be set up on the server, namely a facial feature information database and a facial dynamic authentication prompt information database.

During the face registration stage, the terminal can obtain the facial feature information of the registered user and send it to the server, which will save the facial feature information of the registered user to the facial feature information database. During the identity authentication stage, face authentication can be performed first. At this time, the user sends the acquired facial feature information to the server. When the server verifies that the facial feature information matches the facial feature information of the user stored in the facial feature information database, it can be preliminarily determined that the user currently undergoing identity authentication is the user himself. Then, face dynamic authentication is performed. At this time, the server can return the face dynamic authentication prompt information obtained from the face dynamic authentication prompt information database to the user. When the terminal recognizes the facial posture presented by the user, the posture recognition information of the face dynamic authentication prompt information is obtained and sent to the server. When the server verifies that the posture recognition information is consistent with the face dynamic authentication prompt information, it can be known that the currently authenticated user is a living user, thereby finally determining that the user has passed the identity authentication. For the sake of convenience of description, in the embodiment of the present application, the facial feature information of the user obtained in the face registration stage can be referred to as the second facial feature information, and the facial feature information of the user obtained in the face authentication stage can be referred to as the first facial feature information. The embodiment of the present application is described in detail below.

2A is a flow chart of an embodiment of the identity authentication method of the present application, which is described from the perspective of a terminal implementing identity authentication.

Step 201: When the user performs identity authentication, the user receives dynamic facial authentication prompt information sent by the server.

In an embodiment of the present application, the server can randomly extract facial dynamic authentication prompt information from the facial dynamic authentication prompt information data and return it to the terminal. The facial dynamic authentication prompt information may include at least one of the following information: facial expression prompt information, such as closing eyes, opening mouth, turning head, etc.; voice reading prompt information, such as paying 20 yuan, etc.

Optionally, before receiving the dynamic facial authentication prompt information sent by the server, the terminal can first obtain the user's facial feature information, and use the facial feature information obtained during the identity authentication as the user's first facial information. After sending the user's first facial feature information to the server, the server sends the dynamic facial authentication prompt information to the terminal when verifying that the first facial feature information matches the saved second facial feature information.

Among them, when obtaining the user's facial feature information, the terminal can start the integrated camera device thereon, such as a camera, to detect the user's face. When the face is detected, the user's face is tracked. During the face tracking process, facial images are obtained at preset time intervals. For each facial image obtained, it is determined whether the facial image meets the preset feature extraction conditions. If the feature extraction conditions are met, the user's facial feature information is extracted from the facial image.

Among them, after the server receives the user's first facial feature information, it can search the facial feature information database according to the user's username, obtain the second facial feature information corresponding to the username, and then use a preset comparison method to compare the first facial feature information and the second facial feature information. If the feature comparison value is within a preset similarity range, it can be determined that the first facial feature information matches the second facial feature information. After determining that the first facial feature information matches the second facial feature information, it can be determined that the user has passed the facial authentication. At this time, the server sends a facial dynamic authentication prompt message to the terminal.

Step 202: Obtain gesture recognition information of dynamic facial authentication prompt information by identifying the facial gesture presented by the user.

In an embodiment of the present application, after the terminal receives the dynamic facial authentication prompt information, the dynamic facial authentication prompt information is displayed on the identity authentication interface. The user can present the corresponding facial posture based on this information. When the terminal recognizes the facial posture, it can track the user's face and obtain facial tracking information. The facial tracking information can include at least one of facial key point position information and head posture information. The terminal then obtains the user's posture recognition information by analyzing the facial tracking information. For example, the facial key point position information can be used to determine whether the user closes his eyes or opens his mouth according to the facial expression prompt information, or the user's mouth shape when reading the voice prompt information (the pronunciation of each word corresponds to the mouth shape, and the user's posture recognition information can be determined by the mouth shape); the head posture information can be used to determine whether the user turns his head or lowers his head.

Step 203: Send the gesture recognition information to the server, so that the server determines that the user has passed the identity authentication when verifying that the gesture recognition information is consistent with the face dynamic authentication prompt information.

For the server, it may be necessary to authenticate multiple users at the same time. If different dynamic authentication prompt information is sent to different users, then in step 201, the server can send the face dynamic authentication prompt information to the terminal and record the correspondence between the user's username and the face dynamic authentication prompt information; in this step, after the terminal sends the posture recognition information to the server, the server obtains the corresponding face dynamic authentication prompt information based on the user's username, and when it is verified that the posture recognition information is consistent with the face dynamic authentication prompt information, it indicates that the user is a living user, and at this time it is determined that the user has passed the identity authentication.

In addition, if the face dynamic authentication prompt information in step 201 is voice reading prompt information, the terminal can obtain the user's audio information in addition to the user's mouth shape, and obtain the voice information read by the user through voice recognition of the audio information, so that the server can compare the voice information with the voice reading prompt information to see if they are consistent, and determine that the user has passed the identity authentication if they are consistent.

2B is a flow chart of another embodiment of the identity authentication method of the present application, which is described from the perspective of the server side implementing the identity authentication:

Step 211: When the user performs identity authentication, a dynamic face authentication prompt message is sent to the terminal.

Step 212: receiving gesture recognition information sent by the terminal, wherein the gesture recognition information is gesture recognition information obtained by the terminal by recognizing the facial gesture presented by the user according to the dynamic facial authentication prompt information.

Step 213: When the verification gesture recognition information is consistent with the face dynamic authentication prompt information, it is determined that the user has passed the identity authentication.

It should be noted that the difference between the identity authentication process shown in the above Figure 2B and the identity authentication process shown in Figure 2A is only the difference in the execution subject, that is, Figure 2A is described from the terminal side, while Figure 2B is described from the server side. Therefore, the relevant implementation process in the embodiment of Figure 2B can be found in the description in the aforementioned Figure 2A, and will not be repeated here.

It can be seen from the above embodiments that this embodiment can perform high-security authentication of user identity through dynamic facial authentication. Compared with the existing authentication method using authentication passwords, the authentication information will not be stolen by malicious third parties, which improves the reliability of authentication. In addition, dynamic facial authentication can identify users as living users, thereby further improving the accuracy of identity authentication and reducing security risks in the authentication process.

FIG3A is another embodiment of the identity authentication method of the present application, which shows the face registration process in detail:

Step 301: The user registers with the server through the terminal.

Step 302: When the terminal detects the user's face, it tracks the user's face.

Typically, terminals are integrated with a camera, such as a webcam. This embodiment can be configured by default to automatically activate the camera to detect the user's face upon user registration. Typically, the user can hold the terminal and aim the camera at their face. Once the camera detects a face, the terminal can track the user's face using a face tracking algorithm. It should be noted that various existing face tracking algorithms can be used in this embodiment of the present application, which will not be detailed here.

Step 303: The terminal obtains facial images at preset time intervals during the face tracking process.

During face tracking, the terminal obtains face images through a camera at preset time intervals. The time interval is set to avoid extracting substantially identical face images. For example, the preset time interval may be 3 seconds.

Step 304: Determine whether the clarity of the facial image meets a preset clarity threshold. If so, execute step 305; otherwise, end the current process.

For the facial image obtained in step 303, its clarity can be first determined to exclude facial images with insufficient clarity. At this point, the terminal can call a pre-set fuzzy judgment function to determine whether the clarity of the facial image meets the clarity threshold. The fuzzy judgment function can adopt the fuzzy judgment function of existing image recognition processing technology, which is not limited in this embodiment of the present application. For facial images that meet the clarity threshold, step 305 is executed. For facial images that do not meet the clarity threshold, they are directly discarded, and then the process returns to step 303.

Step 305: The terminal extracts head posture information from the face image.

After determining in step 304 that the acquired facial image is a clear facial image, the terminal extracts head posture information from the facial image. FIG3B is a schematic diagram of head posture in an embodiment of the present application. In this embodiment, the head posture information may include at least one of the following angles: a low head tilt angle, a side face angle, and a tilted head angle.

Step 306: The terminal determines whether each angle included in the head posture information is within a preset angle range. If so, step 307 is executed; otherwise, the current process ends.

In this embodiment of the present application, the head posture information can be used to determine whether the facial image is a frontal image of the user. In this case, the terminal can determine whether each angle included in the head posture information is within a preset angle range, for example, the preset angle range is 0 degrees to 10 degrees. For the facial image corresponding to the head posture information with a positive judgment result, step 307 is executed; for the facial image corresponding to the head posture information with a negative judgment result, the terminal directly discards the facial image and returns to step 303.

Step 307: The terminal extracts the user's facial feature information from the facial image.

The embodiments of the present application may employ an LBP (Linear Back Projection) feature extraction algorithm to extract facial feature vector values from a facial image as the user's facial feature information. Of course, the embodiments of the present application are not limited to a specific algorithm for facial feature extraction; any facial feature extraction algorithm used in existing image processing techniques may be applicable to the embodiments of the present application, such as a windowed Fourier transform Gabor feature extraction algorithm.

In order to ensure the accuracy of face recognition in the subsequent identity authentication stage, in the face registration stage, for the same registered user, the user's facial feature information can be extracted from multiple face images. The number of the multiple face images can be pre-set, for example, 5. Accordingly, according to the set number of face images, the aforementioned steps 303 to 307 can be executed repeatedly to obtain face images that meet the preset number and extract facial feature information from them.

Step 308: The terminal sends the facial feature information to the server.

Step 309: The server saves the correspondence between the registered user's username and the facial features, and ends the current process.

In this embodiment, after the server receives the facial feature information sent by the terminal, it can save the correspondence between the registered user's username and facial features in the facial feature information database. When multiple facial feature information is received, the correspondence between the username and multiple facial feature information is saved accordingly.

Referring to FIG4A , another embodiment of the identity authentication method of the present application is shown. This embodiment is based on the face registration process shown in FIG3 and describes in detail the process of authenticating the user:

Step 401: Start authenticating the user.

Step 402: The terminal obtains the user's first facial feature information.

During the identity authentication process, the way in which the terminal obtains the user's facial feature information is consistent with the way in which facial feature information is obtained during the face registration process shown in Figure 3 above, specifically consistent with steps 302 to 307 shown in Figure 3, and will not be repeated here.

In this step, the terminal can obtain at least one first facial feature information.

Step 403: The terminal sends the user's first facial feature information to the server.

Step 404: The server verifies whether the first facial feature information matches the saved second facial feature information of the user. If so, step 405 is executed; otherwise, the current process ends.

In an embodiment of the present application, after the server receives the user's first facial feature information, it can search the facial feature information database based on the user's username to obtain the second facial feature information corresponding to the username, and then use a preset comparison method to compare the first facial feature information and the second facial feature information. If the feature comparison value is within a preset similarity range, it can be determined that the first facial feature information matches the second facial feature information.

Assume that the facial feature information in the embodiment of the present application is a facial feature vector extracted by the LBP algorithm:

In one example, the first facial feature information and the second facial feature information may be compared using a Euclidean distance comparison method. The sum of squares of the differences between the second facial feature vector and the first facial feature vector is calculated. If the sum of squares is less than a preset threshold, it can be determined that the person being authenticated is the user.

In another example, the cosine distance comparison method can be used to compare the first facial feature information and the second facial feature. Assuming that the first facial feature vector is V1 and the second facial feature vector is V2, the following formula value can be calculated: V2*V1/(|V1|*|V2|). If the formula value is greater than the preset threshold, it can be determined that the person performing identity authentication is the user himself.

Step 405: The server sends a dynamic face authentication prompt message to the terminal.

When the server verifies that the first facial feature information matches the second facial feature information, it determines that the person being authenticated is the user, and the dynamic facial authentication process begins. The server can randomly extract a dynamic facial authentication prompt information from the dynamic facial authentication prompt information database.

In this embodiment, the dynamic facial authentication prompt information may include facial expression prompt information or voice reading prompt information. For facial expression prompt information, the action suggested is usually an action that the user can easily perform through facial gestures, such as opening the mouth, closing the eyes, turning the head, etc.; for voice reading prompt information, the message is usually relatively short, so that the user can read it easily during authentication and the terminal can recognize the user's facial gesture when reading it.

Step 406: The terminal obtains face tracking information by tracking the user's face.

After receiving the dynamic facial authentication prompt, the terminal can display the dynamic facial authentication prompt on the authentication interface. The user can then present a corresponding facial pose based on this information. During the presentation process, the terminal uses a face tracking algorithm to obtain the user's facial tracking information. The facial tracking information may include at least one of the following: facial key point location information and head pose information.

Step 407: The terminal analyzes the face tracking information to obtain the user's gesture recognition information.

In an example, assuming that the prompt information for dynamic facial authentication is "open your mouth", the user will make a corresponding action of opening his mouth. The terminal can obtain facial key point position information by tracking the user's face, specifically the key point position information of the mouth. See Figures 4B and 4C, which are schematic diagrams of facial key point position information in an embodiment of the present application: Figure 4B is the user's mouth key point position information extracted under normal conditions, and Figure 4C is the user's mouth key point position information extracted after the user presents an "open mouth" gesture. By comparing the key point position information extracted from Figures 4B and 4C, that is, comparing the coordinate distances of the upper and lower key point positions of the mouth, the user's posture recognition information can be obtained as "open mouth".

In another example, assuming that the prompt information for dynamic facial authentication is "turn head", the user will turn his head accordingly. The terminal can obtain the head posture information by tracking the user's face, specifically the three corners shown in Figure 3B. If the angle values of the three corners meet the angle value range defined by "turn head", the user's posture recognition information can be obtained as "turn head".

Step 408: The terminal sends the gesture recognition information to the server.

Step 409: The server verifies whether the gesture recognition information is consistent with the dynamic face authentication prompt information. If so, step 410 is executed; otherwise, the current process ends.

Step 410: The server determines that the user has passed the identity authentication and ends the current process.

It can be seen from the above embodiments that this embodiment combines face recognition and dynamic authentication to perform high-security authentication of user identity, wherein face recognition can preliminarily verify whether it is the user himself. Compared with the existing authentication method using authentication passwords, authentication information is not easily stolen by malicious third parties, which improves the reliability of authentication. Moreover, on the basis of confirming that it is the user himself, dynamic face authentication can identify the user as a living user, thereby further improving the accuracy of identity authentication and reducing the security risks in the authentication process.

Corresponding to the embodiment of the identity authentication method of the present application, the present application also provides embodiments of an identity authentication device, a terminal and a server.

The embodiments of the identity authentication device of the present application can be applied to terminals and servers respectively. The device embodiments can be implemented by software, or by hardware or a combination of software and hardware. Taking software implementation as an example, as a device in a logical sense, it is formed by the processor of the device in which it is located reading the corresponding computer program instructions in the non-volatile memory into the memory and running them. From the hardware level, as shown in Figure 5, it is a hardware structure diagram of the device in which the identity authentication device of the present application is located. In addition to the processor, memory, network interface, and non-volatile memory shown in Figure 5, the device in which the device is located in the embodiment can also include other hardware according to the actual function of the device. For example, for a terminal, it may include a camera, a touch screen, a communication component, etc. For a server, it may include a forwarding chip responsible for processing messages, etc.

6 , which is a block diagram of an embodiment of an identity authentication device of the present application, the identity authentication device may be applied on a terminal, and the device includes: a receiving unit 610 , an identification unit 620 and a sending unit 630 .

The receiving unit 610 is configured to receive dynamic facial authentication prompt information sent by the server when the user performs identity authentication;

The recognition unit 620 is configured to obtain gesture recognition information of the dynamic facial authentication prompt information by recognizing the facial gesture presented by the user;

The sending unit 630 is configured to send the gesture recognition information to the server, so that the server determines that the user has passed the identity authentication when verifying that the gesture recognition information is consistent with the dynamic face authentication prompt information.

In an alternative implementation:

The identification unit 620 may include (not shown in FIG6 ):

a face information obtaining subunit, configured to obtain face tracking information by tracking the face of the user when the user presents a face gesture according to the face dynamic authentication prompt information;

The face information analysis subunit is used to analyze the face tracking information to obtain the user's posture recognition information.

Among them, the facial information analysis subunit can be specifically used to obtain the user's expression posture recognition information by analyzing the facial key point position information when the facial tracking information is facial key point position information, and to obtain the user's head rotation recognition information by analyzing the head posture information when the facial tracking information is head posture information.

The dynamic face authentication prompt information may include at least one of the following information: facial expression prompt information, and voice reading prompt information.

In another alternative implementation:

The apparatus may further comprise (not shown in FIG6 ):

an acquiring unit, configured to acquire facial feature information of the user, and use the facial feature information acquired during identity authentication as first facial feature information of the user;

The sending unit 630 can also be used to send the user's first facial feature information to the server, so that the server sends the dynamic facial authentication prompt information when verifying that the first facial feature information matches the saved second facial feature information of the user.

Optionally, the acquisition unit can also be used to obtain the facial feature information of the user when the user registers, and use the facial feature information obtained during registration as the second facial feature information of the user; the sending unit 630 can also be used to send the second facial feature information to the server, so that the server saves the correspondence between the user's username and the second facial feature.

Optionally, the acquisition unit may include: a face tracking subunit, used to track the face of the user when the user's face is detected; an image acquisition subunit, used to acquire a face image at a preset time interval during the face tracking process; a condition judgment subunit, used to judge whether the face image meets a preset feature extraction condition; and a feature extraction subunit, used to extract the user's facial feature information from the face image if the feature extraction condition is met.

The condition judgment subunit may further include:

a clarity judgment module, configured to judge whether the clarity of the facial image meets a preset clarity threshold;

a posture information extraction module, configured to extract head posture information from the face image if the clarity threshold is met, the head posture information including at least one of the following angles: a low head tilt angle, a side face angle, and a tilted head angle;

An angle judgment module, used to judge whether each angle included in the head posture information is within a preset angle range;

The judgment and determination module is used to determine whether the face image meets the feature extraction condition if it is within a preset angle range.

Among them, the feature extraction subunit can be specifically used to adopt a preset feature extraction algorithm to extract facial feature vector values from the facial image as the facial feature information of the user; wherein, the preset feature extraction algorithm may include: linear back projection LBP feature extraction algorithm, or windowed Fourier transform Gabor feature extraction algorithm, etc.

7 , which is a block diagram of another embodiment of the identity authentication device of the present application, the identity authentication device may be applied on a server, and the device includes: a sending unit 710 , a receiving unit 720 and a determining unit 730 .

The sending unit 710 is used to send dynamic face authentication prompt information to the terminal when the user performs identity authentication;

A receiving unit 720 is configured to receive gesture recognition information sent by the terminal, where the gesture recognition information is obtained by the terminal by recognizing the facial gesture presented by the user according to the dynamic facial authentication prompt information;

The determination unit 730 is configured to determine that the user has passed the identity authentication when verifying that the gesture recognition information is consistent with the dynamic face authentication prompt information.

In an alternative implementation:

The receiving unit 720 may also be configured to receive the first facial feature information of the user sent by the terminal;

The apparatus may further include (not shown in FIG7 ): a verification unit configured to verify whether the first facial feature information matches the saved second facial feature information of the user;

The sending unit 710 may be specifically configured to send dynamic face authentication prompt information to the terminal during matching.

Optionally, the receiving unit 720 can also be used to receive the second facial feature information of the user sent by the terminal when the user registers; the device can also include (not shown in Figure 7): a saving unit, used to save the correspondence between the user's username and the second facial feature information.

Optionally, the verification unit may include: a feature search subunit for searching the corresponding relationship based on the user's username to obtain second facial feature information corresponding to the username; a feature comparison subunit for comparing the first facial feature information and the second facial feature information according to a preset comparison method; and a match determination subunit for determining that the first facial feature information and the second facial feature information match if the feature comparison value is within a preset similarity range. The preset comparison methods that can be used by the feature comparison subunit include: a Euclidean distance comparison method or a cosine distance comparison method.

The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

It can be seen from the above embodiments that when authenticating a user, the user identity can be highly securely authenticated through dynamic facial authentication. Compared with the existing authentication method using an authentication password, the authentication information will not be stolen by malicious third parties, which improves the reliability of authentication. In addition, dynamic facial authentication can identify the user as a living user, thereby further improving the accuracy of identity authentication and reducing security risks in the authentication process.

Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims (24)

1. An identity authentication method, characterized in that the method comprises: When a user performs identity authentication, the system receives a dynamic facial authentication prompt message sent by the server; wherein the dynamic facial authentication prompt message includes at least one of the following: facial expression prompt message and voice reading prompt message; By recognizing the facial posture presented by the user, the posture recognition information of the facial expression prompt information is obtained; By recognizing the user's audio information, the voice information of the voice reading prompt is obtained; The gesture recognition information and voice information are sent to the server so that the server determines that the user has passed identity authentication when verifying that the gesture recognition information is consistent with the facial expression prompt information and that the voice information is consistent with the voice reading prompt information. When the facial dynamic authentication prompt is a voice reading prompt, the mouth shape recognition information of the voice reading prompt is obtained by recognizing the mouth shape posture corresponding to the pronunciation of each word when the user reads the voice reading prompt. By recognizing the user's audio information, the voice information of the voice reading prompt is obtained; The lip-reading recognition information and voice information are sent to the server so that the server determines that the user has passed identity authentication when it verifies that the lip-reading recognition information matches the lip shape of the voice reading prompt information and when it verifies that the voice information matches the voice reading prompt information. 2. The method according to claim 1, characterized in that, obtaining the posture recognition information of the facial expression prompt information by recognizing the facial posture presented by the user includes: When the user presents a facial posture according to the facial expression prompt information, facial tracking information is obtained by performing facial tracking on the user; The user's pose recognition information is obtained by analyzing the face tracking information. 3. The method according to claim 2, wherein analyzing the face tracking information to obtain the user's pose recognition information includes: When the face tracking information is facial key point location information, the user's facial expression and posture recognition information is obtained by analyzing the facial key point location information. When the face tracking information is head posture information, the user's head rotation recognition information is obtained by analyzing the head posture information. 4. The method according to claim 1, characterized in that, before receiving the face dynamic authentication prompt information sent by the server, the method further includes: Obtain the user's facial feature information, and use the facial feature information obtained during identity authentication as the user's first facial feature information; The user's first facial feature information is sent to the server so that the server sends the dynamic facial authentication prompt information when verifying that the first facial feature information matches the user's saved second facial feature information. 5. The method according to claim 4, characterized in that the method further comprises: When a user registers, the user's facial feature information is obtained, and the facial feature information obtained during registration is used as the user's second facial feature information; The second facial feature information is sent to the server so that the server can save the correspondence between the user's username and the second facial feature. 6. The method according to claim 4 or 5, wherein obtaining the user's facial feature information includes: When the user's face is detected, face tracking is performed on the user; During the face tracking process, face images are acquired at preset time intervals; Determine whether the face image meets the preset feature extraction conditions; If the feature extraction conditions are met, then the user's facial feature information is extracted from the face image. 7. The method according to claim 6, wherein determining whether the face image meets the preset feature extraction conditions includes: Determine whether the clarity of the face image meets a preset clarity threshold; If the clarity threshold is met, then head posture information is extracted from the face image. The head posture information includes at least one of the following angles: low head tilt angle, side face angle, and head tilt angle. Determine whether each angle included in the human head posture information is within a preset angle range; If the angle is within the preset range, then the face image is determined to meet the feature extraction conditions. 8. An identity authentication method, characterized in that the method comprises: When a user performs identity authentication, a dynamic facial authentication prompt message is sent to the terminal; wherein, the dynamic facial authentication prompt message includes at least one of the following: facial expression prompt message and voice reading prompt message; The terminal receives posture recognition information and voice information. The posture recognition information is obtained by the terminal by recognizing the facial posture presented by the user according to the facial expression prompt information. The voice information is obtained by the terminal by recognizing the audio information emitted by the user according to the voice reading prompt information. When the gesture recognition information is verified to be consistent with the facial expression prompt information and the voice information is verified to be consistent with the voice reading prompt information, it is determined that the user has passed the identity authentication. When the facial dynamic authentication prompt is a voice reading prompt, the terminal receives lip shape recognition information and voice information. The lip shape recognition information is obtained by the terminal by recognizing the lip shape posture corresponding to the pronunciation of each word when the user reads the voice reading prompt. The voice information is obtained by the terminal by recognizing the audio information emitted by the user according to the voice reading prompt. When the lip-reading recognition information matches the lip-reading information in the voice reading prompt and the voice information matches the voice reading prompt, the user is determined to have passed identity authentication. 9. The method according to claim 8, characterized in that, before sending the dynamic face authentication prompt information to the terminal, the method further includes: Receive the user's first facial feature information sent by the terminal; Verify whether the first facial feature information matches the saved second facial feature information of the user; If a match is found, then the process of sending a dynamic facial authentication prompt to the terminal is executed. 10. The method according to claim 9, wherein the method further comprises: When the user registers, the terminal sends the user's second facial feature information. The correspondence between the user's username and the second facial feature information is saved. 11. The method according to claim 10, wherein verifying whether the first facial feature information matches the saved second facial feature information of the user includes: Based on the user's username, the corresponding relationship is searched to obtain the second facial feature information corresponding to the username; The first facial feature information and the second facial feature information are compared using a preset comparison method; If the feature comparison value is within a preset similarity range, then the first facial feature information is determined to match the second facial feature information. 12. An identity authentication device, characterized in that the device comprises: The receiving unit is used to receive dynamic facial authentication prompt information sent by the server when the user performs identity authentication; wherein, the dynamic facial authentication prompt information includes at least one of the following: facial expression prompt information and voice reading prompt information; The recognition unit is used to obtain the posture recognition information of the facial expression prompt information by recognizing the facial posture presented by the user, and to obtain the voice information of the voice reading prompt information by recognizing the user's audio information; The sending unit is configured to send the gesture recognition information and voice information to the server, so that the server determines that the user has passed authentication when verifying that the gesture recognition information is consistent with the facial expression prompt information and that the voice information is consistent with the voice reading prompt information. Wherein, when the face dynamic authentication prompt information is a voice reading prompt information, the recognition unit is used to obtain the mouth shape recognition information of the voice reading prompt information by recognizing the mouth shape posture corresponding to the pronunciation of each word when the user reads the voice reading prompt information, and to obtain the voice information of the voice reading prompt information by recognizing the user's audio information; The sending unit is used to send the lip-shape recognition information and voice information to the server, so that the server determines that the user has passed identity authentication when verifying that the lip-shape recognition information matches the lip shape of the voice reading prompt information and when verifying that the voice information matches the voice reading prompt information. 13. The apparatus according to claim 12, wherein the identification unit comprises: The face information acquisition subunit is used to obtain face tracking information by performing face tracking on the user when the user presents a face posture according to the facial expression and action prompt information; The face information analysis subunit is used to analyze the face tracking information to obtain the user's posture recognition information. 14. The apparatus according to claim 13, characterized in that, The face information analysis subunit is specifically used to obtain the user's expression and posture recognition information by analyzing the facial key point location information when the face tracking information is facial key point location information, and to obtain the user's head rotation recognition information by analyzing the head posture information when the face tracking information is head posture information. 15. The apparatus according to claim 12, wherein the apparatus further comprises: The acquisition unit is used to acquire the user's facial feature information and use the facial feature information acquired during identity authentication as the user's first facial feature information. The sending unit is further configured to send the user's first facial feature information to the server, so that the server sends the dynamic facial authentication prompt information when verifying that the first facial feature information matches the user's saved second facial feature information. 16. The apparatus according to claim 15, characterized in that, The acquisition unit is further configured to acquire the user's facial feature information when the user registers, and use the facial feature information acquired during registration as the user's second facial feature information; The sending unit is further configured to send the second facial feature information to the server, so that the server can save the correspondence between the user's username and the second facial feature. 17. The apparatus according to claim 15 or 16, wherein the acquiring unit comprises: A face tracking subunit is used to perform face tracking on the user when the user's face is detected. An image acquisition subunit is used to acquire face images at preset time intervals during the face tracking process; The condition judgment subunit is used to determine whether the face image meets the preset feature extraction conditions; The feature extraction subunit is used to extract the user's facial feature information from the face image if the feature extraction conditions are met. 18. The apparatus according to claim 17, wherein the condition determination subunit comprises: A sharpness determination module is used to determine whether the sharpness of the face image meets a preset sharpness threshold. The pose information extraction module is used to extract head pose information from the face image if the clarity threshold is met. The head pose information includes at least one of the following angles: low head tilt angle, side face angle, and head tilt angle. An angle determination module is used to determine whether each angle contained in the human head posture information is within a preset angle range; The determination module is used to determine that if the face image is within a preset angle range, it satisfies the feature extraction conditions. 19. An identity authentication device, characterized in that the device comprises: The sending unit is used to send dynamic facial authentication prompt information to the terminal when the user performs identity authentication; wherein, the dynamic facial authentication prompt information includes at least one of the following: facial expression prompt information and voice reading prompt information; The receiving unit is configured to receive posture recognition information and voice information sent by the terminal. The posture recognition information is obtained by the terminal by recognizing the facial posture presented by the user according to the facial expression prompt information. The voice information is obtained by the terminal by recognizing the audio information emitted by the user according to the voice reading prompt information. The determining unit is configured to determine that the user has passed identity authentication when verifying that the posture recognition information is consistent with the facial expression prompt information and that the voice information is consistent with the voice reading prompt information. Wherein, when the face dynamic authentication prompt information is a voice reading prompt information, the receiving unit is used to receive the lip shape recognition information and voice information sent by the terminal. The lip shape recognition information is the lip shape recognition information obtained by the terminal by recognizing the lip shape posture corresponding to the pronunciation of each word when the user reads the voice reading prompt information. The voice information is the voice information obtained by the terminal by recognizing the audio information emitted by the user according to the voice reading prompt information. The determining unit is used to determine that the user has passed identity authentication when verifying that the lip shape recognition information matches the lip shape of the voice reading prompt information and that the voice information matches the voice reading prompt information. 20. The apparatus according to claim 19, characterized in that, The receiving unit is further configured to receive the user's first facial feature information sent by the terminal; The device further includes: The verification unit is used to verify whether the first facial feature information matches the saved second facial feature information of the user; The sending unit is specifically used to send a dynamic face authentication prompt message to the terminal during matching. 21. The apparatus according to claim 20, characterized in that, The receiving unit is also configured to receive the user's second facial feature information sent by the terminal when the user registers; The device further includes: The storage unit is used to store the correspondence between the user's username and the second facial feature information. 22. The apparatus according to claim 21, wherein the verification unit comprises: The feature lookup subunit is used to look up the corresponding relationship based on the user's username and obtain the second facial feature information corresponding to the username; The feature comparison subunit is used to compare the first facial feature information and the second facial feature information according to a preset comparison method; The matching determination subunit is used to determine that the first facial feature information matches the second facial feature information if the feature comparison value is within a preset similarity range. 23. A terminal, characterized in that it comprises: Processor; memory for storing instructions executable by the processor; The processor is configured as follows: When a user performs identity authentication, the system receives a dynamic facial authentication prompt message sent by the server; wherein the dynamic facial authentication prompt message includes at least one of the following: facial expression prompt message and voice reading prompt message; By recognizing the facial posture presented by the user, the posture recognition information of the facial expression prompt information is obtained; By recognizing the user's audio information, the voice information of the voice reading prompt is obtained; The gesture recognition information and voice information are sent to the server so that the server determines that the user has passed identity authentication when verifying that the gesture recognition information is consistent with the facial expression prompt information and that the voice information is consistent with the voice reading prompt information. When the facial dynamic authentication prompt is a voice reading prompt, the mouth shape recognition information of the voice reading prompt is obtained by recognizing the mouth shape posture corresponding to the pronunciation of each word when the user reads the voice reading prompt. By recognizing the user's audio information, the voice information of the voice reading prompt is obtained; The lip-reading recognition information and voice information are sent to the server so that the server determines that the user has passed identity authentication when it verifies that the lip-reading recognition information matches the lip shape of the voice reading prompt information and when it verifies that the voice information matches the voice reading prompt information. 24. A server, characterized in that it comprises: Processor; memory for storing instructions executable by the processor; The processor is configured as follows: When a user performs identity authentication, a dynamic facial authentication prompt message is sent to the terminal; wherein, the dynamic facial authentication prompt message includes at least one of the following: facial expression prompt message and voice reading prompt message; The terminal receives posture recognition information and voice information. The posture recognition information is obtained by the terminal by recognizing the facial posture presented by the user according to the facial expression prompt information. The voice information is obtained by the terminal by recognizing the audio information emitted by the user according to the voice reading prompt information. When the gesture recognition information is verified to be consistent with the facial expression prompt information and the voice information is verified to be consistent with the voice reading prompt information, it is determined that the user has passed the identity authentication. When the facial dynamic authentication prompt is a voice reading prompt, the terminal receives lip shape recognition information and voice information. The lip shape recognition information is obtained by the terminal by recognizing the lip shape posture corresponding to the pronunciation of each word when the user reads the voice reading prompt. The voice information is obtained by the terminal by recognizing the audio information emitted by the user according to the voice reading prompt. When the lip-reading recognition information matches the lip-reading information in the voice reading prompt and the voice information matches the voice reading prompt, the user is determined to have passed identity authentication.